Sign in

v51

OpenAPI 3.1.0raw.githubusercontent.com2026-08-018486293.2 KB
audio

Create Speech

OpenAI-compatible audio speech (TTS) endpoint.

Authentication modes:

  • Master key + user field: Use specified user (must exist)
  • API key + user field: Use specified user (must exist)
  • API key without user field: Use the shared "default" user
post/v1/audio/speech

Request body

inputstring required
instructionsstring nullable
modelstring required
response_formatstring nullable
speednumber nullable
userstring nullable
voicestring required

Response

Audio bytes in the requested format

{"stackTrail":"paths:/v1/audio/speech:post:responses:200:content:application/json:schema","oasType":"schema","type":"unknown"}