Generate speech (TTS)
Audio
Generate speech
Convert text to spoken audio synchronously and get it back inline as base64. model and input are required; voice, format (mp3 default), and speed are normalized and validated against the model’s declared capabilities, and everything in parameters is forwarded verbatim to the provider. Output is saved to /v3/files by default and returned with a reusable file_id; set store: false to opt out.
POST
Generate speech (TTS)
See the Audio guide for runnable examples and voices.
Authorizations
API key authentication. Pass your API key as a Bearer token.
Body
application/json