API reference
Generate speech
Synthesize a complete audio clip from text. OpenAI-compatible.
POST
Generates speech for the given text and returns raw audio bytes. The endpoint is
drop-in compatible with the OpenAI Audio API — point the OpenAI SDK at
https://sabi-tts.dev.neuralace.co/v1 with your sk_ key.
Authorization
Bearer sk_… — your secret API key.Body
The voice id. Use
capella.The text to speak. Supports inline audio tags.
One of
wav, mp3, pcm, opus, flac. With pcm, audio is streamed to the
response as it is synthesized (lowest time-to-first-byte).Accepted for OpenAI SDK compatibility but ignored — the voice selects the model.
Response
Raw audio bytes with the matchingContent-Type (audio/wav, audio/mpeg, audio/pcm,
audio/opus, or audio/flac) and Cache-Control: no-store.
Model inference time for this request, in milliseconds.
Total gateway time in milliseconds. Subtract
x-upstream-ms to get exact gateway
overhead for the same request.