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

# Text-to-Speech Models

> Text-to-speech models with multilingual voice support

<div id="model-search-placeholder" data-filter="tts">Loading models...</div>

***

## Voice catalog

Voices are **model-specific**. The `voice` you pass must come from the catalog
of the `model` you selected. Pick a model below to browse its voices.

<div id="tts-voice-picker-placeholder">Loading voices...</div>

<Note>
  Voice IDs are case-sensitive and **only valid for the matching `model`**. Pass
  both fields together in your request payload. See the
  [Audio Speech API](/api-reference/endpoint/audio/speech) for examples.
</Note>

### Example request

```bash theme={"dark"}
curl https://api.venice.ai/api/v1/audio/speech \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-kokoro",
    "voice": "af_sky",
    "input": "Hello from Venice."
  }' \
  --output speech.mp3
```

To switch models, change **both** `model` and `voice` to a pair from the
selected model above.