Skip to main content

Introduction to Producer Music Generation

Welcome to the Producer Music Generation service documentation! Producer is an AI music generation service powered by Lyria 3 Pro (Google DeepMind), enabling high-quality music creation from text prompts, lyrics, and even images.

Supported Models

ModelDescription
Lyria 3 ProGoogle DeepMind’s latest music generation model — high quality, recommended

Features

Create Music

Generate original tracks from sound prompts and lyrics with fine-grained control over style

Image-Guided

Use an image to influence the mood and style of generated music

Stem Separation

Split generated tracks into individual stems (vocals, drums, bass, etc.)

Multi-Format Export

Export as MP3, M4A, WAV audio or generate video with visual presets

How to Use Producer

1

Create a music generation task

Call POST /producer/audios with your sound prompt, lyrics, and model. You’ll receive a taskId.
2

Poll for results

Use GET /producer/tasks?taskId=xxx to poll until status is completed. The result contains the generated audio data.
3

Download or process

Use /producer/download to get audio in MP3/M4A/WAV, /producer/download-video for video with visualizers, or /producer/stems for stem separation.

Quick Example

curl -X POST "https://api.mountsea.ai/producer/audios" \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "action": "create_music",
    "model": "Lyria 3 Pro",
    "soundPrompt": "emotional pop with gentle piano, warm synths, and a catchy beat",
    "lyrics": "[Verse]\nSunshine on my face today\nEverything is going my way\n\n[Chorus]\nSummer vibes, feeling alive",
    "title": "Summer Vibes",
    "makeInstrumental": false
  }'

Available Endpoints

EndpointMethodDescription
/producer/audiosPOSTCreate music with Lyria 3 Pro
/producer/tasksGETQuery task status and results
/producer/uploadPOSTUpload external audio file
/producer/stemsPOSTGet stem separation
/producer/downloadPOSTDownload audio (MP3/M4A/WAV)
/producer/download-videoPOSTGenerate and download video

Explore the API Documentation

Key Parameters

ParameterTypeDescription
actionstringcreate_music (required)
modelstringLyria 3 Pro (required)
soundPromptstringStyle/mood description for the music
lyricsstringLyrics with section tags like [Verse], [Chorus]
titlestringSong title (max 80 characters)
seednumberRandom seed for reproducible generation
makeInstrumentalbooleanGenerate without vocals (default: false)
imageUrlstringImage URL for image-guided generation
Either soundPrompt or lyrics should be provided for music generation. Set makeInstrumental: true to ignore lyrics and generate an instrumental track.