Skip to main content
POST

​
Model Versions

  • Current models: V6 (default), V6_WILD, V6_MINI
  • Deprecated models: V5_5, V5, V4_5PLUS, V4_5ALL, V4_5, V4
  • Deprecated values remain available only for backward compatibility. New integrations should use a V6-series model.

​
Parameter Usage Guide

  • This endpoint always runs in custom mode. A source audio (audioId) is enough to generate; lyrics (or prompt), title, and style are optional.
  • Required: audioId, model, callBackUrl
  • model (string, required): V6, V6_WILD, V6_MINI. Deprecated: V4_5ALL, V4, V4_5, V4_5PLUS, V5, V5_5.
  • prompt is lyrics. Optional. If lyrics is also provided, lyrics takes priority and prompt is not used as lyrics.
  • Character limits by model:
    • V4 (Deprecated): prompt max 3000, style max 200
    • V4_5ALL (Deprecated): prompt max 5000, style max 1000
    • V4_5, V4_5PLUS, V5, V5_5 (Deprecated): prompt max 5000, style max 1000
    • V6, V6_WILD & V6_MINI: lyrics/prompt max 5000, style max 1000, title max 100
  • taskId is optional and can be provided to identify the original generation task
  • If instrumental is true: do not provide prompt or vocalGender

​
Optional parameters

The following fields are optional controls available for this endpoint:
  • lyrics (string): Lyrics content. Optional. V6 series maximum 5000 characters. Takes priority over prompt as lyrics.
  • prompt (string): Lyrics content. Optional. Used as lyrics when lyrics is not provided. V6 series maximum 5000 characters.
  • style (string): Music style. Optional. V6 series maximum 1000 characters.
  • title (string): Track title. Optional. Maximum 100 characters.
  • continueAt (number): Time point in seconds from which to start extending. Greater than 0 and less than the source audio duration.
  • taskId (string): Unique identifier of the original music generation task that produced the source audio. Can be a taskId returned from Generate Music or a previous Extend Music request.
  • instrumental (boolean): Whether to extend the track as instrumental music. Defaults to false. When true, prompt and vocalGender must not be provided.
  • vocalGender (string): Preferred vocal gender. Allowed values: m (male), f (female). Must not be provided when instrumental is true.
  • styleWeight (number): Style adherence weight in range 0–1 (recommended two decimals)
  • weirdnessConstraint (number): Creativity/novelty constraint in range 0–1 (recommended two decimals)
  • audioWeight (number): Relative weight of audio consistency in range 0–1 (recommended two decimals)
  • variety (number): Diversity of generated results. Integer from 0–4, default 1. 0 off, 1 normal (default), 2 high, 3 extra, 4 max.
  • personaId (string): Persona ID or Suno Voice voiceId. If you use a Voice-generated ID, set personaModel to voice_persona.
  • personaModel (string): Persona type. Use style_persona for Generate Persona IDs, or voice_persona for Suno Voice IDs. Default style_persona.

​
Developer Notes

  1. Generated files are retained for 15 days
  2. Model version must be consistent with the source music
  3. This feature is ideal for creating longer compositions by extending existing tracks

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:

⚠️ 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
​
audioId
string
required

Audio ID of the track to extend. Required. With a source audio ID, generation can proceed; lyrics (or prompt), title, and style are optional.

Example:

"e231****-****-****-****-****8cadc7dc"

​
model
enum<string>
default:V6
required

AI model version. Default: V6.

  • V6: Current standard model and recommended default.
  • V6_WILD: Current model for more experimental and creative results.
  • V6_MINI: Current lightweight model.
  • Deprecated: V5_5, V5, V4_5PLUS, V4_5ALL, V4_5, and V4. These values remain listed only for backward compatibility; use a V6-series model for new integrations.
Available options:
V6,
V6_WILD,
V6_MINI,
V5_5,
V5,
V4_5PLUS,
V4_5ALL,
V4_5,
V4
Example:

"V6"

​
callBackUrl
string<uri>
required

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

  • For detailed callback format and implementation guide, see Music Extension Callbacks
  • Alternatively, you can use the Get Music Generation Details interface to poll task status
Example:

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

​
instrumental
boolean
default:false

Whether the extended music should be instrumental (without vocals). Optional. If true, neither prompt nor vocalGender may be provided.

