# MiniMax Speech 2.8 Turbo (speech-2-8-turbo)

Vendor: MiniMax
Model ID: `speech-2-8-turbo`
Base URL: `https://api.mulerouter.ai`
Type: Inference API (async task-based)

## Description
Fast text-to-speech model with 40+ languages, emotion control, voice modification, and interjection tags support

## Variant: Create Speech Generation Task

Endpoint: `POST /vendors/minimax/v1/speech-2.8-turbo/text-to-speech/generation`

### Input Schema
The API accepts the following input parameters:

- **`prompt`** (`string`, _required_):
  Text to convert to speech. Use <#x#> for pauses (x = 0.01-99.99 seconds). Supports interjection tags: (laughs), (sighs), (coughs), (clears throat), (gasps), (sniffs), (groans), (yawns).
  - Max length: 50000

- **`voice_modify`** (`object`, _optional_):
  Voice modification settings.

  - **`pitch`** (`integer`, _optional_):
    Pitch adjustment. Range: -100 to 100.
    - Default: `0`
    - Range: `-100` to `100`

  - **`timbre`** (`integer`, _optional_):
    Timbre adjustment. Range: -100 to 100.
    - Default: `0`
    - Range: `-100` to `100`

  - **`intensity`** (`integer`, _optional_):
    Intensity/energy of the voice. Range: -100 to 100.
    - Default: `0`
    - Range: `-100` to `100`

- **`audio_setting`** (`object`, _optional_):
  Audio output configuration.

  - **`format`** (`string`, _optional_):
    Audio format.
    - Options: `"mp3"`, `"pcm"`, `"flac"`
    - Default: `"mp3"`

  - **`bitrate`** (`integer`, _optional_):
    Bitrate of generated audio (bps).
    - Options: `32000`, `64000`, `128000`, `256000`
    - Default: `128000`

  - **`channel`** (`integer`, _optional_):
    Number of audio channels (1=mono, 2=stereo).
    - Options: `1`, `2`
    - Default: `1`

  - **`sample_rate`** (`integer`, _optional_):
    Sample rate of generated audio (Hz).
    - Options: `8000`, `16000`, `22050`, `24000`, `32000`, `44100`
    - Default: `32000`

- **`output_format`** (`string`, _optional_):
  Format of the output content. Default: hex.
  - Options: `"url"`, `"hex"`
  - Default: `"hex"`

- **`voice_setting`** (`object`, _optional_):
  Voice configuration settings.

  - **`vol`** (`number`, _optional_):
    Volume, range [0, 10].
    - Default: `1`
    - Range: `0.01` to `10`

  - **`pitch`** (`integer`, _optional_):
    Voice pitch, range [-12, 12].
    - Default: `0`
    - Range: `-12` to `12`

  - **`speed`** (`number`, _optional_):
    Speech speed, range [0.5, 2.0].
    - Default: `1`
    - Range: `0.5` to `2`

  - **`emotion`** (`string | null`, _optional_):
    Emotion of the generated speech.

  - **`voice_id`** (`string`, _optional_):
    Voice ID for synthesis. e.g. Chinese: male-qn-qingse, female-shaonv, female-yujie; English: Charming_Lady, English_Trustworthy_Man, English_Graceful_Lady. Supports 327+ system presets across 20+ languages. See docs for full list.

  - **`english_normalization`** (`boolean`, _optional_):
    Enables English text normalization to improve number reading performance.
    - Default: `false`

- **`language_boost`** (`string | null`, _optional_):
  Enhance recognition of specified languages and dialects.

- **`pronunciation_dict`** (`object`, _optional_):
  Custom pronunciation dictionary for text replacement.

  - **`tone_list`** (`list<string>`, _optional_):
    List of pronunciation replacements in format ['text/(pronunciation)', ...].

- **`normalization_setting`** (`object`, _optional_):
  Loudness normalization settings for the audio.

  - **`enabled`** (`boolean`, _optional_):
    Enable loudness normalization.
    - Default: `true`

  - **`target_peak`** (`number`, _optional_):
    Target peak level in dBTP.
    - Default: `-0.5`
    - Range: `-3` to `0`

  - **`target_range`** (`number`, _optional_):
    Target loudness range in LU.
    - Default: `8`
    - Range: `0` to `20`

  - **`target_loudness`** (`number`, _optional_):
    Target loudness in LUFS.
    - Default: `-18`
    - Range: `-70` to `-10`

