Suno

Where AI and Melody Unite Seamlessly! Transform text prompts into stunning AI-generated tracks, blending vocals and instruments with revolutionary realism. Newly added V5 delivers hyper-dynamic, natural performances—emotional arcs, breathing, and fluid progressions for lifelike depth. Ideal for developers crafting immersive apps: fast and scalable. Revolutionize music creation today!

Music Generation

Music Extension

Audio Cover

Audio Expansion

Accompaniment

Vocal Generation

Music Generation Configuration

Model Version *

Upload Audio File *

Click to upload audio fileSupports MP3, WAV, M4A formats, max 2 minutes

Upload audio file to expand, ensure length does not exceed 2 minutes

Use Custom Parameter Mode

Need to provide custom parameters like style, title, etc.

Expansion Time Point (seconds) *

Specify the time point from the original audio to start the expansion

Prompt

Describe how the music should expand, max 5000 characters

0/5000

Instrumental (No Lyrics)

If instrumental is selected, only style and title are needed

Music Style *

Defines genre, mood, or artistic direction

Music Title *

Will be displayed in the player interface and filename

Exclude Tags

Music styles or characteristics to exclude from generated audio

Style Weight (0.65)

Loose (0)Strict (1)

Creative Constraint (0.65)

Conservative (0)Experimental (1)

Audio Weight (0.65)

Low Weight (0)High Weight (1)

Generation Result

No music generated yet

Configure parameters and click "Generate Music" to start creating

🎵Music Generation: Create new music; Music Extension: Extend existing audio; Audio Cover: Recreate audio; Audio Expansion: Expand on uploaded audio; Accompaniment: Generate accompaniment; Vocal Generation: Generate vocals for audio

🎼Simple mode is suitable for quick generation, custom mode provides more control options

🎹Extend function requires selecting audio, cover and expand functions require uploading audio files (max 2 minutes), accompaniment and vocal generation require uploading source audio files

⚡V5 model has faster generation speed and better music expressiveness

🎯Vocal generation guides vocal content and style through prompts, supports music style and exclude tags control