Example:

false

​
taskId
string

Unique identifier of the original music generation task that produced the source audio. Optional. Can be a taskId returned from Generate Music (/api/v1/generate) or a previous Extend Music (/api/v1/generate/extend) request.

Example:

"5c79****be8e"

​
prompt
string

Lyrics content. Optional. Used as lyrics when lyrics is not provided. If lyrics is also provided, lyrics takes priority and this field is not used as lyrics.

  • V4 (Deprecated): Maximum 3000 characters
  • V4_5, V4_5PLUS, V4_5ALL, V5, V5_5 (Deprecated): Maximum 5000 characters
  • V6, V6_WILD, V6_MINI: Maximum 5000 characters
Example:

"[Verse] Night city lights shining bright"

​
lyrics
string

Lyrics for the generated audio. Optional. For V6, V6_MINI, and V6_WILD: maximum 5000 characters. Takes priority over prompt as lyrics. If omitted, prompt is used as lyrics.

Example:

"[Verse] Night city lights shining bright"

​
style
string

Music style, e.g. Jazz, Classical, or Electronic. Optional. For V6, V6_WILD, and V6_MINI: maximum 1000 characters.

  • V4 (Deprecated): Maximum 200 characters
  • V4_5, V4_5PLUS, V4_5ALL, V5, V5_5 (Deprecated): Maximum 1000 characters
Example:

"Classical"

​
title
string

Music title. Optional. Maximum 100 characters.

Maximum string length: 100
Example:

"Peaceful Piano Extended"

​
continueAt
number

The time point (in seconds) from which to start extending the music. Optional.

  • Value range: greater than 0 and less than the total duration of the source audio.
  • Specifies the position in the original track where the extension should begin.
Example:

60

​
personaId
string

Persona ID to apply to the generated music. Optional. You can use either:

  • A Persona ID generated by the Generate Persona endpoint. Use personaModel: style_persona or omit personaModel to use the default.
  • A voiceId generated by the Suno Voice workflow. When using a voice-generated ID, you must set personaModel: voice_persona.
Example:

"persona_123"

​
personaModel
enum<string>
default:style_persona

Persona model type to apply when using personaId. Optional.

  • style_persona (default): Use this for Persona IDs generated by the Generate Persona endpoint.
  • voice_persona: Required when personaId is a voiceId generated by Suno Voice. This option is only available with V5 (Deprecated), V5_5 (Deprecated), V6, V6_WILD, and V6_MINI models.
Available options:
style_persona,
voice_persona
Example:

"style_persona"

​
negativeTags
string

Music styles to exclude from generation

Example:

"Relaxing Piano"

​
vocalGender
enum<string>

Preferred vocal gender. Optional. Allowed values: m (male), f (female). Must not be provided when instrumental is true.

Available options:
m,
f
Example:

"m"

​
styleWeight
number

Style adherence weight. Optional. Range: 0-1. Two decimal places recommended.

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

0.65

​
weirdnessConstraint
number

Creativity/novelty constraint. Optional. Range: 0-1. Two decimal places recommended.

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

0.65

​
audioWeight
number

Relative weight of audio consistency versus other controls. Optional. Range: 0-1. Two decimal places recommended.

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

0.65

​
variety
number
default:1

Controls the diversity and stylistic variation of generated results. Optional. Integer from 0–4, default 1.

  • 0: off (exact style) — fully off, strictly the same style
  • 1: normal (balanced variety) — default, balances stability and diversity
  • 2: high (distinct styles) — produces results with clearly different styles
  • 3: extra (bold exploration) — higher variation, encourages bold exploration of different styles
  • 4: max (unreasonably varied) — maximum diversity; results may differ in style very significantly
Required range: 0 <= x <= 4Must be a multiple of 1
Example:

1

Callbacks

POST
{$request.body#/callBackUrl}audioExtend

Body

application/json
​
code
integer

Status code

Example:

200

​
msg
string

Response message

Example:

"All generated successfully"

​
data
object

Response

200

Callback received successfully

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