Niches · Conversational voice agents
Talk to an app in the browser or on a device
Four or more companies' docs show a full fit.
What counts as done
A short-lived token minted server-side, interruptions honoured, and a client-side tool runs without the model speaking its plan aloud.
Measured, for our own tests: first audio back within 1 second of the user stopping. No docs we read state these figures, so they don't count against a listing here.
How agents ask for it: add a voice assistant to my app
, let users talk to the agent from the web page
, a companion that reacts to tone
Does the job 10
The docs show it meets the test above, and nothing we read says otherwise.
| Listing | Why |
|---|---|
| AssemblyAI Voice Agent API C AssemblyAI, Inc. | Server mints a single-use token with expires_in_seconds and max_session_duration_seconds; the browser connects with ?token=. Client function tools return tool.result, and hold mode keeps the agent from talking during a tool. source |
| Deepgram Voice Agent API BB Deepgram, Inc. | The server mints a short-lived token via /v1/auth/grant with ttl_seconds and the Browser Agent SDK takes a tokenFactory; client-side functions run in the browser and return FunctionCallResponse. source |
| ElevenLabs Agents API + MCP BB Eleven Labs Inc. | GET /v1/convai/conversation/token returns a WebRTC session token and a signed-URL endpoint exists, so the key stays server-side; client tools run in the browser with a configurable response timeout. source |
| Inworld Realtime API B Theai, Inc. dba Inworld AI | WebRTC with a session token minted by the backend so the Basic key stays server-side, server VAD interruption, and client-run tools with auto continuation. source |
| LiveKit Agents BB LiveKit Incorporated | Frontends join with a short-lived access token minted on the server with the API secret; WebRTC transport, interruptions and client RPC tools are documented. source |
| OpenAI Realtime API BB OpenAI OpCo, LLC | POST /v1/realtime/client_secrets mints an ek_ token lasting 10 seconds to 2 hours (default 10 minutes) for WebRTC in the browser; speed is settable from 0.25 to 1.5. source |
| Pipecat B Daily | The client SDK calls the developer's /api/start endpoint, which creates a Daily room and returns a room token, so the API key stays on the server; RTVI carries client-side function calls. source |
| Retell AI API + MCP B Retell AI Inc. | POST /v3/create-web-call returns a call-scoped access_token with expires_at for the browser SDK, so the API key stays on the server. source |
| Ultravox Realtime API C Theai, Inc. dba Inworld AI | The server creates the call and hands the client only its joinUrl, client tools run in the browser, and the agent reaction setting (listens or speaks-once) stops it narrating around a tool. source |
| Vapi API + MCP B Vapi Inc. | Web SDK with public keys and short-lived JWTs signed server-side with origin restrictions, plus client-side tools handled in the browser. source |
Does the job, with a limit 10
It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.
| Listing | Why |
|---|---|
| Amazon Nova 2 Sonic B Amazon Web Services, Inc. | Browser clients reach Sonic through a WebSocket server such as AgentCore with SigV4 auth; there is no short-lived client token in the Sonic docs, so the developer builds the auth layer. source |
| Bland AI API + MCP B Intelliga Corporation | An embeddable voice and chat widget identified by a public widget_id keeps the key off the page, but there is no token endpoint for a custom client and no client-side tool mechanism. source |
| Bolna API + MCP D Voxlabs Private Limited | The Web Call SDK takes a backend-minted ephemeral session (about 120 second TTL) so the key stays server-side. Client-side tools are not documented. source |
| Gemini Live API C Google LLC | Ephemeral tokens from auth_tokens, single use, locked by liveConnectConstraints. Resumption must be granted inside the token constraints or no handle arrives (acc-23), and one tester found replies unnaturally fast (acc-07). source |
| GPT-Live BB OpenAI OpCo, LLC | WebRTC with the server exchanging the browser's SDP offer, so the key stays server-side, but there is no short-lived client token. Client delegation runs tools in the app and can suppress the spoken acknowledgement. source |
| Rime Prism B Rime Labs, Inc. | No browser tokens or ephemeral keys: the app must stream the microphone through the developer's backend, which holds the key and adds a hop before first audio. source |
| Synthflow API + MCP D AgentFlow AI GmbH | A backend call returns a per-session media URL and sid for a WebSocket audio stream, so the API key stays server-side, but no client-side tool mechanism is documented and the sid is not described as short-lived. source |
| Vaani Developer Platform E Vaani AI Research Private Limited (Bengaluru, India, CIN U62099KA2025PTC201212) | POST /api/webrtc/session/create returns a session_token (session_ttl 60 to 86,400 s, default 30 minutes) that the client exchanges for WebRTC credentials, so the key stays server-side. No client-side tools documented. source |
| Vocily AI C VOCILY AI PRIVATE LIMITED | A website widget has voice with a public key that can be rotated, so the API key stays private, but it is a long-lived public key rather than a short-lived token and no client-side tools are documented. source |
| Vogent API E Monoid, Inc. | GET /dials/{id}/token returns a dial token described as safe to pass to a client, so the key stays server-side, but richer browser flows need advancedBrowserInteraction set with Vogent's help, and no client-side tools are documented. source |
Couldn't check 1
The docs were closed to us, or silent. These carry no mark either way.
| Listing | Why |
|---|---|
| Hume EVI (Empathic Voice Interface) C Hume AI, Inc. | EVI docs withdrawn (redirect to Audio Decisions), so the access-token flow could not be re-read. acc-27 moved a coding assistant's default voice from Hume EVI 3 to ElevenLabs for naturalness, citing about 300 ms latency. source |
Doesn't do this job 6
Listings in the category that do something else, with the reason.
| Listing | Why |
|---|---|
| CueLight D sshah03 (individual GitHub account, no name or organisation stated) | No session, token or speech model; a component only. The browser demo runs locally. source |
| fone.me F Fone | The website widget lets visitors call the owner's fone.me agent by voice, but it is a keyless embed of that agent, not a session a developer controls with client tools. source |
| Fresha AI Concierge F Fresha.com SV Ltd | Phone, SMS and in-app chat for Fresha clients only; no web voice SDK or token. source |
| Harmony.ai E monday.com Ltd. | No browser voice SDK or client token in the API; the API covers contacts, workflows, calls and webhooks only. source |
| Pipecat PhoneLLM B Daily | No browser session, token or audio; a text model only. source |
| PlaceCall C VOYGR Tech, Inc. | Phone calls to businesses only; no browser or app voice session. source |
What stops agents finishing
- no browser token, so the key would ship to the page
- ephemeral token runs in restricted mode until resumption is granted server-side
- voice too fast or looping with no pacing control
Around it
Before: auth.session-token. After: agent.tool-use.
Where this comes from
Weight 9 of 100 in Conversational voice agents: 4 of 31 accounts (acc-06, acc-07, acc-23, acc-27)
The same as data: /api/v1/use-cases/voice-agents.web-voice-assistant.json, or the MCP tool get_use_case with id voice-agents.web-voice-assistant. Other jobs in this category: /api/v1/niches?category=voice-agents.
For companies
Do agents find, use and choose your tools?
An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.