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

> ## Agent Instructions
> The Venice API is OpenAI-compatible: use any OpenAI SDK with the base URL `https://api.venice.ai/api/v1` and a Venice API key, or pay per request from a USDC wallet through x402 with no account.
> Read model IDs from `GET /models` or `GET /models/traits` at runtime instead of hardcoding them from memory or from these pages. Models are added and retired often.
> Every model's price is in https://docs.venice.ai/pricing.md. Quote video and audio jobs with `POST /video/quote` or `POST /audio/quote` before you queue them.
> Search these docs from an MCP client at https://docs.venice.ai/mcp. The full agent guide is https://docs.venice.ai/agents.md.

# Kokoro Text to Speech API

> Kokoro Text to Speech API on Venice: text to speech with 54 voices at $3.50 per 1M characters (about $0.0029 per minute). Private, with zero data retention.



## Kokoro Text to Speech API

Kokoro Text to Speech is a text-to-speech model by hexgrad, available on the Venice API as `tts-kokoro`. This model is private and no prompt data is stored in any capacity.

Kokoro is hexgrad's open-weight 82M-parameter text-to-speech model. It speaks in 54 voices across several languages and returns MP3, Opus, AAC, FLAC, WAV or PCM audio.

### Kokoro Text to Speech API pricing

| Model ID | Variant | Privacy | Price |
| - | - | - | - |
| `tts-kokoro` | Standard | Private | \$3.50 / 1M chars |

### Kokoro Text to Speech specifications

| Spec | Value |
| - | - |
| Provider | hexgrad |
| Released | Mar 19, 2025 |
| Privacy | Private |
| Status | Stable |
| Open weights | [hexgrad/Kokoro-82M](https://huggingface.co/hexgrad/Kokoro-82M) |
| Voices | 54 |
| Formats | mp3, opus, aac, flac, wav, pcm |

### How to use the Kokoro Text to Speech API

Send requests to `POST https://api.venice.ai/api/v1/audio/speech` with `"model": "tts-kokoro"` and your API key.

```bash theme={"system"}
curl https://api.venice.ai/api/v1/audio/speech \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-kokoro",
    "input": "Private AI for everyone.",
    "voice": "af_alloy",
    "response_format": "mp3"
  }' --output speech.mp3
```

### Related models

* [Inworld TTS-1.5 Max API](https://docs.venice.ai/models/inworld-tts-1-5-max.md): \$12.50 / 1M chars
* [xAI TTS v1 API](https://docs.venice.ai/models/xai-tts-v1.md): \$18.75 / 1M chars
* [Chatterbox HD (Resemble AI) API](https://docs.venice.ai/models/chatterbox-hd.md): \$50.00 / 1M chars
* [Gradium TTS API](https://docs.venice.ai/models/gradium-tts.md): \$47.50 / 1M chars


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.