telli vs Deepgram Voice Agent
free-tier · usage-based · enterprise-custom
telli wins · 25–11 (25 drawn)
Agent building — building agents — abstractions, tool wiring, control flowAgent building
Building agents — abstractions, tool wiring, control flow
Agent ops
ai-native userMy coding agent can provision a complete voice agent end to end — create the agent, attach a number, and place a call — through the API, CLI, or MCP without touching the dashboard
weight 3 · round drawntelli's REST API documents endpoints for scheduling calls and importing/attaching phone numbers (telli-docs-17, telli-docs-19), and the MCP server lets AI tools talk to Charlie, who can 'build and refine agents' (telli-docs-11, telli-docs-22), suggesting agent creation is possible without the dashboard. However, there is no explicit API/CLI 'create agent' endpoint documented, no CLI tool is mentioned at all, and the MCP-driven agent creation is only described as an assistant chat capability rather than a deterministic API call — so a full end-to-end create→attach-number→place-call pipeline via one consistent interface is not clearly evidenced. Missing for 10: a documented create-agent API/CLI endpoint, confirmation MCP/Charlie can fully provision agents without any dashboard step, and an example combining all three steps in one flow.
- [claimed-docs] “Charlie: Build and refine agents, automate workflows, and analyze your calls with telli's built-in AI assistant.”
- [claimed-docs] “API Endpoints: Use telli's REST API to programmatically manage contacts, schedule calls, and integrate with your existing systems.”
- [claimed-docs] “Schedules a call at the earliest opportunity within the dialer window. May occur immediately or on the next business day depending on settin…”
- [claimed-docs] “Imports a phone number from your own SIP trunk provider. This allows you to use existing phone numbers with telli by configuring custom SIP …”
- [claimed-docs] “The telli MCP server lets AI tools like Claude, ChatGPT, and Codex talk to Charlie, telli's AI assistant, over the Model Context Protocol.”
- [probe] “PROBE openapi: HTTP 200 at https://docs.telli.com/openapi.json — contains "openapi" key”
- [probe] “official MCP server documented at https://docs.telli.com/integrations/mcp”
Deepgram documents agent creation via reusable agent configs (UUID-based), telephony connectivity for inbound/outbound calls, and a CLI with a built-in MCP server giving AI coding tools API access — the building blocks for programmatic provisioning exist. However, the evidence shows phone-call handling is done via a Twilio bridge (server code required) rather than a native Deepgram 'attach number/place call' API, and no doc shows the CLI or MCP server actually exposing agent-create + number-attach + call-place as a single end-to-end flow. Missing for 10: explicit CLI/MCP commands for provisioning a phone number and placing a call, and confirmation that this full workflow avoids external glue code/dashboard steps.
- [claimed-docs] “Reusable Agent Configurations allow you to define and persist the agent block of your Settings message using the Deepgram API. Once created,…”
- [claimed-docs] “Telephony: connect voice agents to phone networks for inbound and outbound calls.”
- [claimed-docs] “The dg CLI includes a built-in MCP (Model Context Protocol) server that gives AI coding tools direct access to Deepgram APIs.”
- [claimed-docs] “Twilio streams the call audio to your server, and your server bridges that audio to the Deepgram Voice Agent API, a single WebSocket that ru…”
- [probe] “official MCP server documented at https://developers.deepgram.com/developer-tools/agentic-tools”
- [probe] “official CLI documented at https://developers.deepgram.com/developer-tools/cli/getting-started”
ai-native userThe platform's own AI helps me author agents — generating or improving prompts, flows, and test cases from a description
weight 1 · round to telliCharlie, telli's built-in AI assistant, is documented as helping to 'build and refine agents, automate workflows, and analyze your calls,' which supports the core idea of AI-assisted agent authoring, and the MCP server lets external AI tools interact with Charlie too. However there's no concrete evidence of generating test cases from a description, or detailed examples of prompt/flow generation output. missing for 10: documented examples of Charlie generating/improving prompts or flows from a natural-language description, evidence of AI-generated test case creation, and independent/hands-on confirmation of these capabilities in practice.
- [claimed-docs] “Charlie: Build and refine agents, automate workflows, and analyze your calls with telli's built-in AI assistant.”
- [claimed-docs] “The telli MCP server lets AI tools like Claude, ChatGPT, and Codex talk to Charlie, telli's AI assistant, over the Model Context Protocol.”
- [probe] “official MCP server documented at https://docs.telli.com/integrations/mcp”
Deepgram Voice Agentnone0/10Evidence covers building agents manually (prompting, function calling, reusable configs, MCP server for coding tools) but there is no mention of the platform's own AI generating or improving prompts, flows, or test cases from a description; the MCP server exposes Deepgram APIs to external coding assistants rather than being an AI author within the platform itself.
- [claimed-docs] “Prompting: write system prompts that shape live-call behavior.”
- [claimed-docs] “Reusable Agent Configurations allow you to define and persist the agent block of your Settings message using the Deepgram API. Once created,…”
- [claimed-docs] “The dg CLI includes a built-in MCP (Model Context Protocol) server that gives AI coding tools direct access to Deepgram APIs.”
- [probe] “official MCP server documented at https://developers.deepgram.com/developer-tools/agentic-tools”
Build
developerBuild a working phone voice agent — prompt, voice, and phone number — and take my first live call within an hour
weight 3 · round drawntelli provides agent builder, test call feature, voice cloning, and phone number setup (forwarding or SIP trunk import) which together support building and testing a voice agent with prompt, voice, and number, but there's no explicit walkthrough or evidence confirming a full end-to-end setup can be completed within an hour or that phone number provisioning is instant/self-serve for new numbers. missing for 10: a documented quick-start/time-to-first-call benchmark, evidence of instant/native number provisioning (vs SIP/forwarding setup), and independent/hands-on confirmation of the full flow's speed.
- [claimed-docs] “In the agent builder, click Test call to open the dialog. Pick the agent version (your draft with unsaved changes or any saved revision)...”
- [claimed-docs] “Use the side-by-side view to listen to the recording while following along in the transcript.”
- [claimed-docs] “Voice cloning lets you give your agent a custom voice (your own, a colleague's, or a professional voice actor's), so the agent sounds exactl…”
- [claimed-docs] “Keep your public business number and forward incoming calls to a telli number. You configure the forwarding with your phone provider or PBX.”
- [claimed-docs] “Connect an existing number and phone system for incoming and outgoing calls. You need SIP trunk access from your provider.”
- [claimed-docs] “Imports a phone number from your own SIP trunk provider. This allows you to use existing phone numbers with telli by configuring custom SIP …”
Deepgram provides all core building blocks — prompting, voice/LLM selection, telephony via Twilio bridging, and a single WebSocket API — that together could plausibly get a developer to a first live call quickly. However, the telephony path requires standing up your own server to bridge Twilio audio to the Voice Agent WebSocket, which is nontrivial integration work rather than a turnkey 'phone number in one hour' flow, and there's no first-party quickstart or time-to-first-call benchmark cited. missing for 10: an end-to-end quickstart/tutorial demonstrating full setup within an hour, evidence of a managed/no-code telephony number provisioning path, and independent hands-on confirmation of setup speed.
- [claimed-docs] “Deepgram's Voice Agent API collapses that stack into a single, unified API. You open one WebSocket connection, send audio in, and receive au…”
- [claimed-docs] “Telephony: connect voice agents to phone networks for inbound and outbound calls.”
- [claimed-docs] “Prompting: write system prompts that shape live-call behavior.”
- [claimed-docs] “Supported LLM providers | Parameter | open_ai | anthropic | aws_bedrock | google | groq | nvidia”
- [claimed-docs] “Twilio streams the call audio to your server, and your server bridges that audio to the Deepgram Voice Agent API, a single WebSocket that ru…”
- [claimed-docs] “That includes barge-in, the ability to talk over the agent and have it stop instantly.”
developerRun conversations in multiple languages, including detecting and switching language mid-call
weight 2 · round to Deepgram Voice Agenttellinone0/10No evidence in the pack mentions multilingual support, language detection, or mid-call language switching for telli's voice agents; all documented features concern scheduling, webhooks, tools, analytics, and MCP integration.
Deepgram's docs confirm multilingual voice agent support, noting that STT and TTS model choices must be configured for the target language (deepgram-docs-10), but the evidence pack does not explicitly document automatic language detection or dynamic switching mid-call — only static multilingual configuration is described. Missing for 10: explicit documentation of automatic language detection, mid-call language switching mechanics, and independent/hands-on confirmation of this behavior in production.
- [claimed-docs] “A multilingual voice agent has two model decisions: which STT model transcribes the user, and which TTS model speaks the agent.”
founderDesign multi-step conversation flows in a visual builder with branching, states, and handoffs without writing code
weight 2 · round to tellitelli has an 'agent builder' with test-call and versioning, and workflow triggers (scheduled, SMS/WhatsApp) suggesting some no-code workflow configuration, plus tool-calls like transfer to another agent implying handoffs. But there's no evidence of a visual flow builder with branching/state diagrams — evidence only shows agent settings, tools, and triggers, not a drag-and-drop conversation flow canvas. missing for 10: explicit visual builder UI with branching/state nodes, evidence of designing multi-step flows with conditional paths, and documentation of handoff logic beyond simple 'transfer tool'.
- [claimed-docs] “In the agent builder, click Test call to open the dialog. Pick the agent version (your draft with unsaved changes or any saved revision)...”
- [claimed-docs] “Transfer tools | Move the call to another agent or number.”
- [claimed-docs] “Choose SMS and WhatsApp workflow recipients from contact properties, collected values, or a fixed number”
- [claimed-docs] “Workflows can now run automatically on a recurring schedule. Add a Scheduled trigger, choose the interval and start time, and let the workfl…”
Deepgram Voice Agentnone0/10All evidence describes a code/API-first architecture (WebSocket connections, JSON Settings messages, system prompts, function calling, CLI/SDK) rather than a visual no-code builder; there is no mention of a drag-and-drop flow designer, branching UI, or state-machine editor. missing for 10: any visual builder UI, no-code branching/state design, or drag-and-drop handoff configuration.
- [claimed-docs] “Deepgram's Voice Agent API collapses that stack into a single, unified API. You open one WebSocket connection, send audio in, and receive au…”
- [claimed-docs] “Multi-Agent Architecture: orchestrate multiple specialized agents that hand off based on context, intent, or domain.”
