# MiniMax Voice Cloning

> Clone any voice from a 10s-5min audio sample and use it as a custom voice_id with MiniMax speech models. Returns a cloned voice_id plus a preview audio clip.

- **Provider**: replicate
- **Model ID**: minimax/voice-cloning
- **Category**: tts_voice
- **Credits**: 6980 per request
- **Pricing Type**: fixed

## API Endpoint

Base URL: https://api.core.today/v1

### Create Prediction
POST /predictions

### Get Status
GET /predictions/{job_id}

### Cancel
DELETE /predictions/{job_id}

## Authentication

Header: `X-API-Key: YOUR_API_KEY`

## Input Parameters

- `accuracy` (number, optional): Text validation accuracy threshold (0-1) (Default: `0.7`; Range: min: 0, max: 1)
- `voice_file` (string, **required**): Voice file to clone. Must be MP3, M4A, or WAV format, 10s to 5min duration, and less than 20MB.
- `need_noise_reduction` (boolean, optional): Enable noise reduction. Use this if the voice file has background noise. (Default: `False`)
- `model` (string, optional): The text-to-speech model to train (Default: `speech-02-turbo`; Options: `speech-2.6-turbo`, `speech-2.6-hd`, `speech-02-turbo`, `speech-02-hd`)
- `need_volume_normalization` (boolean, optional): Enable volume normalization (Default: `False`)

## Example Request

```json
{
  "model": "minimax/voice-cloning",
  "input": {
    "need_noise_reduction": false,
    "need_volume_normalization": false,
    "accuracy": 0.7,
    "model": "speech-02-turbo",
    "voice_file": "https://replicate.delivery/czjl/21U5IFboRwrhBlKks9pmaz119Hvo1ISryE0LNUKuerpqS9UKA/output.wav"
  }
}
```

## Response Format

```json
{
  "job_id": "abc123",
  "status": "pending",
  "provider": "replicate",
  "model": "black-forest-labs/flux-schnell",
  "created_at": "2026-01-01T00:00:00Z",
  "result": null,
  "error": null
}
```

Status values: `pending`, `processing`, `completed`, `failed`, `cancelled`

## Usage Flow

1. POST /predictions with model and input → receive job_id
2. Poll GET /predictions/{job_id} until status is `completed` or `failed`
3. Result contains output URL(s) or data

## Output Type

json

## Tags

voice-cloning, tts, audio, voice-synthesis, minimax, custom-voice

## Documentation

https://replicate.com/minimax/voice-cloning