Skip to main content
POST
/
api
/
v1
/
generate
Generate Music
curl --request POST \
  --url https://api.sunoapi.org/api/v1/generate \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "customMode": true,
  "instrumental": true,
  "model": "V4_5ALL",
  "callBackUrl": "https://api.example.com/callback",
  "prompt": "A calm and relaxing piano track with soft melodies",
  "style": "Classical",
  "title": "Peaceful Piano Meditation",
  "personaId": "persona_123",
  "negativeTags": "Heavy Metal, Upbeat Drums",
  "vocalGender": "m",
  "styleWeight": 0.65,
  "weirdnessConstraint": 0.65,
  "audioWeight": 0.65
}
'
{
  "code": 200,
  "msg": "success",
  "data": {
    "taskId": "5c79****be8e"
  }
}
This is the key endpoint in the Suno API. Each request returns exactly 2 songs.
  • Stream URL: Available in 30-40 seconds.
  • Downloadable song URL: Ready in 2-3 minutes.
Concurrency limit: 20 requests every 10 seconds. Exceeding this will result in request rejection. Please review the parameters carefully to ensure proper use.

​
Parameter Usage Guide

  • When customMode is true (Custom Mode):
    • If instrumental is true: style and title are required
    • If instrumental is false: style, prompt, and title are required
    • Prompt length limit:
      • For V4 model: 3000 characters
      • For V4_5, V4_5PLUS, V4_5ALL and V5 models: 5000 characters
    • Style length limit:
      • For V4 model: 200 characters
      • For V4_5, V4_5PLUS, V4_5ALL and V5 models: 1000 characters
    • Title length limit:
      • For V4 and V4_5ALL model: 80 characters
      • For V4_5, V4_5PLUS and V5 models: 100 characters
  • When customMode is false (Non-custom Mode):
    • Only prompt is required regardless of instrumental setting
    • prompt length limit: 500 characters
    • Other parameters should be left empty

​
Developer Notes

  1. Recommendation for First-Time Users: Start with customMode: false and instrumental: false, and only provide a prompt. This is the simplest setup to quickly test the API and experience the results.
  2. Generated files are retained for 15 days before being deleted
  3. Ensure all required fields are provided based on the customMode and instrumental settings to avoid errors
  4. Respect the character limits for prompt, style, and title to ensure successful processing
  5. Callback process has three stages: text (text generation), first (first track complete), complete (all tracks complete)
  6. You can use the Get Music Generation Details endpoint to actively check task status instead of waiting for callbacks

Authorizations

​
Authorization
string
header
required

🔑 API Authentication

All endpoints require authentication using Bearer Token.

Get API Key

  1. Visit the API Key Management Page to obtain your API Key

Usage

Add to request headers:

Authorization: Bearer YOUR_API_KEY

⚠️ Note:

  • Keep your API Key secure and do not share it with others
  • If you suspect your API Key has been compromised, reset it immediately from the management page

Body

application/json
​
customMode
boolean
required

Enables Custom Mode for advanced audio generation settings.

  • Set to true to use Custom Mode (requires style and title; prompt required if instrumental is false). The prompt will be strictly used as lyrics if instrumental is false.
  • Set to false for Non-custom Mode (only prompt is required). Lyrics will be auto-generated based on the prompt.
Example:

true

​
instrumental
boolean
required

Determines if the audio should be instrumental (no lyrics).

  • In Custom Mode (customMode: true):
    • If true: Only style and title are required.
    • If false: style, title, and prompt are required (with prompt used as the exact lyrics).
  • In Non-custom Mode (customMode: false): No impact on required fields (prompt only). Lyrics are auto-generated if instrumental is false.
Example:

true

​
model
enum<string>
required

The model version to use for audio generation.