- [claimed-docs] “Reusable Agent Configurations allow you to define and persist the agent block of your Settings message using the Deepgram API. Once created,…”
- [claimed-docs] “Prompting: write system prompts that shape live-call behavior.”
- [claimed-docs] “Supported LLM providers | Parameter | open_ai | anthropic | aws_bedrock | google | groq | nvidia”
Personalization
developerInject dynamic variables and per-caller context at call time so each conversation is personalized
weight 2 · round to Deepgram Voice Agenttellinone0/10The evidence describes contact properties and collected values being used to select SMS/WhatsApp recipients (telli-docs-5) and APIs to manage contacts and schedule calls (telli-docs-12, telli-docs-17), but nowhere does it document injecting dynamic variables or per-caller context into an agent's voice call script/persona at call time. Missing for 10: explicit documentation of variable placeholders in agent prompts, a mechanism for passing per-call custom data via the schedule-call API, and any example of personalized call content driven by caller-specific fields.
- [claimed-docs] “Choose SMS and WhatsApp workflow recipients from contact properties, collected values, or a fixed number”
- [claimed-docs] “API Endpoints: Use telli's REST API to programmatically manage contacts, schedule calls, and integrate with your existing systems.”
- [claimed-docs] “Schedules a call at the earliest opportunity within the dialer window. May occur immediately or on the next business day depending on settin…”
Deepgram supports prompting, reusable agent configs (passed at call time via UUID), function calling, and mid-call message injection, which together allow injecting per-call context/variables into agent behavior; A/B testing of configs also implies runtime parameterization. However there is no explicit documented mechanism for templated dynamic variables (e.g., {{caller_name}}) or a dedicated per-caller context API akin to other platforms. missing for 10: explicit dynamic variable templating syntax, dedicated per-caller metadata injection API, hands-on example of personalizing a call with caller-specific data.
- [claimed-docs] “Reusable Agent Configurations allow you to define and persist the agent block of your Settings message using the Deepgram API. Once created,…”
- [claimed-docs] “Prompting: write system prompts that shape live-call behavior.”
- [claimed-docs] “Inject agent message | Mid-call | InjectAgentMessage | Makes the agent speak a specific line”
- [claimed-docs] “A/B testing voices or prompts — Run two configurations in parallel and measure conversion, CSAT, or containment rate to pick a winner—no cod…”
- [claimed-docs] “In the context of Deepgram Voice Agents, function calling enables your agent to perform tasks during a live conversation.”
developerGround the agent on my documents with a built-in knowledge base or RAG so it answers from my content
weight 2 · round drawntellinone0/10No evidence of a built-in knowledge base or RAG feature for grounding agents on uploaded documents; the docs describe custom tools for API integration and a web_search tool for public information, but nothing about ingesting documents or content for retrieval-based answers.
Deepgram Voice Agentnone0/10The evidence pack covers architecture, function calling, multi-agent handoff, telephony, prompting, and LLM providers, but nowhere documents a built-in knowledge base or RAG feature for grounding the agent on user documents. Function calling ([deepgram-docs-2]) could theoretically be wired to an external retrieval system, but that is not the same as a built-in KB/RAG capability, and no such feature is described.
- [claimed-docs] “In the context of Deepgram Voice Agents, function calling enables your agent to perform tasks during a live conversation.”
- [claimed-docs] “Multi-Agent Architecture: orchestrate multiple specialized agents that hand off based on context, intent, or domain.”
- [claimed-docs] “Prompting: write system prompts that shape live-call behavior.”
Agenticness — how well agents can access and operate the productAgenticness
How well agents can access and operate the product
Agent access
ai-native userPoint an agent at llms.txt or agent-oriented docs
weight 2 · round drawntelli hosts a live llms.txt file (confirmed via probe, HTTP 200) plus machine-readable OpenAPI spec explicitly intended for coding agents, and docs also mention agent-oriented context for downloading API specs. missing for 10: no independent/third-party confirmation of an agent successfully consuming llms.txt in practice.
- [probe] “PROBE llms.txt: HTTP 200 at https://docs.telli.com/llms.txt # telli Documentation > telli is the AI voice platform for agents that sell, su…”
- [claimed-docs] “Download them to generate client libraries, import the API into tools like Postman, or give coding agents machine-readable API context”
- [probe] “PROBE openapi: HTTP 200 at https://docs.telli.com/openapi.json — contains "openapi" key”
Direct probe confirms llms.txt exists at developers.deepgram.com/llms.txt (HTTP 200) with explicit AI-agent instructions, and docs pages support .md suffix for clean markdown retrieval, both verified by live probes. missing for 10: no independent third-party confirmation of an agent actually consuming this in practice.
- [probe] “PROBE llms.txt: HTTP 200 at https://developers.deepgram.com/llms.txt # Deepgram's Docs ## Instructions for AI Agents - For clean Markdown …”
- [probe] “PROBE docs-md: HTTP 200 at https://developers.deepgram.com/docs/voice-agent.md > For clean Markdown of any page, append .md to the page URL.…”
ai-native userRun the product headlessly / in CI for automation
weight 2 · round drawntelli exposes a full REST API (with OpenAPI spec) to programmatically schedule calls, manage contacts, and trigger workflows, plus webhooks for event-driven automation and scheduled/recurring workflow triggers — all of which support headless, non-UI automation suitable for CI-like pipelines. However there is no explicit CI/CD example, CLI tool, or documented automated pipeline integration beyond the API/webhook primitives. Missing for 10: dedicated CI/CD documentation or examples, a CLI for scripted invocation, and independent confirmation of headless use in production pipelines.
- [claimed-docs] “API Endpoints: Use telli's REST API to programmatically manage contacts, schedule calls, and integrate with your existing systems.”
- [claimed-docs] “Schedules a call at the earliest opportunity within the dialer window. May occur immediately or on the next business day depending on settin…”
- [claimed-docs] “Workflows can now run automatically on a recurring schedule. Add a Scheduled trigger, choose the interval and start time, and let the workfl…”
- [claimed-docs] “Webhooks push data from telli to your systems in real time. When something happens on a call, telli sends a POST request to the endpoint you…”
- [probe] “PROBE openapi: HTTP 200 at https://docs.telli.com/openapi.json — contains "openapi" key”
The Voice Agent is a WebSocket API (no GUI dependency) and Deepgram ships a terminal-based `dg` CLI for scripting Deepgram operations (transcribe, synthesize, manage account) which is inherently automatable/CI-friendly, and temporary tokens support secure automated auth. However, there is no explicit documentation of running the Voice Agent itself headlessly in CI pipelines, no CI/CD examples, and the CLI's primary use-cases described are transcription/synthesis rather than orchestrating full voice-agent sessions programmatically. Missing for 10: dedicated CI/headless automation guide for Voice Agent sessions, example CI pipeline configs, and confirmation the CLI can drive the Agent API end-to-end rather than just STT/TTS.
- [claimed-docs] “Deepgram's Voice Agent API collapses that stack into a single, unified API. You open one WebSocket connection, send audio in, and receive au…”
- [claimed-docs] “The dg CLI lets you transcribe files, stream live audio, synthesize speech, analyze text, and manage your Deepgram account from the terminal…”
- [claimed-docs] “Unlike traditional API keys, temporary tokens are ideal for real-time applications requiring secure, temporary access to Deepgram's services…”
- [probe] “official CLI documented at https://developers.deepgram.com/developer-tools/cli/getting-started”
ai-native userPlug MCP servers into this product so it can use their tools
weight 3 · round drawntellinone0/10Telli's documented MCP support only runs in the opposite direction — it exposes an MCP server so external AI tools (Claude, ChatGPT, Codex) can talk to its Charlie assistant (telli-docs-22, telli-probe-3), not a mechanism for telli's own voice agents to consume external MCP servers' tools. Custom Tools (telli-docs-14, telli-docs-20) let agents call external APIs but are described as custom integrations, not MCP-based tool ingestion.
- [claimed-docs] “The telli MCP server lets AI tools like Claude, ChatGPT, and Codex talk to Charlie, telli's AI assistant, over the Model Context Protocol.”
- [probe] “official MCP server documented at https://docs.telli.com/integrations/mcp”
- [claimed-docs] “Custom Tools: Extend telli's capabilities with custom integrations and workflows.”
- [claimed-docs] “Custom tools allow your AI agents to access external information by connecting to your APIs.”
Deepgram Voice Agentnone0/10Deepgram Voice Agent supports function calling for custom tool use, but there is no evidence the Voice Agent can act as an MCP client to consume external MCP servers' tools. The only MCP-related evidence is a built-in MCP *server* in the `dg` CLI that lets coding tools access Deepgram's APIs — the opposite direction of the story.
- [claimed-docs] “In the context of Deepgram Voice Agents, function calling enables your agent to perform tasks during a live conversation.”
- [claimed-docs] “The dg CLI includes a built-in MCP (Model Context Protocol) server that gives AI coding tools direct access to Deepgram APIs.”
- [probe] “official MCP server documented at https://developers.deepgram.com/developer-tools/agentic-tools”
ai-native userConnect an agent via an official MCP server
weight 3 · round to tellitelli documents an official MCP server that lets external AI tools (Claude, ChatGPT, Codex) connect over the Model Context Protocol to interact with Charlie, telli's assistant, confirmed both in docs and via a live probe of the integrations/mcp page. Missing for 10: no independent/hands-on corroboration beyond first-party docs and the probe, and no detail on server setup/auth specifics.
- [claimed-docs] “The telli MCP server lets AI tools like Claude, ChatGPT, and Codex talk to Charlie, telli's AI assistant, over the Model Context Protocol.”
- [probe] “official MCP server documented at https://docs.telli.com/integrations/mcp”
Deepgram ships an official MCP server (bundled in the dg CLI) that lets AI coding tools/agents connect directly to Deepgram's APIs, confirmed both in docs and via a dedicated agentic-tools page. This directly satisfies the story of connecting an agent to Deepgram via an official MCP server. Missing for 10: independent/hands-on verification that the MCP server works reliably in practice, and more detail on which Voice Agent capabilities specifically are exposed through it.
- [claimed-docs] “The dg CLI includes a built-in MCP (Model Context Protocol) server that gives AI coding tools direct access to Deepgram APIs.”
