Voice Agent Platforms arenaBuyer checklist

Every requirement we judge voice agent platforms products against, as a ready-to-send RFP checklist — with each item's priority, why it matters, and how the top-ranked products score on it today.

61 requirements · 14 themes · verdicts for 9 products · updated 2026-09-15 · priorities mirror the story weights our scoring uses (methodology)

Procurement report →

Show the markdown export

# Voice Agent Platforms — buyer checklist (RFP)

Derived from ProductArena's evidence-graded user-story taxonomy for Voice Agent Platforms: 61 judged requirements. Priorities mirror story weights (3 = must-have, 2 = should-have, 1 = nice-to-have).

## Agent building

- [ ] **[must-have]** 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
- [ ] **[must-have]** Build a working phone voice agent — prompt, voice, and phone number — and take my first live call within an hour
- [ ] **[should-have]** Run conversations in multiple languages, including detecting and switching language mid-call
- [ ] **[should-have]** Design multi-step conversation flows in a visual builder with branching, states, and handoffs without writing code
- [ ] **[should-have]** Inject dynamic variables and per-caller context at call time so each conversation is personalized
- [ ] **[should-have]** Ground the agent on my documents with a built-in knowledge base or RAG so it answers from my content
- [ ] **[nice-to-have]** The platform's own AI helps me author agents — generating or improving prompts, flows, and test cases from a description

## Agenticness

- [ ] **[must-have]** Plug MCP servers into this product so it can use their tools
- [ ] **[must-have]** Connect an agent via an official MCP server
- [ ] **[must-have]** Drive the product through a documented public API
- [ ] **[must-have]** Delegate tasks to a built-in AI assistant inside the product
- [ ] **[should-have]** Point an agent at llms.txt or agent-oriented docs
- [ ] **[should-have]** Run the product headlessly / in CI for automation
- [ ] **[should-have]** Use an official CLI
- [ ] **[should-have]** Issue scoped/least-privilege API credentials for an agent
- [ ] **[should-have]** Build against official SDKs
- [ ] **[should-have]** Subscribe to events via webhooks
- [ ] **[should-have]** Get AI-generated insights and suggestions from my data inside the product
- [ ] **[should-have]** Set up automations that run autonomously in the background
- [ ] **[should-have]** Operate the product with natural-language commands
- [ ] **[should-have]** Explore an interactive API reference with runnable examples
- [ ] **[should-have]** Download a machine-readable API spec (OpenAPI or equivalent)
- [ ] **[should-have]** Rely on versioned APIs with a documented deprecation policy
- [ ] **[nice-to-have]** Test against a sandbox environment without touching production data

## Automation depth

- [ ] **[must-have]** Define rules that trigger actions automatically on events
- [ ] **[should-have]** Perform bulk operations across many items at once
- [ ] **[should-have]** Schedule recurring jobs or workflows
- [ ] **[nice-to-have]** Version, review, and roll back my automations

## Compliance trust

- [ ] **[should-have]** Meet call-recording consent and disclosure obligations with per-call recording controls and configurable data retention
- [ ] **[should-have]** Run regulated workloads with HIPAA/BAA support, SOC 2, and data-residency options

## Deployment scale

- [ ] **[must-have]** Self-host the voice agent runtime from open-source code on my own infrastructure
- [ ] **[should-have]** See documented concurrency limits and scale to many simultaneous calls without manual capacity begging

## Latency turntaking

- [ ] **[must-have]** See documented end-to-end voice latency numbers or tuning guidance backing the platform's speed claims
- [ ] **[must-have]** Rely on the agent to handle interruptions (barge-in) gracefully — stopping speech, updating context, and recovering the turn
- [ ] **[should-have]** Use model-based end-of-turn detection beyond simple VAD silence timeouts so the agent doesn't talk over slow speakers
- [ ] **[nice-to-have]** Enable noise suppression or audio filtering so the agent stays coherent on noisy real-world calls

