Suno API provides comprehensive AI-powered audio generation capabilities including music creation, vocal synthesis, stem extraction, and more.

​
Authentication

All endpoints require a Bearer token in the Authorization header: 
Authorization: Bearer YOUR_API_KEY

​
Pricing

For detailed pricing information, see the Pricing page.

​
Available Models

​
Music Generation Models

  • chirp-v3-0 - Version 3.0
  • chirp-v3-5 - Version 3.5
  • chirp-v4 - Version 4.0
  • chirp-auk - Version 4.5
  • chirp-bluejay - Version 4.5+
  • chirp-crow - Version 5.0

​
Lyrics Generation Models

  • remi-v1 - Primary lyrics model
  • default - Default lyrics model

​
Model Limits

v3.5, v4:
  • Prompt: 3,000 characters
  • Style: 200 characters
v4.5, v4.5+ & v5:
  • Prompt: 5,000 characters
  • Style: 1,000 characters
Simple Mode:
  • Prompt: 500 characters (regardless of model)

​
Available Endpoints

Music Generation

Generate music using simple or custom mode

Extend Music

Extend existing songs or uploaded audio

Cover Generation

Generate cover versions of songs

Add Vocals

Add vocals to uploaded music

Add Instrumental

Add instrumental backing to uploaded music

Extract Stems

Extract vocals and instrumental tracks

Extract All Stems

Extract all available stems

Generate Lyrics

Generate lyrics based on description

Fetch Lyrics

Retrieve completed lyrics

Convert to WAV

Convert songs to WAV format

Get Feed Info

Get detailed task information

Timestamped Lyrics

Get timestamped/aligned lyrics

Get Downbeats

Get timing information for downbeats

​
Advanced Settings

For custom mode endpoints, advanced settings provide fine-grained control:
​
style_weight
number
0.0-1.0: Controls how closely the generation follows the style description
​
weirdness_constraint
number
0.0-1.0: Controls experimental/creative freedom (0 = conservative, 1 = experimental)
​
audio_weight
number
0.0-1.0: Prioritizes audio quality vs style matching
​
vocal_gender
string
“m” or “f”: Specifies preferred vocal gender