- [probe] “official MCP server documented at https://developers.deepgram.com/developer-tools/agentic-tools”
- [claimed-docs] “The dg CLI lets you transcribe files, stream live audio, synthesize speech, analyze text, and manage your Deepgram account from the terminal…”
ai-native userUse an official CLI
weight 2 · round to Deepgram Voice Agenttellinone0/10telli offers a REST API, webhooks, and an MCP server for AI assistants, but there is no mention anywhere in the evidence of an official CLI tool for telli. missing for 10: any documentation or reference to a telli CLI, its commands, or installation instructions.
Deepgram ships an official 'dg' CLI for transcribing files, streaming audio, synthesizing speech, and managing accounts from the terminal, and it even embeds an MCP server for AI coding tools, directly supporting agentic/AI-native workflows. Missing for 10: independent/hands-on corroboration beyond first-party docs and more detail on CLI coverage of Voice Agent-specific features.
- [claimed-docs] “The dg CLI lets you transcribe files, stream live audio, synthesize speech, analyze text, and manage your Deepgram account from the terminal…”
- [claimed-docs] “The dg CLI includes a built-in MCP (Model Context Protocol) server that gives AI coding tools direct access to Deepgram APIs.”
- [probe] “official CLI documented at https://developers.deepgram.com/developer-tools/cli/getting-started”
- [probe] “official MCP server documented at https://developers.deepgram.com/developer-tools/agentic-tools”
ai-native userDrive the product through a documented public API
weight 3 · round drawntelli documents a REST API with endpoints (schedule-call, import-phone-number), API key/bearer auth, webhooks, and a downloadable OpenAPI spec (confirmed live at openapi.json), plus an MCP server for AI tool access — enabling full programmatic/agentic control. missing for 10: independent third-party validation of API robustness beyond vendor docs.
- [claimed-docs] “API Endpoints: Use telli's REST API to programmatically manage contacts, schedule calls, and integrate with your existing systems.”
- [claimed-docs] “Webhooks: Receive real-time notifications about call events, status changes, and outcomes.”
- [claimed-docs] “All endpoints authenticate with an API key from the telli app (Settings > Developer), sent as a bearer token”
- [claimed-docs] “Download them to generate client libraries, import the API into tools like Postman, or give coding agents machine-readable API context”
- [claimed-docs] “Schedules a call at the earliest opportunity within the dialer window. May occur immediately or on the next business day depending on settin…”
- [claimed-docs] “Imports a phone number from your own SIP trunk provider. This allows you to use existing phone numbers with telli by configuring custom SIP …”
- [claimed-docs] “Webhooks push data from telli to your systems in real time. When something happens on a call, telli sends a POST request to the endpoint you…”
- [claimed-docs] “The telli MCP server lets AI tools like Claude, ChatGPT, and Codex talk to Charlie, telli's AI assistant, over the Model Context Protocol.”
- [probe] “PROBE openapi: HTTP 200 at https://docs.telli.com/openapi.json — contains "openapi" key”
- [probe] “official MCP server documented at https://docs.telli.com/integrations/mcp”
Deepgram publishes a documented public API (WebSocket-based Voice Agent API plus OpenAPI spec confirmed live), extensive docs covering endpoints, function calling, LLM providers, telephony, and auth, and even a CLI/MCP server for programmatic/agentic access, making it clearly drivable by an AI-native user. Missing for 10: independent third-party corroboration of API usage beyond vendor docs.
- [claimed-docs] “Deepgram's Voice Agent API collapses that stack into a single, unified API. You open one WebSocket connection, send audio in, and receive au…”
- [probe] “PROBE openapi: HTTP 200 at https://developers.deepgram.com/openapi.json — contains "openapi" key”
- [claimed-docs] “The dg CLI lets you transcribe files, stream live audio, synthesize speech, analyze text, and manage your Deepgram account from the terminal…”
- [claimed-docs] “The dg CLI includes a built-in MCP (Model Context Protocol) server that gives AI coding tools direct access to Deepgram APIs.”
- [probe] “official CLI documented at https://developers.deepgram.com/developer-tools/cli/getting-started”
- [claimed-docs] “Unlike traditional API keys, temporary tokens are ideal for real-time applications requiring secure, temporary access to Deepgram's services…”
ai-native userIssue scoped/least-privilege API credentials for an agent
weight 2 · round to Deepgram Voice Agenttellinone0/10telli documents a single API key (bearer token) generated in Settings > Developer, but there's no evidence of scoped permissions, role-based keys, or least-privilege credential issuance for agents specifically.
- [claimed-docs] “All endpoints authenticate with an API key from the telli app (Settings > Developer), sent as a bearer token”
Deepgram documents temporary, short-lived tokens as an alternative to traditional API keys for secure, limited-duration access (deepgram-docs-14), which partially satisfies a least-privilege credential story, but there is no evidence of granular scopes/permissions (e.g., restricting a key to specific endpoints or agent capabilities) or role-based access control for agents. Missing for 10: documented scope/permission granularity, per-agent key restriction, and evidence of enforcement/verification of least-privilege in practice.
- [claimed-docs] “Unlike traditional API keys, temporary tokens are ideal for real-time applications requiring secure, temporary access to Deepgram's services…”
ai-native userBuild against official SDKs
weight 2 · round drawntelli provides a REST API with an OpenAPI spec that can be used to generate client libraries, plus webhooks, custom tools, and an MCP server for agent integration, but there is no evidence of telli-maintained official SDKs in specific languages (e.g., Python/JS packages published by telli) — only self-generated clients from the OpenAPI spec. missing for 10: dedicated first-party SDK packages/repos, language-specific SDK documentation, versioning/release notes for such SDKs.
- [claimed-docs] “API Endpoints: Use telli's REST API to programmatically manage contacts, schedule calls, and integrate with your existing systems.”
- [claimed-docs] “All endpoints authenticate with an API key from the telli app (Settings > Developer), sent as a bearer token”
- [claimed-docs] “Download them to generate client libraries, import the API into tools like Postman, or give coding agents machine-readable API context”
- [probe] “PROBE openapi: HTTP 200 at https://docs.telli.com/openapi.json — contains "openapi" key”
Evidence shows an official 'Browser Agent SDK' with composable packages, plus an OpenAPI spec, CLI, and MCP server for developer tooling, indicating some official SDK/build tooling exists. However, evidence does not mention broader server-side/language SDKs (Python, Node, Go, etc.) commonly expected for building agentic applications, nor independent corroboration of SDK quality. Missing for 10: multi-language SDK documentation, independent/hands-on developer reports, broader agentic build examples beyond browser.
- [claimed-docs] “Browser Agent SDK: add voice AI to any web application via four composable packages.”
- [probe] “PROBE openapi: HTTP 200 at https://developers.deepgram.com/openapi.json — contains "openapi" key”
- [probe] “official CLI documented at https://developers.deepgram.com/developer-tools/cli/getting-started”
- [probe] “official MCP server documented at https://developers.deepgram.com/developer-tools/agentic-tools”
ai-native userSubscribe to events via webhooks
weight 2 · round to tellitelli documents a webhooks system that pushes real-time POST notifications about call events, status changes, and outcomes, explicitly described as event-driven subscription for external systems (telli-docs-13, telli-docs-21). Missing for 10: no evidence of configurable event-type filtering/subscription granularity or independent third-party confirmation of reliability.
- [claimed-docs] “Webhooks: Receive real-time notifications about call events, status changes, and outcomes.”
- [claimed-docs] “Webhooks push data from telli to your systems in real time. When something happens on a call, telli sends a POST request to the endpoint you…”
- [claimed-docs] “API Endpoints: Use telli's REST API to programmatically manage contacts, schedule calls, and integrate with your existing systems.”
Deepgram Voice Agentnone0/10The evidence pack shows Deepgram Voice Agent operates via a persistent WebSocket connection for real-time audio streaming, not webhook-based event subscription; no documentation mentions webhooks for event notifications (e.g., call completion, transcript ready, errors). Absence of evidence for an applicable capability yields 'none'.
Agentic features
ai-native userGet AI-generated insights and suggestions from my data inside the product
weight 2 · round to tellitelli ships a built-in AI assistant (Charlie) that can 'analyze your calls' and help build/refine agents, plus dashboards for reach rate, call duration, success rate, and per-call transcript/outcome analysis, which together provide AI-driven insight into product data. However, the docs don't detail proactive, autonomous 'suggestions' surfaced to the user (e.g., recommended actions, anomaly detection) beyond on-demand analysis via Charlie or manual dashboard review. Missing for 10: concrete examples of Charlie proactively surfacing insights/recommendations, independent user corroboration of insight quality.
- [claimed-docs] “Charlie: Build and refine agents, automate workflows, and analyze your calls with telli's built-in AI assistant.”
- [claimed-docs] “Track key metrics like reach rate, call duration, and success rate.”
- [claimed-docs] “Analyze individual calls, transcripts, and call outcome fields.”
- [claimed-docs] “Submit feedback on calls to continuously improve your agent.”
Deepgram Voice Agentnone0/10The evidence pack covers Deepgram Voice Agent's API capabilities (function calling, multi-agent orchestration, telephony, LLM providers, prompting) but contains no mention of an in-product analytics dashboard, conversation insights, or AI-generated suggestions derived from a user's own data. While such a feature (e.g., call analytics/insights) is plausible for a voice AI platform, no evidence shows Deepgram surfaces this.
ai-native userSet up automations that run autonomously in the background
weight 2 · round to tellitelli supports Scheduled triggers so workflows run automatically without a call event, plus retry/dialing-window configuration, webhooks, and an AI assistant (Charlie) to build/automate workflows — together enabling background autonomous automations. Missing for 10: independent/hands-on verification of scheduled automations running reliably in production, and more detail on monitoring/error-handling for autonomous runs beyond docs claims.
- [claimed-docs] “Workflows can now run automatically on a recurring schedule. Add a Scheduled trigger, choose the interval and start time, and let the workfl…”
- [claimed-docs] “Configure dialing windows, calling strategies, and retry behavior.”
- [claimed-docs] “Charlie: Build and refine agents, automate workflows, and analyze your calls with telli's built-in AI assistant.”
- [claimed-docs] “Webhooks: Receive real-time notifications about call events, status changes, and outcomes.”