## Openness

- [ ] **[must-have]** Export all of my data in open formats and leave
- [ ] **[must-have]** Self-host the core product
- [ ] **[should-have]** Do everything through the API that I can do in the UI
- [ ] **[should-have]** Read the product's source under an open license

## Pricing plans

- [ ] **[should-have]** See published per-minute or usage pricing and estimate cost per call before committing

## Privacy posture

- [ ] **[must-have]** Prevent my data from being used to train AI models
- [ ] **[should-have]** Choose where my data is stored (region/residency)
- [ ] **[should-have]** Control data retention and deletion
- [ ] **[should-have]** Opt out of telemetry and usage tracking

## Telephony

- [ ] **[must-have]** Provision phone numbers and run both inbound and outbound calls through the platform's API
- [ ] **[should-have]** Escalate a live call to a human with warm or blind transfer, passing context along
- [ ] **[should-have]** Run batch outbound call campaigns with scheduling and throughput controls
- [ ] **[should-have]** Connect my own carrier or PBX via SIP trunking (or import Twilio/Telnyx numbers) instead of being locked to bundled telephony
- [ ] **[nice-to-have]** My agent can send DTMF keypresses, navigate IVR menus, and detect or leave voicemail

## Testing analytics

- [ ] **[should-have]** The platform's AI reviews my calls for me — scoring quality, flagging failures, and analyzing resolution automatically
- [ ] **[should-have]** See call analytics — success rates, durations, outcomes, sentiment — in dashboards without building my own
- [ ] **[should-have]** Test agents with simulated conversations or evals before putting them on real phone calls
- [ ] **[nice-to-have]** Monitor live calls in production and get alerts when agents misbehave or error rates spike

## Tools function calling

- [ ] **[must-have]** My agent can call external APIs and custom functions mid-conversation and speak the result without awkward dead air
- [ ] **[should-have]** Extract structured data from every call — outcomes, entities, dispositions — delivered via API or webhook after the call
- [ ] **[should-have]** My voice agent can plug in MCP servers as tool sources so one integration grants it whole toolsets mid-call

## Transcription recording

- [ ] **[should-have]** Retrieve full call recordings and transcripts programmatically for every call
- [ ] **[should-have]** Get accurate real-time transcription with control over the STT provider, language models, or key terms

## Voices tts

- [ ] **[should-have]** Clone a custom brand voice and use it for my agents, with a documented consent process
- [ ] **[should-have]** Choose from a broad voice library or plug in multiple TTS providers to get the voice I want

---

Source: https://ultrametric.ai/productarena/arena/voice-agents (evidence-graded verdicts for 9 products) · methodology: https://ultrametric.ai/productarena/methodology

Chips show the top 5 ranked products' current verdict on each requirement — ✓ full · ~ partial · ! disputed · — none · n/a not applicable.

Agent building — building agents — abstractions, tool wiring, control flowAgent building· 7 items

Building agents — abstractions, tool wiring, control flow

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
Core requirement — weighs 3× in arena scoring · 3 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
must-have
developerBuild a working phone voice agent — prompt, voice, and phone number — and take my first live call within an hour
Core requirement — weighs 3× in arena scoring · 5 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
must-have
developerRun conversations in multiple languages, including detecting and switching language mid-call
Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet
telli Bland Retell AI LiveKit Agents Bolna
should-have
founderDesign multi-step conversation flows in a visual builder with branching, states, and handoffs without writing code
Important, not disqualifying — weighs 2× in arena scoring · 2 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
should-have
developerInject dynamic variables and per-caller context at call time so each conversation is personalized
Important, not disqualifying — weighs 2× in arena scoring · 1 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
should-have
developerGround the agent on my documents with a built-in knowledge base or RAG so it answers from my content
Important, not disqualifying — weighs 2× in arena scoring · 1 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
should-have
ai-native userThe platform's own AI helps me author agents — generating or improving prompts, flows, and test cases from a description
Differentiator, not a dealbreaker — weighs 1× in arena scoring · no product fully delivers this yet
telli Bland Retell AI LiveKit Agents Bolna
nice-to-have

