Description

n8n-nodes-musicgpt

Official n8n community node for MusicGPT – AI-powered audio processing, music generation, and voice transformation.

Features

• 🎵 Audio Generation: Create music from text prompts or lyrics
• 🎙️ Text-to-Speech: Convert text to natural-sounding speech in 10+ languages
• 🎤 Voice Transformation: Change voices in audio files with 100+ voice options
• 🎸 Stem Separation: Extract vocals, instruments, and 20+ individual stems
• 🎛️ Audio Processing: Denoise, deecho, dereverb, master, trim, speed, convert
• 🎹 Advanced Generation: Remix, extend, inpaint, add vocals, generate sound effects
• 🔍 Voice Search: Find and list available voices dynamically
• ⚡ Triggers: Monitor conversions and automate workflows
• 🌐 Webhook Support: Async processing with callbacks
• 📦 Binary File Handling: Process files from previous nodes seamlessly

Quick Start

Installation

Via n8n Community Nodes (Recommended)

1. Open your n8n instance
2. Go to Settings → Community Nodes
3. Click Install
4. Enter: n8n-nodes-musicgpt
5. Click Install

Via npm (Self-Hosted)

cd ~/.n8n/nodes
npm install n8n-nodes-musicgpt

Setup Credentials

1. Get your API key from musicgpt.com
2. In n8n, go to Credentials → New
3. Search for "MusicGPT API"
4. Enter your API key

Your First Workflow

Manual Trigger →
MusicGPT (Generate Audio):
  - Prompt: "Upbeat electronic dance music"
→ Wait (45 seconds) →
MusicGPT (Get Conversion by ID) →
Process result

Operations Overview

📦 What's Included

• 1 Action Node: MusicGPT (25 operations across 4 resources)
• 1 Trigger Node: MusicGPT Trigger (2 trigger types)

Audio Generation (6 operations)

Audio Processing (9 operations)

Advanced Generation (6 operations)

Searches (4 operations)

Triggers (2 types)

Documentation

Usage Examples

Example 1: Text-to-Speech Podcast Generator

Schedule Trigger (weekly) →
Fetch Script (HTTP Request) →
Text to Speech:
  - Text: {{ $json.script }}
  - Language: English
  - Voice: Professional narrator
→ Wait (20s) →
Get Conversion →
Upload to Podcast Host →
Notify Team (Slack)

Example 2: AI Cover Song API

Webhook (receive song URL + artist) →
Search Voices (find artist voice) →
Cover Song (generate with voice) →
Respond (task_id)

(Separate Webhook)
Completion Callback →
Upload to Storage →
Notify User

Example 3: Audio Processing Pipeline

File Upload Trigger →
Parallel Processing:
  ├─ Denoise
  ├─ Extract Key/BPM
  └─ Transcribe
→ Merge Results →
Audio Mastering →
Save to Database

Example 4: Music Production Workflow

Manual Trigger →
Generate Audio (from lyrics) →
Wait (45s) →
Get Conversion →
Extraction (separate stems) →
Wait (60s) →
Remix (transform style) →
Download & Archive

Example 5: Automated Content Creation

MusicGPT Trigger (New Conversions) →
Filter (music_generation, completed) →
Auto-Master Audio →
Convert to Multiple Formats →
Upload to CDN →
Update Database →
Email Notification

Supported Formats & Features

Audio Formats

• Input: MP3, WAV, FLAC, OGG, AAC, WEBM, M4A
• Output: MP3, WAV, FLAC, OGG, AAC, WEBM

Languages (TTS & Transcription)

English, Spanish, French, German, Italian, Portuguese, Chinese, Japanese, Korean, Auto-detect

Available Stems (Extraction)

• Vocals: vocals, male_vocal, female_vocal, lead_vocal, back_vocal
• Rhythm: drums, kick, snare, toms, hi-hat, ride, crash
• Strings: guitar, bass, rhythm_guitar, solo_guitar, acoustic_guitar, electric_guitar
• Keys: piano, keys, strings, winds
• Full: instrumental (all instruments)

Sample Rates

8kHz, 16kHz, 22.05kHz, 24kHz, 32kHz, 44.1kHz (CD), 48kHz (Pro), 96kHz (Hi-Res), 192kHz (Ultra)

Advanced Features

Webhook Callbacks

Enable async processing for long operations:

{
  "webhook_url": "https://your-webhook.com/callback"
}

Receive completion notifications:

{
  "event": "conversion.completed",
  "task_id": "task_abc123",
  "status": "completed",
  "output_url": "https://cdn.musicgpt.com/result.mp3"
}

Binary File Processing

Process files from previous nodes:

HTTP Request (download) →
  └─ Response: File
MusicGPT:
  └─ Audio Source: File
  └─ Binary Property: "data"

Dynamic Voice Loading

Voice selection fields dynamically load 100+ available voices from the API, with search and filter capabilities.

Troubleshooting

Contributing

Contributions are welcome! See the GitHub repository for development setup and guidelines.

Support

• 📖 Documentation: DOCUMENTATION.md
• ⚡ Quick Reference: API-REFERENCE.md
• 💬 Community: n8n Forum
• 📧 Email: support@musicgpt.com

Resources

• MusicGPT API Docs: docs.musicgpt.com
• n8n Documentation: docs.n8n.io
• Creating n8n Nodes: docs.n8n.io/integrations/creating-nodes
• n8n Community: community.n8n.io

License

MIT License – see LICENSE file for details.

Credits

• MusicGPT API: musicgpt.com
• n8n Platform: n8n.io

Made with ❤️ for the n8n community