> ## 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.

# MiniMax Speech-02 HD API

> MiniMax Speech-02 HD API on Venice: text to speech with 15 voices at $125 per 1M characters (about $0.1031 per minute). Anonymized access without your identity.



## MiniMax Speech-02 HD API

MiniMax Speech-02 HD is a text-to-speech model by MiniMax, available on the Venice API as `tts-minimax-speech-02-hd`. The provider of this model may retain prompt data (though it is anonymized by Venice). For sensitive content, use a private model.

Clone your voice from a short recording and generate natural speech in it across 30+ languages.

### MiniMax Speech-02 HD API pricing

| Model ID | Variant | Privacy | Price |
| - | - | - | - |
| `tts-minimax-speech-02-hd` | Standard | Anonymized | \$125 / 1M chars |

### MiniMax Speech-02 HD specifications

| Spec | Value |
| - | - |
| Provider | MiniMax |
| Released | Apr 17, 2026 |
| Privacy | Anonymized |
| Status | Stable |
| Voices | 15 |
| Formats | mp3, pcm, flac |

### How to use the MiniMax Speech-02 HD API

Send requests to `POST https://api.venice.ai/api/v1/audio/speech` with `"model": "tts-minimax-speech-02-hd"` 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-minimax-speech-02-hd",
    "input": "Private AI for everyone.",
    "voice": "CalmWoman",
    "response_format": "mp3"
  }' --output speech.mp3
```

### Related models

* [ElevenLabs Multilingual v2 API](https://docs.venice.ai/models/elevenlabs-multilingual-v2.md): \$115 / 1M chars
* [ElevenLabs TTS v3 API](https://docs.venice.ai/models/elevenlabs-tts-v3.md): \$115 / 1M chars
* [Qwen 3 TTS 1.7B API](https://docs.venice.ai/models/qwen-3-tts-1-7b.md): \$113 / 1M chars
* [Qwen 3 TTS 0.6B API](https://docs.venice.ai/models/qwen-3-tts-0-6b.md): \$87.50 / 1M chars


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