Agenticness — how well agents can access and operate the productAgenticness· 17 items

How well agents can access and operate the product

ai-native userPlug MCP servers into this product so it can use their tools
Core requirement — weighs 3× in arena scoring · 3 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
must-have
ai-native userConnect an agent via an official MCP server
Core requirement — weighs 3× in arena scoring · 7 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
must-have
ai-native userDrive the product through a documented public API
Core requirement — weighs 3× in arena scoring · 8 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
must-have
ai-native userDelegate tasks to a built-in AI assistant inside the product
Core requirement — weighs 3× in arena scoring · 2 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
must-have
ai-native userPoint an agent at llms.txt or agent-oriented docs
Important, not disqualifying — weighs 2× in arena scoring · all 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
should-have
ai-native userRun the product headlessly / in CI for automation
Important, not disqualifying — weighs 2× in arena scoring · 2 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
should-have
ai-native userUse an official CLI
Important, not disqualifying — weighs 2× in arena scoring · 8 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
should-have
ai-native userIssue scoped/least-privilege API credentials for an agent
Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet
telli Bland Retell AI LiveKit Agents Bolna
should-have
ai-native userBuild against official SDKs
Important, not disqualifying — weighs 2× in arena scoring · 4 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
should-have
ai-native userSubscribe to events via webhooks
Important, not disqualifying — weighs 2× in arena scoring · 3 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
should-have
ai-native userGet AI-generated insights and suggestions from my data inside the product
Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet
telli Bland Retell AI LiveKit Agents Bolna
should-have
ai-native userSet up automations that run autonomously in the background
Important, not disqualifying — weighs 2× in arena scoring · 2 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
should-have
ai-native userOperate the product with natural-language commands
Important, not disqualifying — weighs 2× in arena scoring · 6 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
should-have
ai-native userExplore an interactive API reference with runnable examples
Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet
telli Bland Retell AI LiveKit Agents Bolna
should-have
ai-native userDownload a machine-readable API spec (OpenAPI or equivalent)
Important, not disqualifying — weighs 2× in arena scoring · 2 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
should-have
ai-native userRely on versioned APIs with a documented deprecation policy
Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet
telli Bland Retell AI LiveKit Agents Bolna
should-have
ai-native userTest against a sandbox environment without touching production data
Differentiator, not a dealbreaker — weighs 1× in arena scoring · 1 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
nice-to-have

Automation depth — how much of the product can run unattendedAutomation depth· 4 items

How much of the product can run unattended

ai-native userDefine rules that trigger actions automatically on events
Core requirement — weighs 3× in arena scoring · 1 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
must-have
ai-native userPerform bulk operations across many items at once
Important, not disqualifying — weighs 2× in arena scoring · 1 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
should-have
ai-native userSchedule recurring jobs or workflows
Important, not disqualifying — weighs 2× in arena scoring · 1 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
should-have
ai-native userVersion, review, and roll back my automations
Differentiator, not a dealbreaker — weighs 1× in arena scoring · no product fully delivers this yet
telli Bland Retell AI LiveKit Agents Bolna
nice-to-have

Compliance trust — stories about compliance trust in this arenaCompliance trust· 2 items

Stories about compliance trust in this arena

founderMeet call-recording consent and disclosure obligations with per-call recording controls and configurable data retention
Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet
telli Bland Retell AI LiveKit Agents Bolna
should-have
platform-engineerRun regulated workloads with HIPAA/BAA support, SOC 2, and data-residency options
Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet
telli Bland Retell AI LiveKit Agents Bolna
should-have

Deployment scale — stories about deployment scale in this arenaDeployment scale· 2 items