- [claimed-docs] “Schedules a call at the earliest opportunity within the dialer window. May occur immediately or on the next business day depending on settin…”
ai-native userDelegate tasks to a built-in AI assistant inside the product
weight 3 · round to tellitelli documents "Charlie," a built-in AI assistant that can build/refine agents, automate workflows, and analyze calls, and this assistant is also exposed via an MCP server for external AI tools to interact with. This directly matches delegating tasks to a built-in assistant within the product. Missing for 10: independent/hands-on verification of Charlie's task delegation in practice and more detail on the scope of tasks it can autonomously execute.
- [claimed-docs] “Charlie: Build and refine agents, automate workflows, and analyze your calls with telli's built-in AI assistant.”
- [claimed-docs] “The telli MCP server lets AI tools like Claude, ChatGPT, and Codex talk to Charlie, telli's AI assistant, over the Model Context Protocol.”
- [probe] “official MCP server documented at https://docs.telli.com/integrations/mcp”
ai-native userOperate the product with natural-language commands
weight 2 · round to Deepgram Voice Agenttelli offers Charlie, a built-in AI assistant that can build/refine agents, automate workflows, and analyze calls via natural language, plus an MCP server letting external AI tools (Claude, ChatGPT, Codex) converse with Charlie — both point to natural-language operation. However, most of the product surface (workflows, scheduling, dialing windows, phone number setup) is described as configured through UI/API rather than conversational commands, and there's no independent/hands-on evidence of Charlie's NL command scope or reliability. missing for 10: hands-on evidence of Charlie executing complex natural-language commands, documentation detailing the breadth of actions controllable purely via NL, independent corroboration beyond vendor docs.
- [claimed-docs] “Charlie: Build and refine agents, automate workflows, and analyze your calls with telli's built-in AI assistant.”
- [claimed-docs] “The telli MCP server lets AI tools like Claude, ChatGPT, and Codex talk to Charlie, telli's AI assistant, over the Model Context Protocol.”
- [probe] “official MCP server documented at https://docs.telli.com/integrations/mcp”
Deepgram Voice Agent is fundamentally a conversational system: users interact via natural spoken language, and the agent supports function calling to perform tasks, live prompting to shape behavior, and mid-call message injection—all driven by natural-language conversation rather than rigid commands. This is core, well-documented functionality (docs-2, docs-7, docs-11) directly matching the story's intent for an ai-native/agentic persona. Missing for 10: independent/hands-on validation of natural-language command accuracy and no evidence of complex multi-turn command chaining reliability from third-party sources.
- [claimed-docs] “In the context of Deepgram Voice Agents, function calling enables your agent to perform tasks during a live conversation.”
- [claimed-docs] “Prompting: write system prompts that shape live-call behavior.”
- [claimed-docs] “Inject agent message | Mid-call | InjectAgentMessage | Makes the agent speak a specific line”
- [claimed-docs] “Multi-Agent Architecture: orchestrate multiple specialized agents that hand off based on context, intent, or domain.”
Api quality
ai-native userExplore an interactive API reference with runnable examples
weight 2 · round to tellitelli publishes an OpenAPI spec (openapi.json) and API docs with downloadable schemas for generating client libraries or feeding coding agents, but there is no evidence of an interactive reference with runnable/'try it' examples in-browser. missing for 10: an interactive try-it console, live runnable code samples, or sandboxed request execution within the docs site.
- [claimed-docs] “Download them to generate client libraries, import the API into tools like Postman, or give coding agents machine-readable API context”
- [probe] “PROBE openapi: HTTP 200 at https://docs.telli.com/openapi.json — contains "openapi" key”
- [claimed-docs] “All endpoints authenticate with an API key from the telli app (Settings > Developer), sent as a bearer token”
Deepgram Voice Agentnone0/10Evidence shows an OpenAPI spec exists and docs pages are available as clean Markdown, but there is no evidence of an interactive API reference with runnable/try-it-now examples (e.g., embedded playground, live code execution, or Swagger/Postman-style explorer). Missing for 10: interactive explorer UI, runnable/executable code snippets, live request/response testing.
- [probe] “PROBE openapi: HTTP 200 at https://developers.deepgram.com/openapi.json — contains "openapi" key”
- [probe] “PROBE llms.txt: HTTP 200 at https://developers.deepgram.com/llms.txt # Deepgram's Docs ## Instructions for AI Agents - For clean Markdown …”
- [probe] “PROBE docs-md: HTTP 200 at https://developers.deepgram.com/docs/voice-agent.md > For clean Markdown of any page, append .md to the page URL.…”
ai-native userDownload a machine-readable API spec (OpenAPI or equivalent)
weight 2 · round drawntelli provides a downloadable OpenAPI spec confirmed live at /openapi.json, and docs explicitly state it can be downloaded to generate client libraries, import into tools, or give coding agents machine-readable API context. Missing for 10: no independent third-party confirmation of spec completeness/versioning beyond first-party docs and probe.
- [claimed-docs] “Download them to generate client libraries, import the API into tools like Postman, or give coding agents machine-readable API context”
- [probe] “PROBE openapi: HTTP 200 at https://docs.telli.com/openapi.json — contains "openapi" key”
A probe confirms Deepgram publishes a machine-readable OpenAPI spec at openapi.json containing the 'openapi' key, directly satisfying the story. Missing for 10: no first-party docs page explicitly announcing/describing the OpenAPI spec's coverage or versioning.
- [probe] “PROBE openapi: HTTP 200 at https://developers.deepgram.com/openapi.json — contains "openapi" key”
ai-native userTest against a sandbox environment without touching production data
weight 1 · round to tellitelli's agent builder includes a 'Test call' feature that lets users dial a draft or saved agent version and review the recording/transcript before going live, which functions as a lightweight test mode (telli-docs-28, telli-docs-29). However, there is no documentation of a dedicated sandbox environment, separate test dataset, or explicit guarantee that test calls don't write to production contacts/analytics. missing for 10: explicit sandbox/staging environment separate from production, confirmation that test calls don't affect production data/metrics, and any mention of test API keys or isolated test accounts.
- [claimed-docs] “In the agent builder, click Test call to open the dialog. Pick the agent version (your draft with unsaved changes or any saved revision)...”
- [claimed-docs] “Use the side-by-side view to listen to the recording while following along in the transcript.”
Deepgram Voice Agentnone0/10No evidence pack item mentions a sandbox environment, test/dev API keys, or a way to test without touching production data or usage; only production endpoints, EU endpoint, and opt-out flags are documented. Missing for 10: sandbox/test-mode environment, documentation of non-production keys or test credits, any guidance on isolating test traffic from production data.
ai-native userRely on versioned APIs with a documented deprecation policy
weight 2 · round drawntellinone0/10Evidence shows an OpenAPI spec and API key auth exist, but nothing in the pack mentions API versioning (e.g., v1/v2 paths, version headers) or any documented deprecation/sunset policy for endpoints. Missing for 10: explicit API version scheme, changelog of breaking changes, and a stated deprecation/sunset policy.
- [claimed-docs] “API Endpoints: Use telli's REST API to programmatically manage contacts, schedule calls, and integrate with your existing systems.”
- [claimed-docs] “All endpoints authenticate with an API key from the telli app (Settings > Developer), sent as a bearer token”
- [probe] “PROBE openapi: HTTP 200 at https://docs.telli.com/openapi.json — contains "openapi" key”
Automation depth — how much of the product can run unattendedAutomation depth
How much of the product can run unattended
ai-native userPerform bulk operations across many items at once
weight 2 · round to telliTelli's platform is built around calling large contact lists (dialing windows, calling strategies, retry behavior, reach-rate metrics) and its REST API lets users 'programmatically manage contacts, schedule calls' at scale, implying bulk campaign operations. However, there is no explicit documentation of a bulk-upload/bulk-schedule endpoint or UI for acting on many items simultaneously — the schedule-call endpoint documented is single-call oriented. Missing for 10: explicit bulk-contact import/schedule endpoint, documented batch size limits, and independent evidence of large-scale bulk execution.
- [claimed-docs] “Configure dialing windows, calling strategies, and retry behavior.”
- [claimed-docs] “Track key metrics like reach rate, call duration, and success rate.”
- [claimed-docs] “API Endpoints: Use telli's REST API to programmatically manage contacts, schedule calls, and integrate with your existing systems.”
- [claimed-docs] “Schedules a call at the earliest opportunity within the dialer window. May occur immediately or on the next business day depending on settin…”
- [probe] “PROBE llms.txt: HTTP 200 at https://docs.telli.com/llms.txt # telli Documentation > telli is the AI voice platform for agents that sell, su…”
ai-native userDefine rules that trigger actions automatically on events
weight 3 · round drawntelli's workflows can be triggered by call events (implied default) and now by a recurring schedule, and webhooks notify external systems on call events, showing some event-driven automation. However there's no documented rule-definition interface (conditions, event-type selection, if/then logic) for arbitrary events beyond calls/schedule. Missing for 10: explicit rule/condition builder, broader event-type coverage beyond calls, and evidence of user-defined trigger logic rather than fixed schedule/call triggers.
- [claimed-docs] “Workflows can now run automatically on a recurring schedule. Add a Scheduled trigger, choose the interval and start time, and let the workfl…”
- [claimed-docs] “Webhooks: Receive real-time notifications about call events, status changes, and outcomes.”
- [claimed-docs] “Webhooks push data from telli to your systems in real time. When something happens on a call, telli sends a POST request to the endpoint you…”
Deepgram Voice Agent supports function calling that lets the agent trigger actions during a live conversation, and features like InjectAgentMessage and multi-agent handoff suggest some event-driven behavior, but this is developer-defined logic (via function calling code) rather than a declarative rules engine for automatically triggering actions on arbitrary events. missing for 10: a documented rules/trigger engine (if-this-then-that style), event subscription system, or automation workflow builder distinct from manual function-calling code.
- [claimed-docs] “In the context of Deepgram Voice Agents, function calling enables your agent to perform tasks during a live conversation.”
- [claimed-docs] “Multi-Agent Architecture: orchestrate multiple specialized agents that hand off based on context, intent, or domain.”
