> ## 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.

# 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.

> [accordion] Plain-text specification
>
> ## 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`. It runs privately, with zero data retention.
>
> ### 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 | Yes |
> | 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.