Stories about deployment scale in this arena

platform-engineerSelf-host the voice agent runtime from open-source code on my own infrastructure
Core requirement — weighs 3× in arena scoring · 3 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
must-have
platform-engineerSee documented concurrency limits and scale to many simultaneous calls without manual capacity begging
Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet
telli Bland Retell AI LiveKit Agents Bolna
should-have

Latency turntaking — stories about latency turntaking in this arenaLatency turntaking· 4 items

Stories about latency turntaking in this arena

platform-engineerSee documented end-to-end voice latency numbers or tuning guidance backing the platform's speed claims
Core requirement — weighs 3× in arena scoring · no product fully delivers this yet
telli Bland Retell AI LiveKit Agents Bolna
must-have
developerRely on the agent to handle interruptions (barge-in) gracefully — stopping speech, updating context, and recovering the turn
Core requirement — weighs 3× in arena scoring · 2 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
must-have
developerUse model-based end-of-turn detection beyond simple VAD silence timeouts so the agent doesn't talk over slow speakers
Important, not disqualifying — weighs 2× in arena scoring · 2 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
should-have
developerEnable noise suppression or audio filtering so the agent stays coherent on noisy real-world calls
Differentiator, not a dealbreaker — weighs 1× in arena scoring · 1 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
nice-to-have

Openness — open source, data portability, and self-hosting storiesOpenness· 4 items

Open source, data portability, and self-hosting stories

ai-native userExport all of my data in open formats and leave
Core requirement — weighs 3× in arena scoring · no product fully delivers this yet
telli Bland Retell AI LiveKit Agents Bolna
must-have
ai-native userSelf-host the core product
Core requirement — weighs 3× in arena scoring · 3 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
must-have
ai-native userDo everything through the API that I can do in the UI
Important, not disqualifying — weighs 2× in arena scoring · 3 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
should-have
ai-native userRead the product's source under an open license
Important, not disqualifying — weighs 2× in arena scoring · 2 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
should-have

Pricing plans — plan structure and value — what each tier costs and what it unlocksPricing plans· 1 item

Plan structure and value — what each tier costs and what it unlocks

founderSee published per-minute or usage pricing and estimate cost per call before committing
Important, not disqualifying — weighs 2× in arena scoring · 1 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
should-have

Privacy posture — data-handling and privacy storiesPrivacy posture· 4 items

Data-handling and privacy stories

ai-native userPrevent my data from being used to train AI models
Core requirement — weighs 3× in arena scoring · no product fully delivers this yet
telli Bland Retell AI LiveKit Agents Bolna
must-have
ai-native userChoose where my data is stored (region/residency)
Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet
telli Bland Retell AI LiveKit Agents Bolna
should-have
ai-native userControl data retention and deletion
Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet
telli Bland Retell AI LiveKit Agents Bolna
should-have
ai-native userOpt out of telemetry and usage tracking
Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet
telli Bland Retell AI LiveKit Agents Bolna
should-have

Telephony — stories about telephony in this arenaTelephony· 5 items

Stories about telephony in this arena

developerProvision phone numbers and run both inbound and outbound calls through the platform's API
Core requirement — weighs 3× in arena scoring · 3 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
must-have
developerEscalate a live call to a human with warm or blind transfer, passing context along
Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet
telli Bland Retell AI LiveKit Agents Bolna
should-have
founderRun batch outbound call campaigns with scheduling and throughput controls
Important, not disqualifying — weighs 2× in arena scoring · 1 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
should-have
platform-engineerConnect my own carrier or PBX via SIP trunking (or import Twilio/Telnyx numbers) instead of being locked to bundled telephony
Important, not disqualifying — weighs 2× in arena scoring · 6 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
should-have
developerMy agent can send DTMF keypresses, navigate IVR menus, and detect or leave voicemail
Differentiator, not a dealbreaker — weighs 1× in arena scoring · no product fully delivers this yet
telli Bland Retell AI LiveKit Agents Bolna
nice-to-have