- [claimed-docs] “Inject agent message | Mid-call | InjectAgentMessage | Makes the agent speak a specific line”
ai-native userSchedule recurring jobs or workflows
weight 2 · round to tellitelli documents scheduled triggers that let workflows run recurringly on an interval/start time without a call event, directly matching the recurring-workflow story, and also supports scheduling individual calls via API. missing for 10: independent/hands-on corroboration of recurrence reliability and detail on editing/monitoring scheduled workflow runs.
- [claimed-docs] “Workflows can now run automatically on a recurring schedule. Add a Scheduled trigger, choose the interval and start time, and let the workfl…”
- [claimed-docs] “Schedules a call at the earliest opportunity within the dialer window. May occur immediately or on the next business day depending on settin…”
- [claimed-docs] “Optional flag to bypass dialing window restrictions for the scheduled call. When true, calls at the scheduled time regardless of dialing win…”
ai-native userVersion, review, and roll back my automations
weight 1 · round drawnThe only hint of versioning is in agent testing, where you can pick 'your draft with unsaved changes or any saved revision' (telli-docs-28), implying saved agent versions exist. However there is no documented review interface for comparing versions, no explicit rollback/restore action, and no versioning mentioned for broader automations/workflows (only agents). Missing for 10: explicit rollback UI/API, version diff/review tooling, and versioning coverage for workflows beyond agent test calls.
- [claimed-docs] “In the agent builder, click Test call to open the dialog. Pick the agent version (your draft with unsaved changes or any saved revision)...”
Deepgram's Reusable Agent Configurations let you persist a named agent config and reference it by UUID, and support A/B testing two configs in parallel, which is adjacent to versioning, but there is no documented version history, diff/review workflow, or explicit rollback mechanism. missing for 10: version history tracking, review/approval workflow, explicit rollback capability, changelog or diffing between config versions.
- [claimed-docs] “Reusable Agent Configurations allow you to define and persist the agent block of your Settings message using the Deepgram API. Once created,…”
- [claimed-docs] “A/B testing voices or prompts — Run two configurations in parallel and measure conversion, CSAT, or containment rate to pick a winner—no cod…”
Compliance trust — stories about compliance trust in this arenaCompliance trust
Stories about compliance trust in this arena
Compliance
founderMeet call-recording consent and disclosure obligations with per-call recording controls and configurable data retention
weight 2 · round to tellitelli documents conditional recording based on caller consent and a configurable data-retention policy that auto-deletes contacts and call data after a defined age, directly addressing the founder's compliance need. However, evidence lacks detail on per-call granular controls (e.g., pause/resume, jurisdiction-specific disclosure scripts), audit logging of consent events, or independent verification that these features work as described. Missing for 10: per-call recording toggle/audit trail details, jurisdiction-specific disclosure templates, retention configuration granularity (e.g., per-data-type settings), and independent/hands-on confirmation of compliance behavior.
- [claimed-docs] “Data retention deletes contacts and call data automatically once they reach an age you define.”
- [claimed-docs] “In telli, you can easily make audio recording conditional on the caller's consent — so a call is only recorded once they agree.”
Deepgram documents general data-privacy controls (per-request opt-out from retention via mip_opt_out, EU-region processing endpoint) that touch on data retention/residency, but there is no explicit documentation of per-call recording toggles, consent/disclosure workflows, or configurable retention windows tied to call recordings specifically. Missing for 10: explicit per-call recording enable/disable controls, documented retention period configuration for stored call audio/transcripts, and consent/disclosure feature support.
- [claimed-docs] “Opt out per request with mip_opt_out=true. Opted-out requests are not retained”
- [claimed-docs] “For customers requiring data processing within the European Union, Deepgram provides an EU-specific endpoint at api.eu.deepgram.com.”
platform-engineerRun regulated workloads with HIPAA/BAA support, SOC 2, and data-residency options
weight 2 · round to Deepgram Voice Agenttellinone0/10No evidence in the pack mentions HIPAA, BAA, SOC 2, or data-residency options; only data retention and consent-based recording are covered, which don't establish formal compliance certifications.
Evidence shows EU data-residency endpoint and an opt-out from data retention/training, indicating some compliance/trust infrastructure, but there is no mention of HIPAA/BAA support or SOC 2 certification anywhere in the pack. missing for 10: HIPAA/BAA documentation, SOC 2 attestation evidence, broader regional residency options beyond EU.
- [claimed-docs] “Opt out per request with mip_opt_out=true. Opted-out requests are not retained”
- [claimed-docs] “For customers requiring data processing within the European Union, Deepgram provides an EU-specific endpoint at api.eu.deepgram.com.”
Deployment scale — stories about deployment scale in this arenaDeployment scale
Stories about deployment scale in this arena
Scale
platform-engineerSee documented concurrency limits and scale to many simultaneous calls without manual capacity begging
weight 2 · round drawntellinone0/10No evidence pack item documents concurrency limits, per-account call caps, or scaling guarantees for simultaneous calls; docs mention dialing windows/retry strategy but not concurrency ceilings or auto-scaling behavior. This is a fair question for a voice-calling platform (scaling many simultaneous calls is core to the product's value), so 'none' applies rather than 'na'.
Deepgram Voice Agentnone0/10No evidence pack item mentions concurrency limits, rate limits, per-account call caps, scaling guidance, or capacity request processes for the Voice Agent API; the docs cover architecture, features, and integrations but nothing about scale/concurrency documentation.
Self host
platform-engineerSelf-host the voice agent runtime from open-source code on my own infrastructure
weight 3 · round drawntellinone0/10The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)
Deepgram Voice Agentnone0/10Deepgram Voice Agent is a hosted, cloud-only API accessed via WebSocket; nothing in the evidence indicates open-source runtime code that can be self-hosted on customer infrastructure. All references point to Deepgram-hosted endpoints (api.deepgram.com, api.eu.deepgram.com) and a CLI/SDK for calling the cloud service, not deploying the runtime itself.
- [claimed-docs] “Deepgram's Voice Agent API collapses that stack into a single, unified API. You open one WebSocket connection, send audio in, and receive au…”
- [claimed-docs] “For customers requiring data processing within the European Union, Deepgram provides an EU-specific endpoint at api.eu.deepgram.com.”
- [claimed-docs] “Twilio streams the call audio to your server, and your server bridges that audio to the Deepgram Voice Agent API, a single WebSocket that ru…”
Latency turntaking — stories about latency turntaking in this arenaLatency turntaking
Stories about latency turntaking in this arena
Latency
platform-engineerSee documented end-to-end voice latency numbers or tuning guidance backing the platform's speed claims
weight 3 · round drawntellinone0/10No evidence pack item mentions latency numbers, turn-taking performance, or tuning guidance for voice response speed; documentation covers workflows, API, webhooks, and agent building but nothing on end-to-end latency benchmarks or tuning.
Deepgram Voice Agentnone0/10The evidence pack covers architecture, features (barge-in, telephony, function calling, multi-agent), and CLI/SDK tooling, but contains no documented latency numbers (e.g., ms end-to-end) or tuning guidance for reducing turn-taking latency. missing for 10: quantified latency benchmarks, latency tuning/configuration guidance, any performance dashboard or whitepaper on speed claims.
- [claimed-docs] “Deepgram's Voice Agent API collapses that stack into a single, unified API. You open one WebSocket connection, send audio in, and receive au…”
- [claimed-docs] “That includes barge-in, the ability to talk over the agent and have it stop instantly.”
- [claimed-docs] “Twilio streams the call audio to your server, and your server bridges that audio to the Deepgram Voice Agent API, a single WebSocket that ru…”
Turn taking
developerRely on the agent to handle interruptions (barge-in) gracefully — stopping speech, updating context, and recovering the turn
weight 3 · round to Deepgram Voice Agenttellinone0/10No evidence in the pack addresses barge-in, interruption handling, speech-stopping, or turn recovery mechanics; the docs cover scheduling, workflows, analytics, and integrations but never mention conversational turn-taking behavior.
Docs explicitly claim barge-in support where users can talk over the agent and it stops instantly, plus mid-call context tools like InjectAgentMessage for updating conversation state. However, evidence lacks detail on how turn recovery/context updating works technically after interruption, and there's no independent/hands-on corroboration of graceful recovery in practice. missing for 10: technical details on context-state recovery post-interruption, independent verification of barge-in reliability, edge-case handling (e.g., rapid interruptions, latency of stop).
- [claimed-docs] “That includes barge-in, the ability to talk over the agent and have it stop instantly.”
- [claimed-docs] “Inject agent message | Mid-call | InjectAgentMessage | Makes the agent speak a specific line”
- [claimed-docs] “Deepgram's Voice Agent API collapses that stack into a single, unified API. You open one WebSocket connection, send audio in, and receive au…”
developerEnable noise suppression or audio filtering so the agent stays coherent on noisy real-world calls
weight 1 · round drawntellinone0/10No evidence pack item mentions noise suppression, audio filtering, or any mechanism for handling noisy call environments; documentation covers scheduling, workflows, analytics, and voice cloning but not audio quality/noise handling.
developerUse model-based end-of-turn detection beyond simple VAD silence timeouts so the agent doesn't talk over slow speakers
weight 2 · round drawntellinone0/10No evidence in the pack discusses turn-taking, end-of-turn detection, VAD, or interruption handling in telli's voice agent; the docs cover scheduling, workflows, tools, and integrations but not conversational latency/turn-taking mechanics.
Openness — open source, data portability, and self-hosting storiesOpenness
Open source, data portability, and self-hosting stories
ai-native userDo everything through the API that I can do in the UI
weight 2 · round drawntelli exposes a REST API (with OpenAPI spec) covering contacts, scheduling calls, phone number import, custom tools, and webhooks, and also offers an MCP server so external AI tools can interact with Charlie. However, several UI-native features—agent builder/test-call dialog, live monitoring dashboard, side-by-side transcript/recording view, voice cloning setup, workflow trigger/recurring schedule configuration UI, and analytics dashboards—are not documented as API-accessible endpoints, so full UI/API parity is not evidenced. missing for 10: API endpoints for agent building/testing, live monitoring, voice cloning, workflow scheduling configuration, and analytics/reporting equivalent to UI dashboards.
- [claimed-docs] “API Endpoints: Use telli's REST API to programmatically manage contacts, schedule calls, and integrate with your existing systems.”
