Stream Recording | SpeechifyAI API

Proxy the GCS-stored audio recording for a conversation through the Cloud Run service identity. Returns OGG/Opus bytes (LiveKit room-composite egress default). The response is streamed so a long recording does not buffer in memory; <audio src> consumers can seek directly. Only present when the agent had save_audio_recording enabled at session start.

Authentication

AuthorizationBearer

Enter your API key with the Bearer prefix, e.g. ‘Bearer sk_…’.

Path parameters

conversation_idstringRequired

Conversation id (prefixed external id, conv_...).

Response headers

X-Request-IDstring

Unique identifier for this request, present on every response (2xx and non-2xx alike). If the caller sends an X-Request-ID request header the server echoes it back (sanitized and length-capped) so one logical request can be traced end-to-end; otherwise the server generates a fresh value. Log it on every response and quote it in support requests - it is the stable handle that ties your observation to Speechify’s server-side logs, and it matches the request_id field in the error envelope.

Unique identifier for this request, present on every response (2xx and non-2xx alike). If the caller sends an `X-Request-ID` request header the server echoes it back (sanitized and length-capped) so one logical request can be traced end-to-end; otherwise the server generates a fresh value. Log it on every response and quote it in support requests - it is the stable handle that ties your observation to Speechify's server-side logs, and it matches the `request_id` field in the error envelope.

Response

The recorded audio.

Errors

401

Unauthorized Error

404

Not Found Error