> ## Documentation Index
> Fetch the complete documentation index at: https://docs.behaviq.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Audio

Audio endpoints:

* `GET /v1/audio/voices`
* `POST /v1/audio/tts`

## List voices

This endpoint is public.

```bash theme={null}
curl https://behaviq.io/v1/audio/voices
```

Example response:

```json theme={null}
{
  "voices": ["alloy", "echo", "fable", "onyx", "nova", "shimmer"]
}
```

## Generate speech

```bash theme={null}
curl https://behaviq.io/v1/audio/tts \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Please step back for a moment while I check that for you.",
    "voice": "alloy",
    "format": "mp3"
  }'
```

Request fields:

* `text` required
* `voice` required
* `speed` from `0.25` to `4`
* `format`: `mp3`, `opus`, `aac`, `flac`, `wav`, `pcm`
* `instructions`

The response includes `audioBase64` and `contentType`.

A text to speech request counts as one TTS use.

For API key traffic:

* credit-balance workspaces use `3` credits per TTS request
* enterprise pooled workspaces use included workspace TTS first, then credits if available
* enterprise per-user workspaces use credits for API key traffic

Signed-in app usage can also be limited by member TTS limits.