Deepgram Voice Agent

Drive the product through a documented public API G

Agent access

Connect an agent via an official MCP server G

Agent access

Plug MCP servers into this product so it can use their tools G

Agent access

Delegate tasks to a built-in AI assistant inside the product G

Agentic features

Download a machine-readable API spec (OpenAPI or equivalent) G

Api quality

Point an agent at llms.txt or agent-oriented docs G

Agent access

Operate the product with natural-language commands G

Agentic features

Use an official CLI G

Agent access

Run the product headlessly / in CI for automation G

Agent access

Build against official SDKs G

Agent access

Issue scoped/least-privilege API credentials for an agent G

Agent access

Explore an interactive API reference with runnable examples G

Api quality

Get AI-generated insights and suggestions from my data inside the product G

Agentic features

Rely on versioned APIs with a documented deprecation policy G

Api quality

Set up automations that run autonomously in the background G

Agentic features

Subscribe to events via webhooks G

Agent access

Test against a sandbox environment without touching production data G

Api quality

Build a working phone voice agent — prompt, voice, and phone number — and take my first live call within an hour C

Build

My agent can call external APIs and custom functions mid-conversation and speak the result without awkward dead air C

Tools

Prevent my data from being used to train AI models G

Provision phone numbers and run both inbound and outbound calls through the platform's API C

Numbers

Rely on the agent to handle interruptions (barge-in) gracefully — stopping speech, updating context, and recovering the turn C

Turn taking

Define rules that trigger actions automatically on events G

My 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 C

Agent ops

See documented end-to-end voice latency numbers or tuning guidance backing the platform's speed claims C

Latency

Self-host the core product G

Self-host the voice agent runtime from open-source code on my own infrastructure C

Self host

Export all of my data in open formats and leave G

Choose where my data is stored (region/residency) G

Do everything through the API that I can do in the UI G

Get accurate real-time transcription with control over the STT provider, language models, or key terms C

Transcription

Inject dynamic variables and per-caller context at call time so each conversation is personalized C

Personalization

Control data retention and deletion G

Run conversations in multiple languages, including detecting and switching language mid-call C

Build

Meet call-recording consent and disclosure obligations with per-call recording controls and configurable data retention C

Compliance

Opt out of telemetry and usage tracking G

Run regulated workloads with HIPAA/BAA support, SOC 2, and data-residency options C

Compliance

Choose from a broad voice library or plug in multiple TTS providers to get the voice I want C

Voices

Connect my own carrier or PBX via SIP trunking (or import Twilio/Telnyx numbers) instead of being locked to bundled telephony C

Sip

Design multi-step conversation flows in a visual builder with branching, states, and handoffs without writing code C

Build

Ground the agent on my documents with a built-in knowledge base or RAG so it answers from my content C

Personalization

My voice agent can plug in MCP servers as tool sources so one integration grants it whole toolsets mid-call C

Tools

Run batch outbound call campaigns with scheduling and throughput controls C

Campaigns

See call analytics — success rates, durations, outcomes, sentiment — in dashboards without building my own C

Analytics

Test agents with simulated conversations or evals before putting them on real phone calls C

Testing

Clone a custom brand voice and use it for my agents, with a documented consent process C

Voices

Escalate a live call to a human with warm or blind transfer, passing context along C

Call control

Extract structured data from every call — outcomes, entities, dispositions — delivered via API or webhook after the call C

Post call

Perform bulk operations across many items at once G

Read the product's source under an open license G

Retrieve full call recordings and transcripts programmatically for every call C

Recording

Schedule recurring jobs or workflows G

See documented concurrency limits and scale to many simultaneous calls without manual capacity begging C

Scale

See published per-minute or usage pricing and estimate cost per call before committing G

Pricing

The platform's AI reviews my calls for me — scoring quality, flagging failures, and analyzing resolution automatically C

Analytics

Use model-based end-of-turn detection beyond simple VAD silence timeouts so the agent doesn't talk over slow speakers C

Turn taking

Version, review, and roll back my automations G

The platform's own AI helps me author agents — generating or improving prompts, flows, and test cases from a description C

Agent ops

Enable noise suppression or audio filtering so the agent stays coherent on noisy real-world calls C

Turn taking

Monitor live calls in production and get alerts when agents misbehave or error rates spike C

Monitoring

My agent can send DTMF keypresses, navigate IVR menus, and detect or leave voicemail C

Call control