  • Available options:
    • V5: Superior musical expression, faster generation.
    • V4_5PLUS: V4.5+ is richer sound, new ways to create, max 8 min.
    • V4_5ALL: V4.5-all is better song structure, max 8 min.
    • V4_5: Superior genre blending with smarter prompts and faster output, up to 8 minutes.
    • V4: Best audio quality with refined song structure, up to 4 minutes.
Available options:
V4,
V4_5,
V4_5PLUS,
V4_5ALL,
V5
Example:

"V4_5ALL"

​
callBackUrl
string<uri>
required

The URL to receive task completion notifications when music generation is complete.

For detailed callback format and implementation guide, see Music Generation Callbacks

  • Alternatively, you can use the get music generation details endpoint to poll task status
Example:

"https://api.example.com/callback"

​
prompt
string

A description of the desired audio content.

  • In Custom Mode (customMode: true): Required if instrumental is false. The prompt will be strictly used as the lyrics and sung in the generated track. Character limits by model:
    • V4: Maximum 3000 characters
    • V4_5, V4_5PLUS, V4_5ALL & V5: Maximum 5000 characters
      Example: "A calm and relaxing piano track with soft melodies"
  • In Non-custom Mode (customMode: false): Always required. The prompt serves as the core idea, and lyrics will be automatically generated based on it (not strictly matching the input). Maximum 500 characters.
    Example: "A short relaxing piano tune"
Example:

"A calm and relaxing piano track with soft melodies"

​
style
string

The music style or genre for the audio.

  • Required in Custom Mode (customMode: true). Examples: "Jazz", "Classical", "Electronic".
    • For V4 model: Max length: 200 characters.
    • For V4_5, V4_5PLUS, V4_5ALL and V5 models: Max length: 1000 characters.
      Example: "Classical"
  • In Non-custom Mode (customMode: false): Leave empty.
Example:

"Classical"

​
title
string

The title of the generated music track.

  • Required in Custom Mode (customMode: true). Character limits by model:
    • V4 & V4_5ALL: Maximum 80 characters
    • V4_5, V4_5PLUS & V5: Maximum 100 characters
      Example: "Peaceful Piano Meditation"
  • In Non-custom Mode (customMode: false): Leave empty.
Example:

"Peaceful Piano Meditation"

​
personaId
string

Only available when Custom Mode (customMode: true) is enabled. Persona ID to apply to the generated music. Optional. Use this to apply a specific persona style to your music generation.

To generate a persona ID, use the Generate Persona endpoint to create a personalized music Persona based on generated music.

Example:

"persona_123"

​
negativeTags
string

Music styles or traits to exclude from the generated audio.

  • Optional. Use to avoid specific styles.
    Example: "Heavy Metal, Upbeat Drums"
Example:

"Heavy Metal, Upbeat Drums"

​
vocalGender
enum<string>

Preferred vocal gender for generated vocals. Optional.

Available options:
m,
f
Example:

"m"

​
styleWeight
number

Weight of the provided style guidance. Range 0.00–1.00.

Required range: 0 <= x <= 1Must be a multiple of 0.01
Example:

0.65

​
weirdnessConstraint
number

Constraint on creative deviation/novelty. Range 0.00–1.00.

Required range: 0 <= x <= 1Must be a multiple of 0.01
Example:

0.65

​
audioWeight
number

Weight of the input audio influence (where applicable). Range 0.00–1.00.

Required range: 0 <= x <= 1Must be a multiple of 0.01
Example:

0.65

Response

Request successful

​
code
enum<integer>

Status Codes

  • ✅ 200 - Request successful
  • ⚠️ 400 - Invalid parameters
  • ⚠️ 401 - Unauthorized access
  • ⚠️ 404 - Invalid request method or path
  • ⚠️ 405 - Rate limit exceeded
  • ⚠️ 413 - Theme or prompt too long
  • ⚠️ 429 - Insufficient credits
  • ⚠️ 430 - Your call frequency is too high. Please try again later.
  • ⚠️ 455 - System maintenance
  • ❌ 500 - Server error
Available options:
200,
400,
401,
404,
405,
413,
429,
430,
455,
500
Example:

200

​
msg
string

Error message when code != 200

Example:

"success"

​
data
object