AssemblyAI Voice Agent API vs GPT-Live

AssemblyAI Voice Agent API

One $0.075 a minute rate covers speech-to-text, the managed model, speech output, recordings and hosting, and the socket has an AsyncAPI file, typed error codes and a 30-second resume window. No concurrent-session limit is published, the status page has no Voice Agent component, and phone calls are inbound only through a Twilio trunk the customer owns.

GPT-Live

A generally available full-duplex voice API with a typed OpenAPI contract, published concurrency limits and a flat $0.05 a minute for the voice session. Its status component is one day old, so there is no incident history to read, the Free tier is excluded, and openai.com refused our reader, so the terms and privacy policy were not read.

AssemblyAI Voice Agent API

1. Send session.end before closing the socket. Without it the session stays resumable, and billed, for 30 seconds
2. Retry only at_capacity, concurrency_exceeded and internal_error, with backoff. Every other session error code is fatal
3. Send tool.result inside the reply.done handler, not straight after tool.call
4. Mint a one-time token with GET /v1/token for browser clients and never ship the API key to a page
5. Deduplicate webhooks on event_id, and verify X-AAI-Signature against the raw body bytes because a 401 is not retried

GPT-Live

1. Create sessions on a server with the project API key. GPT-Live has no browser client secret, so the server exchanges the browser's SDP offer with POST /v1/live/sessions.
2. Choose delegation.type at creation. Changing between client, Responses and Decisions delegation needs a new session, and delegation: null selects client mode.
3. After session.started, listen for error with code responses_validation_failed. Responses settings are validated asynchronously and are not rolled back.
4. Do not retry an outbound SIP POST /v1/live/sessions after a timeout. Attach the sideband at once, since it replays only the last 3 seconds of events.
5. Keep the transport open until session.closed to read the final usage.seconds. A WebRTC session bills 15 seconds at creation, credited once it runs.