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

# Audio speech (TTS) API

> OpenAI-compatible speech API with MiniMax metadata extensions.

# Audio speech (TTS) API

Text-to-speech compatible with OpenAI Audio Speech. Extra MiniMax options go in `metadata`. Music generation uses `POST /v1/music_generation`.

**Host:** `https://api.omniall.ai` · Auth `Authorization: Bearer sk-...`.

| Action | Method | Path |
| - | - | - |
| Create speech | `POST` | `/v1/audio/speech` |
| List voices | `POST` | `/v1/get_voice` |
| Music generation | `POST` | `/v1/music_generation` |

| Field | Required | Description |
| - | - | - |
| `model` | yes | e.g. `speech-2.8-hd`, `speech-2.8-turbo` |
| `input` | yes | Text to synthesize |
| `voice` | yes | Voice id, e.g. `English_Graceful_Lady` |
| `response_format` | no | `mp3`, `wav`, `flac`, … |
| `metadata` | no | MiniMax extensions (`voice_setting`, `audio_setting`, …) |

```bash theme={null}
curl -X POST "https://api.omniall.ai/v1/audio/speech" \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "speech-2.8-hd",
    "input": "Hello from Omniall AI",
    "voice": "English_Graceful_Lady",
    "response_format": "mp3"
  }' --output speech.mp3
```

Full fields and playgrounds: **API Reference → Audio → MiniMax audio**.


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