- [claimed-docs] “All endpoints authenticate with an API key from the telli app (Settings > Developer), sent as a bearer token”
- [claimed-docs] “Download them to generate client libraries, import the API into tools like Postman, or give coding agents machine-readable API context”
- [claimed-docs] “Schedules a call at the earliest opportunity within the dialer window. May occur immediately or on the next business day depending on settin…”
- [claimed-docs] “Imports a phone number from your own SIP trunk provider. This allows you to use existing phone numbers with telli by configuring custom SIP …”
- [claimed-docs] “Custom tools allow your AI agents to access external information by connecting to your APIs.”
- [claimed-docs] “Webhooks push data from telli to your systems in real time. When something happens on a call, telli sends a POST request to the endpoint you…”
- [claimed-docs] “The telli MCP server lets AI tools like Claude, ChatGPT, and Codex talk to Charlie, telli's AI assistant, over the Model Context Protocol.”
- [probe] “PROBE openapi: HTTP 200 at https://docs.telli.com/openapi.json — contains "openapi" key”
- [probe] “official MCP server documented at https://docs.telli.com/integrations/mcp”
Deepgram is fundamentally API-first — the Voice Agent is a WebSocket API with full configuration (prompting, function calling, multi-agent, telephony, reusable configs) exposed programmatically, and even the CLI/MCP server let AI-native users manage things from the terminal or via agentic tools rather than a GUI. However, evidence doesn't show a full-featured UI to compare against (e.g., a dashboard/console) nor confirm that every console feature (like A/B testing dashboards, analytics views) has a documented API equivalent. missing for 10: explicit mapping of console/UI-only features (analytics dashboards, A/B test result views) to API endpoints, and confirmation no UI-exclusive functionality exists.
- [claimed-docs] “Deepgram's Voice Agent API collapses that stack into a single, unified API. You open one WebSocket connection, send audio in, and receive au…”
- [claimed-docs] “Reusable Agent Configurations allow you to define and persist the agent block of your Settings message using the Deepgram API. Once created,…”
- [claimed-docs] “The dg CLI lets you transcribe files, stream live audio, synthesize speech, analyze text, and manage your Deepgram account from the terminal…”
- [claimed-docs] “The dg CLI includes a built-in MCP (Model Context Protocol) server that gives AI coding tools direct access to Deepgram APIs.”
- [claimed-docs] “A/B testing voices or prompts — Run two configurations in parallel and measure conversion, CSAT, or containment rate to pick a winner—no cod…”
- [probe] “PROBE openapi: HTTP 200 at https://developers.deepgram.com/openapi.json — contains "openapi" key”
- [probe] “official MCP server documented at https://developers.deepgram.com/developer-tools/agentic-tools”
- [probe] “official CLI documented at https://developers.deepgram.com/developer-tools/cli/getting-started”
ai-native userExport all of my data in open formats and leave
weight 3 · round drawntellinone0/10No evidence of a bulk data-export feature or open-format data portability; only API endpoints to manage/read specific records and a data-retention deletion policy are documented, not a full self-service export/leave capability. Missing for 10: documented full-account export tool/endpoint, open-format (CSV/JSON) bulk export, and any explicit data-portability statement.
- [claimed-docs] “API Endpoints: Use telli's REST API to programmatically manage contacts, schedule calls, and integrate with your existing systems.”
- [claimed-docs] “Data retention deletes contacts and call data automatically once they reach an age you define.”
Deepgram Voice Agentnone0/10No evidence describes any data export, account data portability, or open-format export/deletion workflow letting a user take their data and leave; docs cover retention opt-out and EU processing but not export tooling. missing for 10: data export mechanism, open-format export documentation, account closure/data portability guarantees.
ai-native userRead the product's source under an open license
weight 2 · round drawntellinone0/10The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)
Deepgram Voice Agentnone0/10Deepgram Voice Agent is a proprietary cloud API/SDK product; no evidence anywhere in the pack points to an open-source license or public source repository for the core Voice Agent service. Only API docs, CLI, and SDK usage are documented, none of which imply open-licensed source availability.
ai-native userSelf-host the core product
weight 3 · round drawntellinone0/10The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)
Deepgram Voice Agentnone0/10Deepgram Voice Agent is a cloud API/SaaS product; all evidence points to hosted WebSocket endpoints, EU regional endpoints, and cloud-based configuration — there is no mention of a self-hostable or on-premises deployment package for the core voice agent model/inference stack. missing for 10: any self-hosting/on-prem deployment option, downloadable model weights or container, docs on running the core service outside Deepgram's cloud.
- [claimed-docs] “Deepgram's Voice Agent API collapses that stack into a single, unified API. You open one WebSocket connection, send audio in, and receive au…”
- [claimed-docs] “For customers requiring data processing within the European Union, Deepgram provides an EU-specific endpoint at api.eu.deepgram.com.”
Pricing plans — plan structure and value — what each tier costs and what it unlocksPricing plans
Plan structure and value — what each tier costs and what it unlocks
Pricing
founderSee published per-minute or usage pricing and estimate cost per call before committing
weight 2 · round drawntellinone0/10No evidence in the pack mentions pricing, per-minute rates, usage costs, or any cost calculator/estimator; the docs cover features (workflows, appointments, API, MCP, etc.) but nothing about published pricing.
Privacy posture — data-handling and privacy storiesPrivacy posture
Data-handling and privacy stories
ai-native userChoose where my data is stored (region/residency)
weight 2 · round to Deepgram Voice Agenttellinone0/10No evidence in the pack mentions data residency, region selection, or data storage location controls; data retention (deletion timing) is covered but that is a different capability from choosing storage region.
Deepgram documents an EU-specific endpoint (api.eu.deepgram.com) for customers requiring EU data processing, and a per-request opt-out for model improvement data retention, showing some regional/data-handling control. However, this is limited to EU vs. default (US) with no evidence of broader region selection (e.g., APAC, other jurisdictions) or a general residency configuration option across the platform. Missing for 10: documented list of all available regions, self-serve region selection in dashboard/API config, and independent confirmation of residency guarantees beyond docs.
- [claimed-docs] “For customers requiring data processing within the European Union, Deepgram provides an EU-specific endpoint at api.eu.deepgram.com.”
- [claimed-docs] “Opt out per request with mip_opt_out=true. Opted-out requests are not retained”
ai-native userPrevent my data from being used to train AI models
weight 3 · round to Deepgram Voice Agenttellinone0/10No evidence in the pack addresses AI training data usage or opt-out policies; data retention docs cover deletion of contacts/call data but not model-training exclusion.
Deepgram documents a per-request opt-out (mip_opt_out=true) from its Model Improvement Program, with opted-out requests not retained, directly addressing training-data use. However, the evidence only shows a per-request flag rather than an account-wide default-off setting, and there's no independent verification that opt-out requests are truly excluded from training. Missing for 10: account/org-level opt-out default, third-party audit or independent confirmation of non-training use, and clarity on default behavior when the flag is omitted.
- [claimed-docs] “Opt out per request with mip_opt_out=true. Opted-out requests are not retained”
ai-native userControl data retention and deletion
weight 2 · round to tellitelli documents automatic data retention deletion (contacts and call data purged once they reach a defined age) and conditional consent-based recording, giving users some control over data lifecycle and privacy. However, there's no evidence of user-initiated manual deletion, export/right-to-access tools, or granular per-record deletion controls beyond the age-based policy. missing for 10: manual/on-demand deletion controls, data export capability, independent verification of retention enforcement.
- [claimed-docs] “Data retention deletes contacts and call data automatically once they reach an age you define.”
- [claimed-docs] “In telli, you can easily make audio recording conditional on the caller's consent — so a call is only recorded once they agree.”
Deepgram documents a per-request opt-out (mip_opt_out=true) that prevents retention, and references data-privacy compliance including an EU-specific endpoint, giving users some retention control. However, there is no documented self-service deletion mechanism for already-retained data, no stated retention periods, and no dashboard/API for managing or purging stored voice data. Missing for 10: explicit data deletion API/console, documented retention duration policy, and confirmation of deletion for non-opted-out data.
- [claimed-docs] “Opt out per request with mip_opt_out=true. Opted-out requests are not retained”
- [claimed-docs] “For customers requiring data processing within the European Union, Deepgram provides an EU-specific endpoint at api.eu.deepgram.com.”
ai-native userOpt out of telemetry and usage tracking
weight 2 · round to Deepgram Voice Agenttellinone0/10telli is a voice-agent platform, not a developer tool where telemetry opt-out is typically discussed, but the axis is still fair to ask (does the product track usage, and can a user disable it). The evidence pack (data retention, consent-based recording, etc.) never mentions any telemetry/usage-tracking opt-out mechanism for the product itself. Missing for 10: any documentation of telemetry collection practices or an opt-out setting/toggle.
Deepgram documents an opt-out mechanism (mip_opt_out=true) for model improvement/data retention on a per-request basis, which is a form of telemetry/usage-data opt-out, but this is narrowly scoped to training data retention rather than general telemetry/usage tracking (e.g., analytics, product usage metrics). Missing for 10: documentation of a broader telemetry/usage-tracking opt-out setting, confirmation this covers all usage data beyond model-improvement retention, and independent verification that opting out has no side effects.
- [claimed-docs] “Opt out per request with mip_opt_out=true. Opted-out requests are not retained”
Telephony — stories about telephony in this arenaTelephony
Stories about telephony in this arena
Call control
developerEscalate a live call to a human with warm or blind transfer, passing context along
weight 2 · round to telliDocs confirm a transfer tool that can move a call to another agent or number, matching the core escalation-to-human idea, but there's no mention of distinct warm vs. blind transfer modes or explicit context-passing to the human recipient. missing for 10: explicit warm/blind transfer distinction, evidence of context/data hand-off during transfer, hands-on confirmation of the feature in practice.
- [claimed-docs] “Transfer tools | Move the call to another agent or number.”
Deepgram Voice Agentnone0/10Evidence covers telephony connectivity, function calling, multi-agent handoff between AI agents, and mid-call message injection, but nothing documents a warm/blind transfer to a human agent (e.g., SIP REFER, call transfer function, or context handoff to a live operator).
developerMy agent can send DTMF keypresses, navigate IVR menus, and detect or leave voicemail
weight 1 · round drawntellinone0/10No evidence in the pack mentions DTMF keypress sending, IVR menu navigation, or voicemail detection/leaving; telli's docs cover scheduling, transfers, web search tool, and webhooks but nothing about touch-tone or answering machine handling.