Testing analytics — stories about testing analytics in this arenaTesting analytics· 4 items

Stories about testing analytics in this arena

ai-native userThe platform's AI reviews my calls for me — scoring quality, flagging failures, and analyzing resolution automatically
Important, not disqualifying — weighs 2× in arena scoring · 1 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
should-have
founderSee call analytics — success rates, durations, outcomes, sentiment — in dashboards without building my own
Important, not disqualifying — weighs 2× in arena scoring · 1 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
should-have
developerTest agents with simulated conversations or evals before putting them on real phone calls
Important, not disqualifying — weighs 2× in arena scoring · 5 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
should-have
platform-engineerMonitor live calls in production and get alerts when agents misbehave or error rates spike
Differentiator, not a dealbreaker — weighs 1× in arena scoring · no product fully delivers this yet
telli Bland Retell AI LiveKit Agents Bolna
nice-to-have

Tools function calling — stories about tools function calling in this arenaTools function calling· 3 items

Stories about tools function calling in this arena

developerMy agent can call external APIs and custom functions mid-conversation and speak the result without awkward dead air
Core requirement — weighs 3× in arena scoring · 3 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
must-have
developerExtract structured data from every call — outcomes, entities, dispositions — delivered via API or webhook after the call
Important, not disqualifying — weighs 2× in arena scoring · 1 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
should-have
ai-native userMy voice agent can plug in MCP servers as tool sources so one integration grants it whole toolsets mid-call
Important, not disqualifying — weighs 2× in arena scoring · 3 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
should-have

Transcription recording — stories about transcription recording in this arenaTranscription recording· 2 items

Stories about transcription recording in this arena

platform-engineerRetrieve full call recordings and transcripts programmatically for every call
Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet
telli Bland Retell AI LiveKit Agents Bolna
should-have
developerGet accurate real-time transcription with control over the STT provider, language models, or key terms
Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet
telli Bland Retell AI LiveKit Agents Bolna
should-have

Voices tts — stories about voices tts in this arenaVoices tts· 2 items

Stories about voices tts in this arena

founderClone a custom brand voice and use it for my agents, with a documented consent process
Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet
telli Bland Retell AI LiveKit Agents Bolna
should-have
developerChoose from a broad voice library or plug in multiple TTS providers to get the voice I want
Important, not disqualifying — weighs 2× in arena scoring · 2 of 9 products fully deliver this today
telli Bland Retell AI LiveKit Agents Bolna
should-have

Full evidence behind every verdict lives on the arena page and each product page — chips above deep-link straight to the judged story.

🎙️Voice Agent Platforms arenaBuyer checklist

🤖Agent building — building agents — abstractions, tool wiring, control flowAgent building· 7 items

🤖Agenticness — how well agents can access and operate the productAgenticness· 17 items

⚙️Automation depth — how much of the product can run unattendedAutomation depth· 4 items

⚖️Compliance trust — stories about compliance trust in this arenaCompliance trust· 2 items

🚀Deployment scale — stories about deployment scale in this arenaDeployment scale· 2 items

💬Latency turntaking — stories about latency turntaking in this arenaLatency turntaking· 4 items

🔓Openness — open source, data portability, and self-hosting storiesOpenness· 4 items

💲Pricing plans — plan structure and value — what each tier costs and what it unlocksPricing plans· 1 item

🔒Privacy posture — data-handling and privacy storiesPrivacy posture· 4 items

💬Telephony — stories about telephony in this arenaTelephony· 5 items

📊Testing analytics — stories about testing analytics in this arenaTesting analytics· 4 items

🛠️Tools function calling — stories about tools function calling in this arenaTools function calling· 3 items

🎙️Transcription recording — stories about transcription recording in this arenaTranscription recording· 2 items

💬Voices tts — stories about voices tts in this arenaVoices tts· 2 items