> ## Documentation Index
> Fetch the complete documentation index at: https://docs.musicmint.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# MusicMint - AI Music API

> Enterprise-grade AI music generation API for developers

## Welcome to MusicMint

MusicMint gives you a single, consistent REST API to generate professional-quality music, lyrics, audio stems, and more — powered by multiple best-in-class AI models under the hood.

Whether you're building a music app, a content creation tool, or automating audio production at scale, MusicMint handles the complexity so you can focus on your product.

<CardGroup cols={2}>
  <Card title="Quick Start" icon="rocket" href="/quickstart">
    Get your first track generated in under 5 minutes.
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/introduction">
    Explore all endpoints, parameters, and response formats.
  </Card>

  <Card title="Authentication" icon="key" href="/api-reference/appkey">
    Create and manage your AppKey.
  </Card>

  <Card title="Webhooks" icon="webhook" href="/api-reference/webhooks">
    Get notified when long-running tasks complete.
  </Card>
</CardGroup>

## Core capabilities

### Music generation

Create original, full-length tracks from a text prompt or style tags. Specify mood, genre, instrumentation, or paste in your own lyrics. MusicMint routes your request to the best available model and returns a stream-ready MP3.

### Cover & remix

Transform an existing clip with new style, key, or lyrics. Use the remaster endpoint to clean up or re-process audio without changing the underlying composition.

### Vocal tools

* **Add Vocals** — layer AI-generated vocals on top of an instrumental
* **Add Instrumental** — add a backing track beneath an uploaded vocal recording
* **Sample / Humming** — hum a melody, upload it, and get a fully produced song back

### Lyrics generation

Generate song lyrics from a prompt or topic using large language models. Returns structured verses, chorus, and bridge sections ready to paste into a generation request.

### Audio processing

* **Stem separation** — split a track into vocals, drums, bass, and other
* **MIDI export** — extract a MIDI representation of any clip
* **Waveform / WAV** — get raw waveform data or lossless audio
* **Lyrics timeline** — per-word timestamps for karaoke or subtitle sync

### AI Singer (Persona)

Train a custom AI voice model from a short audio sample. Once created, the persona can sing any lyrics in a consistent, recognizable voice.

## How it works

All generation endpoints are **asynchronous**. You submit a request, receive a `task_id`, then either poll `GET /api/v1/task/{id}` or receive a webhook callback when the result is ready. Most tracks complete in 30–120 seconds.

A few utility endpoints (audio upload, concat) are **synchronous** and return results immediately.

## Reliability & scale

* **Multi-model routing** — requests are distributed across providers with automatic failover
* **Priority queues** — your API tier determines queue priority; Pro keys skip the free queue
* **TTL-managed storage** — generated files are stored on CDN with configurable retention (default 7 days)
* **Signed webhooks** — every callback is signed with HMAC-SHA256 so you can verify authenticity

## Rate limits & quotas

Limits are enforced per AppKey and configured in the dashboard. Contact support to request higher limits for production workloads.