Audio speech
Generate speech audio from text with OpenAI-compatible text-to-speech requests.
Overview
The speech endpoint turns text into audio. Availability depends on the configured upstream providers and models.
Request
POST https://uouo.cloud/v1/audio/speech
Body parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
| model | string | Yes | Text-to-speech model ID. |
| input | string | Yes | Text to synthesize. |
| voice | string | Yes | Voice ID supported by the model. |
| response_format | string | No | mp3, wav, opus, or provider-supported format. |
| speed | number | No | Speech speed for supported models. |
Example
curl https://uouo.cloud/v1/audio/speech \
-H "Authorization: Bearer $UOUODUO_API_KEY" \
-H "Content-Type: application/json" \
-o speech.mp3 \
-d '{
"model": "tts-1",
"voice": "alloy",
"input": "The gateway is ready for production traffic."
}'Notes
- Validate provider voice names before deploying.
- Store generated audio according to your own privacy and retention policy.
- Large text inputs can increase latency and cost.