**Required Parameters Example**:

```json
{
  "prompt": "<Text to convert to speech>"
}
```

**Full Example**:

```json
{
  "prompt": "<Text to convert to speech>",
  "voice_modify": {},
  "audio_setting": {},
  "output_format": "hex",
  "voice_setting": {},
  "language_boost": null,
  "pronunciation_dict": {},
  "normalization_setting": {}
}
```

## Variant: /vendors/minimax/v1/speech-2.8-turbo/text-to-speech/generation/{task_id}

Endpoint: `POST /vendors/minimax/v1/speech-2.8-turbo/text-to-speech/generation/{task_id}`

## Usage (Async Task API)
This model uses an async task-based workflow with two API calls:
1. **Submit a task** — `POST /v1/inference/speech-2-8-turbo` to create a generation task
2. **Poll for result** — `GET /v1/inference/speech-2-8-turbo/{task_id}` to check status and retrieve the result

### Step 1: Submit a Task

#### cURL
```bash
curl -X POST https://api.mulerouter.ai/vendors/minimax/v1/speech-2.8-turbo/text-to-speech/generation \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <YOUR_MULEROUTER_API_KEY>" \
  -d '{
    "prompt": "Your prompt here"
  }'
```

#### Python
```python
import requests

API_KEY = "<YOUR_MULEROUTER_API_KEY>"
ENDPOINT = "https://api.mulerouter.ai/vendors/minimax/v1/speech-2.8-turbo/text-to-speech/generation"

response = requests.post(
    ENDPOINT,
    headers={
        "Content-Type": "application/json",
        "Authorization": f"Bearer {API_KEY}"
    },
    json={
        "prompt": "Your prompt here"
    }
)

result = response.json()
task_id = result["task_info"]["id"]
print(f"Task created: {task_id}")
```

#### Node.js / TypeScript
```typescript
const API_KEY = "<YOUR_MULEROUTER_API_KEY>";
const ENDPOINT = "https://api.mulerouter.ai/vendors/minimax/v1/speech-2.8-turbo/text-to-speech/generation";

const response = await fetch(ENDPOINT, {
    method: "POST",
    headers: {
        "Content-Type": "application/json",
        "Authorization": `Bearer ${API_KEY}`
    },
    body: JSON.stringify({
        prompt: "Your prompt here"
    })
});

const result = await response.json();
const taskId = result.task_info.id;
console.log("Task created:", taskId);
```

#### Submit Response (202)
```json
{
  "task_info": {
    "id": "8e1e315e-b50d-4334-a231-be7d19a372f4",
    "status": "processing",
    "created_at": "2026-01-01T00:00:00.000Z"
  }
}
```

### Step 2: Poll for Result

Use the task ID from Step 1 to poll the status endpoint until the task is completed.

Endpoint: `GET /v1/inference/speech-2-8-turbo/{task_id}`

#### cURL
```bash
curl -X GET https://api.mulerouter.ai/vendors/minimax/v1/speech-2.8-turbo/text-to-speech/generation/<TASK_ID> \
  -H "Authorization: Bearer <YOUR_MULEROUTER_API_KEY>"
```

#### Python
```python
import time

status_url = f"https://api.mulerouter.ai/vendors/minimax/v1/speech-2.8-turbo/text-to-speech/generation/{task_id}"

while True:
    status = requests.get(status_url, headers={
        "Authorization": f"Bearer {API_KEY}"
    }).json()
    task_status = status["task_info"]["status"]
    if task_status in ("completed", "succeeded"):
        print("Result:", status)
        break
    elif task_status == "failed":
        print("Task failed:", status)
        break
    time.sleep(5)
```

#### Node.js / TypeScript
```typescript
const statusUrl = `https://api.mulerouter.ai/vendors/minimax/v1/speech-2.8-turbo/text-to-speech/generation/${taskId}`;

while (true) {
    const statusRes = await fetch(statusUrl, {
        headers: { "Authorization": `Bearer ${API_KEY}` }
    });
    const status = await statusRes.json();
    const taskStatus = status.task_info.status;
    if (taskStatus === "completed" || taskStatus === "succeeded") {
        console.log("Result:", status);
        break;
    } else if (taskStatus === "failed") {
        console.log("Task failed:", status);
        break;
    }
    await new Promise(r => setTimeout(r, 5000));
}
```

## Additional Resources

### Documentation

- [Model Playground](https://www.mulerouter.ai/models/speech-2-8-turbo)
- [API Documentation](https://mulerouter.ai/docs/api-reference/endpoint/minimax/speech-2.8-turbo)

### MuleRouter Platform

- [Platform Documentation](https://www.mulerouter.ai/docs)
- [API Keys Management](https://www.mulerouter.ai/app/api-keys)