Docs: response-streaming behaviour on POST /v1/audio/stream clarified
Docs: response-streaming behaviour on POST /v1/audio/stream clarified
The documentation for POST /v1/audio/stream now describes the endpoint’s response shape accurately:
-
The response body is the raw audio bytes delivered over HTTP chunked transfer encoding. There is no JSON envelope and no Base64 encoding — that shape is what
POST /v1/audio/speechreturns. -
The
Acceptheader selects the container/codec. Each format’s responseContent-Typeand codec are now listed explicitly: -
audio/pcmreturns the IANA-registeredaudio/L16type withrateandchannelsparameters per RFC 4856. Byte order is little-endian (industry convention, not the big-endian default the RFC specifies). The 200 response in the API reference now listsaudio/L16alongsideaudio/mpeg/audio/ogg/audio/aac.
All formats deliver 24 kHz mono audio.
No API behaviour changed. This is a documentation correction only.