Suno API

Authentication

All endpoints require a Bearer token in the Authorization header:

Authorization: Bearer your-api-key-here

Pricing

Suno Music - $0.06 Suno Add Vocals - $0.06 Suno Add Instrumental - $0.06 Suno Extend - $0.06 Suno Cover -$0.06 Suno Stems - $0.05 Suno Stems All - $0.20 Suno Lyrics - $0.012

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, 4.5 Plus & v5 - Prompt 5,000 characters, Style 1,000 characters

In simple mode prompt regardless of the model can not be more than 500 characters

Available Endpoints

1. Music Generation

Generate music using simple or custom mode in a unified endpoint.

Endpoint: POST /suno/music

Simple Mode Example:

Custom Mode Example:

Response:

2. Extend Music

Extend an existing song or upload audio to extend it.

Endpoint: POST /suno/extend

Extend Existing Clip Example (Simple):

Upload and Extend Example (Custom):

Response: Same format as Music Generation

3. Cover Generation

Generate a cover version of an existing song or uploaded audio.

Endpoint: POST /suno/cover

Request Body:

Cover Existing Clip Example (Simple)

Upload and Cover Example (Custom)

Response: Same format as Music Generation

4. Add Vocals

Add vocals to uploaded music (only works with uploaded audio, not Suno-generated).

Endpoint: POST /suno/add-vocals

Request Body:

Example Request:

Response: Same format as Music Generation

5. Add Instrumental

Add instrumental backing to uploaded music (only works with uploaded audio, not Suno-generated).

Endpoint: POST /suno/add-instrumental

Request Body, Custom mode:

Simple mode:

Response: Same format as Music Generation

6. Extract Stems (Vocals and Instrumental)

Extract vocals and instrumental tracks from a song.

Endpoint: POST /suno/stems

Request Body:

Example Request:

Response:

7. Extract All Stems

Extract all available stems from a song (vocals, instrumental, drums, bass, etc.).

Endpoint: POST /suno/stems-all

Request Body:

Example Request:

Response: Same format as Extract Stems

8. Generate Lyrics

Generate lyrics based on a description. Returns IDs that can be used to fetch the completed lyrics.

Endpoint: POST /suno/lyrics

Request Body:

Example Request:

Response:

9. Fetch Lyrics

Fetch the completed lyrics using the lyrics ID from the generate endpoint.

Endpoint: GET /suno/lyrics/:lyricsId

Example Request:

Response:

10. Convert to WAV

Convert a song to WAV format and get download URL.

Endpoint: POST /suno/wav

Request Body:

Example Request:

Response:

10. Get Feed Info

Get detailed information about generation tasks (includes audio/video URLs when ready).

Endpoint: GET /suno/feed/:taskIds

Example Request:

Response:

11. Get Timestamped Lyrics

Get timestamped/aligned lyrics for a song.

Endpoint: GET /suno/aligned_lyrics/:taskId

Example Request:

Response:

12. Get Downbeats

Get timing information for song downbeats.

Endpoint: GET /suno/downbeats/:taskId

Example Request:

Response:

Advanced Settings

For custom mode endpoints, advanced settings provide fine-grained control:

  • style_weight (0.0-1.0): Controls how closely the generation follows the style description

  • weirdness_constraint (0.0-1.0): Controls experimental/creative freedom (0 = conservative, 1 = experimental)

  • audio_weight (0.0-1.0): Prioritizes audio quality vs style matching

  • vocal_gender ("m" or "f"): Specifies preferred vocal gender

Last updated