Welcome to Suno API
The Suno API enables you to create high-quality AI-generated music, lyrics, and audio content using state-of-the-art AI models. Whether you’re building a music app, automating creative workflows, or developing audio content, our API provides comprehensive tools for music generation and audio processing.Generate Music
Create original music tracks with or without lyrics
Extend Music
Extend existing music tracks seamlessly
Generate Lyrics
Create creative lyrics from text prompts
Music Videos
Convert audio tracks into visual music videos
Upload & Cover
Transform uploaded audio into new styles
Upload & Extend
Upload audio files and extend them seamlessly
Add Instrumental
Generate instrumental accompaniment for uploaded audio
Add Vocals
Add vocal singing to uploaded audio files
Separate Vocals
Separate vocals and instrumentals from music
Convert to WAV
Convert audio to high-quality WAV format
Get Lyrics
Retrieve timestamped synchronized lyrics
Authentication
All API requests require authentication using a Bearer token. Get your API key from the API Key Management Page.Keep your API key secure and never share it publicly. If compromised, reset it immediately.
API Base URL
Authentication Header
Quick Start Guide
Step 1: Generate Your First Music Track
Start with a simple music generation request:Step 2: Check Task Status
Use the returned task ID to check the generation status:Response Format
Successful Response:Core Features
- Text-to-Music: Generate music from text descriptions with AI
- Music Extension: Seamlessly extend existing audio tracks
- Lyrics Generation: Create structured lyrical content from creative prompts
- Audio Upload & Cover: Upload audio files and transform them into different musical styles
- Add Instrumental: Generate instrumental accompaniment for uploaded audio files
- Add Vocals: Add vocal singing to uploaded audio files with custom styles
- Vocal Separation: Isolate vocals, instrumentals, and other audio components
- Format Conversion: Support for WAV and other high-quality audio formats
- Music Videos: Create visual content synchronized with your audio tracks
- Audio Processing: Comprehensive tools for audio enhancement and manipulation
AI Models
Choose the right model for your needs:V3_5
Better song structureMax 4 minutes, improved song organization
V4
Improved vocalsMax 4 minutes, enhanced vocal quality
V4_5
Smart promptsMax 8 minutes, faster generation
V4_5PLUS
Richer soundMax 8 minutes, new creative ways
Generation Modes
Controls parameter complexity:
false
: Simple mode, only prompt requiredtrue
: Advanced mode, requires style and title
Determines if music includes vocals:
true
: Instrumental only (no lyrics)false
: Include vocals/lyrics
Key Parameters
Text description of the desired music. Be specific about genre, mood, and instruments.Character Limits:
- Non-custom mode: 400 characters
- Custom mode (V3_5 & V4): 3000 characters
- Custom mode (V4_5 & V4_5PLUS): 5000 characters
Music style specification (Custom Mode only).Examples: Jazz, Classical, Electronic, Pop, Rock, Hip-hopCharacter Limits:
- V3_5 & V4: 200 characters
- V4_5 & V4_5PLUS: 1000 characters
Title for the generated music track (Custom Mode only).Max length: 80 characters
Complete Workflow Example
Here’s a complete example that generates music with lyrics and waits for completion:Advanced Features
Boost Music Style (V4_5 Models)
Enhance your style descriptions for better results:Audio Processing Features
Convert, separate, and enhance your generated music:Async Processing with Callbacks
Set up webhook callbacks for automatic notifications:Learn More About Callbacks
Complete guide to implementing and handling Suno API callbacks
Status Codes & Task States
Task is waiting to be processed or currently generating
Lyrics/text generation completed successfully
First track generation completed
All tracks generated successfully
Failed to create task
Failed to generate audio
Content filtered due to sensitive words
Best Practices
Prompt Engineering
Prompt Engineering
- Be specific about genre, mood, and instruments
- Use descriptive adjectives for better style control
- Include tempo and energy level descriptions
- Reference musical eras or specific artists for style guidance
Model Selection
Model Selection
- V3_5: Best for structured songs with clear verse/chorus patterns
- V4: Choose when vocal quality is most important
- V4_5: Use for faster generation and smart prompt handling
- V4_5PLUS: Select for the highest quality and longest tracks
Performance Optimization
Performance Optimization
- Use callbacks instead of frequent polling
- Start with non-custom mode for simpler requirements
- Implement proper error handling for failed generations
- Cache generated content since files expire after 14 days
Content Guidelines
Content Guidelines
- Avoid copyrighted material in prompts
- Use original lyrics and musical descriptions
- Be mindful of content policies for lyrical content
- Test prompt variations to avoid sensitive word filters
Error Handling
Content Policy Violations (Code 400)
Content Policy Violations (Code 400)
Insufficient Credits (Code 402)
Insufficient Credits (Code 402)
Rate Limiting (Code 429)
Rate Limiting (Code 429)
Support
Need help? Our technical support team is here to assist you.
- Email: support@kie.ai
- Documentation: docs.kie.ai
- API Status: Check our status page for real-time API health
Ready to start creating amazing AI music? Get your API key and begin composing today!