Campaigns
founderRun batch outbound call campaigns with scheduling and throughput controls
weight 2 · round to tellitelli documents dialing windows, calling strategies, and retry behavior (telli-docs-9) plus a schedule-call API endpoint that respects dialer windows or can bypass them (telli-docs-17, telli-docs-18) and reach-rate/success metrics (telli-docs-7), which together support scheduled, throughput-controlled outbound calling. However there is no explicit mention of a 'campaign' concept, bulk contact upload, or concurrency/rate limits for large batches. Missing for 10: explicit batch/campaign creation UI or endpoint, bulk contact import for calling, and documented concurrency/throughput limits beyond dialing windows.
- [claimed-docs] “Configure dialing windows, calling strategies, and retry behavior.”
- [claimed-docs] “Schedules a call at the earliest opportunity within the dialer window. May occur immediately or on the next business day depending on settin…”
- [claimed-docs] “Optional flag to bypass dialing window restrictions for the scheduled call. When true, calls at the scheduled time regardless of dialing win…”
- [claimed-docs] “Track key metrics like reach rate, call duration, and success rate.”
- [claimed-docs] “Workflows can now run automatically on a recurring schedule. Add a Scheduled trigger, choose the interval and start time, and let the workfl…”
Deepgram Voice Agentnone0/10Deepgram's docs confirm outbound telephony connectivity (docs-5, docs-18) and per-call features like barge-in and prompting, but there is no mention of campaign-level batch dialing, call scheduling, or throughput/rate controls for outbound campaigns — this is a real-time conversation API, not a dialer/campaign manager.
- [claimed-docs] “Telephony: connect voice agents to phone networks for inbound and outbound calls.”
- [claimed-docs] “Twilio streams the call audio to your server, and your server bridges that audio to the Deepgram Voice Agent API, a single WebSocket that ru…”
Numbers
developerProvision phone numbers and run both inbound and outbound calls through the platform's API
weight 3 · round to tellitelli's docs show a REST API with a schedule-call endpoint for outbound calls, an import-phone-number endpoint to bring SIP-trunk numbers under API control, webhooks for call events, and an OpenAPI spec confirming the API surface. However, inbound handling is documented mainly as manual forwarding/SIP trunk setup rather than a clear 'provision a new number via API' flow, and there's no explicit doc of purchasing/creating a fresh telli-hosted number through the API. missing for 10: a documented endpoint to provision/purchase brand-new phone numbers (not just import existing SIP trunk numbers), and clearer API-driven inbound call handling beyond forwarding.
- [claimed-docs] “API Endpoints: Use telli's REST API to programmatically manage contacts, schedule calls, and integrate with your existing systems.”
- [claimed-docs] “Schedules a call at the earliest opportunity within the dialer window. May occur immediately or on the next business day depending on settin…”
- [claimed-docs] “Imports a phone number from your own SIP trunk provider. This allows you to use existing phone numbers with telli by configuring custom SIP …”
- [claimed-docs] “Webhooks push data from telli to your systems in real time. When something happens on a call, telli sends a POST request to the endpoint you…”
- [claimed-docs] “Keep your public business number and forward incoming calls to a telli number. You configure the forwarding with your phone provider or PBX.”
- [claimed-docs] “Connect an existing number and phone system for incoming and outgoing calls. You need SIP trunk access from your provider.”
- [probe] “PROBE openapi: HTTP 200 at https://docs.telli.com/openapi.json — contains "openapi" key”
Docs confirm Deepgram Voice Agent supports inbound/outbound calls and telephony integration (e.g., via Twilio bridging audio to a single WebSocket), but there is no evidence Deepgram itself provisions or manages phone numbers—developers must bring their own Twilio account/number and build a bridging server. Missing for 10: native phone-number provisioning API, first-party telephony number management, and evidence of outbound call initiation directly through Deepgram's API without a third-party carrier.
- [claimed-docs] “Telephony: connect voice agents to phone networks for inbound and outbound calls.”
- [claimed-docs] “Twilio streams the call audio to your server, and your server bridges that audio to the Deepgram Voice Agent API, a single WebSocket that ru…”
- [claimed-docs] “That includes barge-in, the ability to talk over the agent and have it stop instantly.”
Sip
platform-engineerConnect my own carrier or PBX via SIP trunking (or import Twilio/Telnyx numbers) instead of being locked to bundled telephony
weight 2 · round to telliDocs explicitly support importing numbers from a customer's own SIP trunk provider via a dedicated API endpoint, plus general SIP trunk connection for incoming/outgoing calls and call forwarding from an existing PBX/provider number. This directly matches the platform-engineer's need to bring their own carrier rather than being locked into bundled telephony. Missing for 10: no explicit mention of native Twilio/Telnyx number import (only generic SIP trunk import), and no independent/hands-on confirmation of the SIP trunk setup working in practice.
- [claimed-docs] “Imports a phone number from your own SIP trunk provider. This allows you to use existing phone numbers with telli by configuring custom SIP …”
- [claimed-docs] “Keep your public business number and forward incoming calls to a telli number. You configure the forwarding with your phone provider or PBX.”
- [claimed-docs] “Connect an existing number and phone system for incoming and outgoing calls. You need SIP trunk access from your provider.”
Deepgram Voice Agentnone0/10Evidence only documents a generic WebSocket bridge pattern for Twilio (docs-18, docs-8) and a general 'Telephony' feature bullet (docs-5), but there is no mention of SIP trunking, PBX connectivity, or Telnyx number import — the specific mechanisms a platform engineer would need to bring their own carrier.
- [claimed-docs] “Telephony: connect voice agents to phone networks for inbound and outbound calls.”
- [claimed-docs] “Twilio streams the call audio to your server, and your server bridges that audio to the Deepgram Voice Agent API, a single WebSocket that ru…”
- [claimed-docs] “That includes barge-in, the ability to talk over the agent and have it stop instantly.”
Testing analytics — stories about testing analytics in this arenaTesting analytics
Stories about testing analytics in this arena
Analytics
ai-native userThe platform's AI reviews my calls for me — scoring quality, flagging failures, and analyzing resolution automatically
weight 2 · round to tellitelli provides analytics like reach rate, success rate, call outcome fields, transcripts, and manual feedback submission for agent improvement, but there's no evidence of automated AI-driven quality scoring, failure flagging, or resolution analysis performed autonomously by the platform's AI — feedback and analysis appear human-driven rather than AI-automated review. missing for 10: automated AI scoring of call quality, automatic failure/anomaly flagging, AI-generated resolution analysis without human review.
- [claimed-docs] “Track key metrics like reach rate, call duration, and success rate.”
- [claimed-docs] “Analyze individual calls, transcripts, and call outcome fields.”
- [claimed-docs] “Submit feedback on calls to continuously improve your agent.”
Deepgram Voice Agentnone0/10The evidence pack covers Deepgram Voice Agent's real-time conversation infrastructure (STT/TTS, function calling, telephony, prompting, A/B testing of voices/prompts) but contains no mention of post-call AI review, automated quality scoring, failure flagging, or resolution analysis of completed calls.
founderSee call analytics — success rates, durations, outcomes, sentiment — in dashboards without building my own
weight 2 · round to tellitelli's docs describe built-in dashboards tracking reach rate, call duration, and success rate, plus per-call analysis of transcripts and outcome fields, and a live monitoring overview—covering most of the story without needing custom tooling. However, there is no explicit mention of sentiment analysis in dashboards. missing for 10: sentiment scoring/analysis in dashboards, independent/hands-on corroboration of dashboard usability.
- [claimed-docs] “Track key metrics like reach rate, call duration, and success rate.”
- [claimed-docs] “Analyze individual calls, transcripts, and call outcome fields.”
- [claimed-docs] “Live Monitoring > Real-time call overview of your contacts”
Deepgram Voice Agentnone0/10Deepgram is a developer API/infrastructure product; evidence shows mentions of A/B testing metrics (conversion, CSAT, containment rate) as data points but no evidence of an actual built-in dashboard for call analytics, success rates, durations, sentiment, or outcomes that founders can view without building their own.
- [claimed-docs] “A/B testing voices or prompts — Run two configurations in parallel and measure conversion, CSAT, or containment rate to pick a winner—no cod…”
Monitoring
platform-engineerMonitor live calls in production and get alerts when agents misbehave or error rates spike
weight 1 · round to tellitelli offers a real-time Live Monitoring call overview (telli-docs-32) and webhooks that push real-time notifications on call events/status/outcomes (telli-docs-13, telli-docs-21), which a platform engineer could wire into an alerting pipeline, plus metric tracking like success/reach rate (telli-docs-7). However there is no documented built-in alerting mechanism, error-rate-spike detection, or agent-misbehavior alerting system. Missing for 10: native alert/notification thresholds, anomaly or error-rate-spike detection, and evidence of alert delivery (email/Slack/PagerDuty) tied to live monitoring.
- [claimed-docs] “Live Monitoring > Real-time call overview of your contacts”
- [claimed-docs] “Webhooks: Receive real-time notifications about call events, status changes, and outcomes.”
- [claimed-docs] “Webhooks push data from telli to your systems in real time. When something happens on a call, telli sends a POST request to the endpoint you…”
- [claimed-docs] “Track key metrics like reach rate, call duration, and success rate.”
Testing
developerTest agents with simulated conversations or evals before putting them on real phone calls
weight 2 · round to tellitelli's agent builder includes a 'Test call' feature to trial a draft or saved agent version and review the recording/transcript side-by-side before going live, which covers pre-production testing, and feedback submission helps iterate on agent quality. However, there is no evidence of simulated/synthetic conversation runs, automated eval suites, or scripted test scenarios independent of an actual phone call. Missing for 10: automated evals framework, non-call simulated conversation testing, batch/regression testing tools.
- [claimed-docs] “In the agent builder, click Test call to open the dialog. Pick the agent version (your draft with unsaved changes or any saved revision)...”
- [claimed-docs] “Use the side-by-side view to listen to the recording while following along in the transcript.”
- [claimed-docs] “Submit feedback on calls to continuously improve your agent.”
Deepgram Voice Agentnone0/10The evidence covers live-call features (function calling, prompting, telephony, A/B testing of live configs) but nothing describes a simulated-conversation or eval framework for pre-production testing of agents before real phone calls. Missing for 10: any documentation of a test/sandbox mode, conversation simulation tool, or eval harness for agents.
