# Mureka | Vocal Clone

Mureka Vocal Clone turns a short audio sample into a reusable custom voice for singing and speech. One voice ID, consistent across every track you generate.

## API Information

- **Model Slug:** mureka-vocal-clone
- **Branded URL:** https://www.eachlabs.ai/mureka/mureka/mureka-vocal-clone
- **Provider:** Mureka
- **Category:** Voice to Text
- **Output Type:** object
- **Status:** active
- **Base Cost:** $5.00 per execution
- **Estimated Processing Time:** 60 seconds
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/mureka-vocal-clone

## Pricing

- **Charge Type:** dynamic
- **Estimate:** $5.00 per execution
- **Pricing Details:** default: $5.00

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| file | string | Yes | - | - | Public URL of the vocal sample to clone. Executor-worker downloads the URL and forwards it as multipart/form-data. Supported formats: mp3, m4a. Max 10 MB. Supported vocal duration range: 15-30 seconds; excess audio is trimmed by Mureka. |
| description | string | No | - | - | Optional vocal description. Maximum 1024 characters. |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "mureka-vocal-clone",
  "input": {
    "file": "https://cdn-us.eachlabs.ai/defaults/8a4c47c1e0f14e648f51dde50ab6dcb6.mp3"
  }
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "object",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**Mureka | Vocal Clone Overview**

**Mureka | Vocal Clone** is a voice cloning feature from Mureka, the AI music platform by Kunlun Tech, that creates a reusable vocal identity from a short MP3 or M4A sample. It is designed for users who want voice-controlled music generation with a consistent singer-like timbre across future outputs. In practice, **Mureka | Vocal Clone** helps turn a one-time reference recording into a voice asset that can be reused for new music generation workflows, which makes it useful for branded content, creator identities, and repeatable vocal style experiments. The broader Mureka family is known for music generation, lyric control, stems, MIDI export, and multilingual output, and the voice cloning feature sits within that more production-oriented ecosystem.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.