# Mureka | Generate Track | Stem Generation

Generates individual audio stems from any track, including vocals, instrumentals, and specific instruments such as drums, bass, guitar, strings, and more.

## API Information

- **Model Slug:** mureka-generate-track-stem-generation
- **Branded URL:** https://www.eachlabs.ai/mureka/mureka/mureka-generate-track-stem-generation
- **Provider:** Mureka
- **Category:** Text to Voice
- **Output Type:** object
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** Track generation: $0.09 per track (Mureka V8 list). Applies to all 12 generate_type variants.
- **Estimated Processing Time:** 60 seconds
- **Last Updated:** 2026-04-27
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/mureka-generate-track-stem-generation

## Pricing

- **Charge Type:** dynamic
- **Estimated Price (default example):** $0.0900
- **Pricing Details:** Track generation: $0.09 per track (Mureka V8 list). Applies to all 12 generate_type variants.

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | Track generation: $0.09 per track (Mureka V8 list). Applies to all 12 generate_type variants. |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | No | - | - | Free-text style prompt (e.g. 'fingerpicking, acoustic, melancholic'). Required when generate_type is Vocals, Instrumental, or a single-instrument type. |
| generate_type | string | Yes | Vocals | Vocals, Instrumental, Drums, Bass, Guitar, Keyboard, Percussion, Strings, Synth, FX, Brass, Woodwinds | Track type to generate. Vocals requires lyrics + prompt and supports vocal_gender. Instrumental requires prompt. Single-instrument types (Drums/Bass/Guitar/etc) require prompt. |
| song_id | string | No | - | - | ID of an existing Mureka song. Mutually exclusive with upload_audio_id. One of song_id/upload_audio_id is required. |
| upload_audio_id | string | No | - | - | Upload ID (purpose=audio). Mutually exclusive with song_id. One of song_id/upload_audio_id is required. |
| lyrics | string | No | - | - | Lyrics for the generated track. Required when generate_type=Vocals. Use square-bracket section tags for structure. |
| vocal_gender | string | No | - | male, female | Vocal gender. Only applicable when generate_type=Vocals — ignored otherwise. |
| generate_start | integer | No | - | - | Start offset (ms) of the segment of the source to use as musical context. Optional. |
| generate_end | integer | No | - | - | End offset (ms) of the segment of the source. Optional. |

## 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-generate-track-stem-generation",
  "input": {
    "generate_type": "Guitar"
  }
}'
```

## 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 | Generate Track | Stem Generation Overview**

Mureka | Generate Track | Stem Generation is a specialized AI model that isolates and generates individual musical stems—vocals, instruments, or specific instrument tracks—from existing audio sources or complete songs. Built on Mureka's V8 architecture, this model solves a critical problem for music producers, content creators, and sound engineers: the ability to extract, remix, or regenerate specific instrumental or vocal components without access to the original multitrack files. Unlike generic music generation tools, Mureka | Generate Track | Stem Generation focuses on stem-level precision, allowing users to generate Vocals, Drums, Bass, Guitar, Keyboard, Percussion, Strings, Synth, FX, Brass, or Woodwinds as isolated tracks. This capability is essential for remixing, music production, podcast audio enhancement, and adaptive soundtrack creation where individual track control is non-negotiable.

## 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.