# AI Audio & Music API

> Generate music, voiceovers, and sound effects via MuApi.ai — Suno create/remix/extend, MMAudio text-to-audio and video-to-audio.

## Overview

Generate, remix, and extend music; create speech and sound effects from text; or generate audio that matches a video. All exposed through the same MuApi JSON API with the standard submit-and-poll flow.

- Music: Suno create / remix / extend
- Sound effects & ambience: MMAudio text-to-audio, MMAudio video-to-audio
- Pair with lipsync for end-to-end dubbed video pipelines

## API Pattern

Every model in this category uses the same submit-then-poll API:

```http
POST https://api.muapi.ai/api/v1/{model}
x-api-key: YOUR_API_KEY
Content-Type: application/json
```

Response: `{ "request_id": "abc123", "status": "processing" }`. Poll `GET https://api.muapi.ai/api/v1/predictions/{request_id}/result` until `status` is `completed` — the result URLs are in the `outputs[]` array. Optionally pass `?webhook=https://your-server` on the submit call to receive a callback instead of polling.

Get an API key at https://muapi.ai/access-keys.

## Quick Start

```bash
# 1. Submit
REQUEST_ID=$(curl -s -X POST https://api.muapi.ai/api/v1/suno-create-music \
  -H "x-api-key: $MUAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"an upbeat lofi hip-hop track with mellow piano"}' | jq -r .request_id)

# 2. Poll
while :; do
  RESP=$(curl -s https://api.muapi.ai/api/v1/predictions/$REQUEST_ID/result -H "x-api-key: $MUAPI_API_KEY")
  STATUS=$(echo "$RESP" | jq -r .status)
  [ "$STATUS" = "completed" ] && echo "$RESP" | jq .outputs && break
  [ "$STATUS" = "failed" ] && echo "$RESP" && exit 1
  sleep 3
done
```

## Models in This Category

- [suno-create-music](https://muapi.ai/playground/suno-create-music): Suno generate music that turns text prompts into full songs — complete with vocals, lyrics, and instrumentation. You can describe a mood, genre, or even a spec…
  - Endpoint: `POST https://api.muapi.ai/api/v1/suno-create-music`
  - Per-model llms.txt: https://muapi.ai/playground/suno-create-music/llms.txt
  - Cost: 0.090 credits per call
- [suno-remix-music](https://muapi.ai/playground/suno-remix-music): This API covers an audio track by transforming it into a new style while retaining its core melody. It incorporates Suno's upload capability, enabling users to…
  - Endpoint: `POST https://api.muapi.ai/api/v1/suno-remix-music`
  - Per-model llms.txt: https://muapi.ai/playground/suno-remix-music/llms.txt
  - Cost: 0.090 credits per call
- [minimax-speech-2.6-hd](https://muapi.ai/playground/minimax-speech-2.6-hd): Speech-2.6-hd is Minimax’s high-definition text-to-speech model that turns written text into natural, human-like audio. It produces studio-quality speech with…
  - Endpoint: `POST https://api.muapi.ai/api/v1/minimax-speech-2.6-hd`
  - Per-model llms.txt: https://muapi.ai/playground/minimax-speech-2.6-hd/llms.txt
  - Cost: 0.650 credits per call
- [mmaudio-v2-text-to-audio](https://muapi.ai/playground/mmaudio-v2-text-to-audio): Convert text into natural-sounding speech using mmAudio-v2. Ideal for voiceovers, virtual assistants, and content narration with lifelike clarity and tone.
  - Endpoint: `POST https://api.muapi.ai/api/v1/mmaudio-v2-text-to-audio`
  - Per-model llms.txt: https://muapi.ai/playground/mmaudio-v2-text-to-audio/llms.txt
  - Cost: 0.010 credits per call
- [minimax-voice-clone](https://muapi.ai/playground/minimax-voice-clone): Minimax Voice Clone creates a high-fidelity digital clone of a speaker’s voice from a short reference audio sample. It reproduces the speaker’s tone, emotion,…
  - Endpoint: `POST https://api.muapi.ai/api/v1/minimax-voice-clone`
  - Per-model llms.txt: https://muapi.ai/playground/minimax-voice-clone/llms.txt
  - Cost: 0.650 credits per call
- [minimax-speech-2.6-turbo](https://muapi.ai/playground/minimax-speech-2.6-turbo): Speech-2.6-turbo is Minimax’s fast, lightweight text-to-speech model designed for quick audio generation while maintaining good natural voice quality. It produ…
  - Endpoint: `POST https://api.muapi.ai/api/v1/minimax-speech-2.6-turbo`
  - Per-model llms.txt: https://muapi.ai/playground/minimax-speech-2.6-turbo/llms.txt
  - Cost: 0.650 credits per call
- [suno-add-vocals](https://muapi.ai/playground/suno-add-vocals): Add vocals to an instrumental track.
  - Endpoint: `POST https://api.muapi.ai/api/v1/suno-add-vocals`
  - Per-model llms.txt: https://muapi.ai/playground/suno-add-vocals/llms.txt
  - Cost: 0.090 credits per call
- [suno-generate-sounds](https://muapi.ai/playground/suno-generate-sounds): Generate sound effects using Suno chirp-crow model.
  - Endpoint: `POST https://api.muapi.ai/api/v1/suno-generate-sounds`
  - Per-model llms.txt: https://muapi.ai/playground/suno-generate-sounds/llms.txt
  - Cost: 0.020 credits per call
- [suno-extend-music](https://muapi.ai/playground/suno-extend-music): This API extends audio tracks while preserving the original style of the audio track. It includes Suno's upload functionality, allowing users to upload audio f…
  - Endpoint: `POST https://api.muapi.ai/api/v1/suno-extend-music`
  - Per-model llms.txt: https://muapi.ai/playground/suno-extend-music/llms.txt
  - Cost: 0.090 credits per call
- [suno-add-instrumental](https://muapi.ai/playground/suno-add-instrumental): Add instrumental backing to acapella audio.
  - Endpoint: `POST https://api.muapi.ai/api/v1/suno-add-instrumental`
  - Per-model llms.txt: https://muapi.ai/playground/suno-add-instrumental/llms.txt
  - Cost: 0.090 credits per call
- [suno-generate-mashup](https://muapi.ai/playground/suno-generate-mashup): Create a mashup using 1-5 audio tracks.
  - Endpoint: `POST https://api.muapi.ai/api/v1/suno-generate-mashup`
  - Per-model llms.txt: https://muapi.ai/playground/suno-generate-mashup/llms.txt
  - Cost: 0.090 credits per call

## FAQ

**Can I extend an existing track?**

Yes — `suno-extend` accepts an audio URL and a continuation prompt and returns a longer clip preserving the original style.

**How do I generate audio that matches a video?**

Use `mmaudio-v2v` (video-to-audio) — it analyzes the video and generates a matching ambient track or sound effect.

## Agent Integration

MuApi ships an MCP server so agents (Claude Code, Cursor, custom) can call every model in this category as a tool:

```bash
npm install -g muapi-cli
muapi auth login
muapi mcp serve  # exposes all MuApi models as MCP tools
```

## Resources

- Category page: https://muapi.ai/playground/group/audio
- Global llms.txt: https://muapi.ai/llms.txt
- API docs: https://muapi.ai/docs
- OpenAPI spec: https://api.muapi.ai/openapi.json