# MiniMax Voice Clone API

> MiniMax Voice Clone by MiniMax creates a reusable custom voice from a reference recording of at least 10 seconds and returns a short preview spoken in that voice.

Source: https://www.sandbase.ai/models/minimax/voice-clone
API reference: https://www.sandbase.ai/models/minimax/voice-clone/docs

## Facts

- Provider: MiniMax
- Type: Audio model
- Model ID: `minimax/voice-clone`
- Price: From $1.80 per run
- Capabilities: text to speech
- Billing: pay per use from one SandBase balance; no provider account or subscription needed

## Call it

- Unified Run API: `POST https://api.sandbase.ai/v1/run`

```bash
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "minimax/voice-clone",
  "text": "Hello, this is a preview of your cloned voice! I hope you like it!",
  "audio": "https://static.sandbase.ai/examples/minimax/voice-clone/input_audio_0.wav",
  "noise_reduction": false,
  "need_volume_normalization": false
}'
```

The response returns a run id; poll `GET https://api.sandbase.ai/v1/run/{id}` until the status is `completed` or `failed`.

## FAQ

### How do I call MiniMax Voice Clone through SandBase?

Create a SandBase API key, then send requests with the model ID "minimax/voice-clone" to Unified Run API (/v1/run) at https://api.sandbase.ai. The request examples on this page show the exact payload.

### Do I need a separate MiniMax account?

No. One SandBase API key and balance gives you access to MiniMax Voice Clone and the other models in the catalog; you do not need to sign up with MiniMax separately.

## README

### MiniMax Voice Clone

Create a reusable custom voice from a reference recording of at least 10 seconds. The response includes the voice ID and a short spoken preview.

#### Fields

| Field | Type | Default | Notes |
|---|---|---|---|
| `audio` | audio URL, required | — | Reference recording, 10 seconds or longer. |
| `text` | string | `Hello, this is a preview of your cloned voice! I hope you like it!` | Preview sentence spoken in the new voice. |
| `need_volume_normalization` | boolean | false | Normalize the recording level. |
| `noise_reduction` | boolean | false | Clean background noise first. |
| `accuracy` | number 0–1 | — | Text-validation threshold for the recording. |

#### Billing

$1.50 per cloned voice plus $0.30 per started 1,000 preview characters.

| Request | Price |
|---|---|
| One voice | $1.80 |

Failed runs are not charged.

#### Prompting

- Record in a quiet room with one speaker.

#### Limits

- Use the returned voice ID as `voice_id` in MiniMax Speech.

#### Also on SandBase

Related: `minimax/speech/2.8/hd`, `minimax/speech/2.8/turbo`, `minimax/voice-design`.