- [claimed-docs] “A/B testing voices or prompts — Run two configurations in parallel and measure conversion, CSAT, or containment rate to pick a winner—no cod…”
- [claimed-docs] “Reusable Agent Configurations allow you to define and persist the agent block of your Settings message using the Deepgram API. Once created,…”
Tools function calling — stories about tools function calling in this arenaTools function calling
Stories about tools function calling in this arena
Post call
developerExtract structured data from every call — outcomes, entities, dispositions — delivered via API or webhook after the call
weight 2 · round to tellitelli documents webhooks pushing real-time call event/status/outcome data and a REST API for programmatic access, plus conversation views showing appointment/outcome fields and call outcome analysis, supporting structured post-call data delivery. However, there's no explicit documentation of a structured schema for entities/dispositions extraction or example payloads showing the full breadth of structured fields promised. missing for 10: example webhook/API payload showing structured entities and disposition fields, documentation of a dedicated 'call outcomes' data model, independent/hands-on confirmation of data completeness.
- [claimed-docs] “Webhooks: Receive real-time notifications about call events, status changes, and outcomes.”
- [claimed-docs] “Webhooks push data from telli to your systems in real time. When something happens on a call, telli sends a POST request to the endpoint you…”
- [claimed-docs] “Analyze individual calls, transcripts, and call outcome fields.”
- [claimed-docs] “Conversations now show appointments saved during a call, including the time, status, hosts, and provider link.”
- [claimed-docs] “API Endpoints: Use telli's REST API to programmatically manage contacts, schedule calls, and integrate with your existing systems.”
Deepgram Voice Agentnone0/10The evidence pack covers live function calling during a call and various agent configuration/telephony features, but there is no mention of post-call structured data extraction (summaries, entities, dispositions) or webhook delivery of such analytics after a call ends.
Tools
ai-native userMy voice agent can plug in MCP servers as tool sources so one integration grants it whole toolsets mid-call
weight 2 · round drawntellinone0/10telli documents custom tools connecting to external APIs (telli-docs-20) and even an MCP server (telli-docs-22, telli-probe-3), but that MCP server lets external AI tools like Claude/ChatGPT talk to telli's Charlie assistant — it is telli acting as an MCP server, not the voice agent consuming external MCP servers as a tool source mid-call. There is no evidence the voice agent itself can plug in MCP servers to gain toolsets during a call.
- [claimed-docs] “The telli MCP server lets AI tools like Claude, ChatGPT, and Codex talk to Charlie, telli's AI assistant, over the Model Context Protocol.”
- [probe] “official MCP server documented at https://docs.telli.com/integrations/mcp”
- [claimed-docs] “Custom tools allow your AI agents to access external information by connecting to your APIs.”
Deepgram Voice Agentnone0/10Evidence confirms mid-call function calling exists for the Voice Agent (deepgram-docs-2) but only documents an MCP *server* built into the CLI that lets coding tools access Deepgram APIs (deepgram-docs-13, deepgram-probe-4) — this is the reverse direction, not the Voice Agent acting as an MCP client to pull in external toolsets mid-call. No evidence shows the Voice Agent itself can connect to MCP servers as a tool source.
- [claimed-docs] “In the context of Deepgram Voice Agents, function calling enables your agent to perform tasks during a live conversation.”
- [claimed-docs] “The dg CLI includes a built-in MCP (Model Context Protocol) server that gives AI coding tools direct access to Deepgram APIs.”
- [probe] “official MCP server documented at https://developers.deepgram.com/developer-tools/agentic-tools”
developerMy agent can call external APIs and custom functions mid-conversation and speak the result without awkward dead air
weight 3 · round drawnDocs confirm custom tools let agents call external APIs mid-call (telli-docs-20) and built-in tool calls like web_search operate during live calls (telli-docs-30), plus transfer tools show mid-call action execution (telli-docs-31). However, there is no documentation addressing latency masking or filler-speech to avoid 'dead air' while awaiting API responses. missing for 10: explicit evidence of latency-hiding/filler speech during tool calls, independent hands-on confirmation of smooth voice continuity.
- [claimed-docs] “Custom tools allow your AI agents to access external information by connecting to your APIs.”
- [claimed-docs] “For a Duo agent, open Tools > System and enable web_search to let the agent search the web for current public information during calls.”
- [claimed-docs] “Transfer tools | Move the call to another agent or number.”
Docs confirm function calling is a supported feature for performing tasks mid-conversation (deepgram-docs-2), and the agent architecture is a single low-latency WebSocket for audio in/out (deepgram-docs-1) with barge-in and inject-message features (deepgram-docs-8, deepgram-docs-11) suggesting attention to latency/dead-air. However there's no explicit documentation or example describing how function-call latency is masked (e.g., filler speech, streaming partial results) while awaiting an API response. Missing for 10: concrete guidance/examples on avoiding dead air during function execution, sample code showing async function calls with the agent speaking a holding phrase, and independent/hands-on verification of smooth latency handling.
- [claimed-docs] “In the context of Deepgram Voice Agents, function calling enables your agent to perform tasks during a live conversation.”
- [claimed-docs] “Deepgram's Voice Agent API collapses that stack into a single, unified API. You open one WebSocket connection, send audio in, and receive au…”
- [claimed-docs] “That includes barge-in, the ability to talk over the agent and have it stop instantly.”
- [claimed-docs] “Inject agent message | Mid-call | InjectAgentMessage | Makes the agent speak a specific line”
Transcription recording — stories about transcription recording in this arenaTranscription recording
Stories about transcription recording in this arena
Recording
platform-engineerRetrieve full call recordings and transcripts programmatically for every call
weight 2 · round to telliDocs confirm transcripts and recordings exist and can be reviewed in-app (side-by-side view, consent-based recording) and telli exposes a general REST API plus webhooks for call events, but no endpoint is documented that explicitly returns full call recordings or transcripts programmatically for every call. missing for 10: a documented GET/recording or GET/transcript API endpoint, confirmation of bulk/enumerable retrieval, and independent verification that recordings are accessible via the API rather than only in the UI.
- [claimed-docs] “Analyze individual calls, transcripts, and call outcome fields.”
- [claimed-docs] “Use the side-by-side view to listen to the recording while following along in the transcript.”
- [claimed-docs] “In telli, you can easily make audio recording conditional on the caller's consent — so a call is only recorded once they agree.”
- [claimed-docs] “API Endpoints: Use telli's REST API to programmatically manage contacts, schedule calls, and integrate with your existing systems.”
- [claimed-docs] “Webhooks: Receive real-time notifications about call events, status changes, and outcomes.”
- [claimed-docs] “Webhooks push data from telli to your systems in real time. When something happens on a call, telli sends a POST request to the endpoint you…”
- [probe] “PROBE openapi: HTTP 200 at https://docs.telli.com/openapi.json — contains "openapi" key”
Deepgram Voice Agentnone0/10The evidence pack covers Voice Agent architecture, function calling, telephony bridging, LLM providers, and data privacy opt-outs, but nowhere describes an API or mechanism to retrieve full call recordings or persisted transcripts after a call ends. No endpoint, storage feature, or retrieval workflow is documented for this specific capability.
Transcription
developerGet accurate real-time transcription with control over the STT provider, language models, or key terms
weight 2 · round to Deepgram Voice Agenttellinone0/10telli documents transcript viewing and side-by-side playback (telli-docs-29) but provides no evidence of developer-facing control over STT provider selection, choice of underlying language models, or custom key-term/vocabulary boosting for transcription accuracy.
- [claimed-docs] “Use the side-by-side view to listen to the recording while following along in the transcript.”
Docs confirm real-time transcription via the unified WebSocket API, selectable LLM providers (docs-9), and multilingual STT/TTS model choices (docs-10), giving developers meaningful control over STT and LLM models. However, there is no evidence of 'key terms' or keyword-boosting controls specific to the Voice Agent's transcription pipeline. Missing for 10: explicit key-term/keyword-boost configuration support, independent benchmarking of transcription accuracy.
- [claimed-docs] “Deepgram's Voice Agent API collapses that stack into a single, unified API. You open one WebSocket connection, send audio in, and receive au…”
- [claimed-docs] “Supported LLM providers | Parameter | open_ai | anthropic | aws_bedrock | google | groq | nvidia”
- [claimed-docs] “A multilingual voice agent has two model decisions: which STT model transcribes the user, and which TTS model speaks the agent.”
Voices tts — stories about voices tts in this arenaVoices tts
Stories about voices tts in this arena
Voices
founderClone a custom brand voice and use it for my agents, with a documented consent process
weight 2 · round to telliVoice cloning is documented as a real feature (telli-docs-27) letting founders give agents a custom voice, but the pack's only consent-related documentation concerns call recording consent (telli-docs-26), not a consent process specifically for cloning someone's voice. Missing for 10: explicit documented consent/authorization workflow for the voice being cloned (e.g., proof of rights from the voice owner), and any legal/compliance guardrails for cloning third-party voices.
- [claimed-docs] “Voice cloning lets you give your agent a custom voice (your own, a colleague's, or a professional voice actor's), so the agent sounds exactl…”
- [claimed-docs] “In telli, you can easily make audio recording conditional on the caller's consent — so a call is only recorded once they agree.”
developerChoose from a broad voice library or plug in multiple TTS providers to get the voice I want
weight 2 · round to telliDocs mention voice cloning to give an agent a custom voice, but there is no evidence of a curated voice library to choose from or the ability to plug in multiple external TTS providers as the story requires. missing for 10: evidence of a selectable voice library, multi-provider TTS integration, developer API/config for switching TTS engines.
- [claimed-docs] “Voice cloning lets you give your agent a custom voice (your own, a colleague's, or a professional voice actor's), so the agent sounds exactl…”
Deepgram Voice Agentnone0/10Evidence confirms TTS model selection exists (docs-10 references choosing a TTS model) but there is no documentation of a broad voice library or of plugging in multiple third-party TTS providers analogous to the multi-LLM-provider list (docs-9). Missing for 10: evidence of voice catalog/library breadth, evidence of multiple supported TTS providers/vendors, and any provider-switching mechanism for voice output.
- [claimed-docs] “A multilingual voice agent has two model decisions: which STT model transcribes the user, and which TTS model speaks the agent.”