POST Audio
Generate speech or queued music from text
Model-specific audio generation endpoint. Speech models return audio bytes synchronously. `minimax-music-v2` returns a 202 queue ticket and rejects speech-only fields such as `voice` and `speed`.
Endpoint
post
/v1/audio/speechResponses
200
Raw audio bytes; Content-Type matches `response_format`.
202
Queued music job accepted; poll the returned URLs.
400
Invalid request