Skip to main content
POST
This endpoint extends a public audio URL directly, so you do not need to call uploadTask first. It always uses custom mode; do not send custom, instrumental, or gpt_description.

Authorizations

string
required
Bearer Token. Obtain API Key from the API Key Management page.

Body

string
default:"suno"
Always use suno.
string
required
A publicly accessible direct HTTP(S) audio URL. Keep the source audio under 8 minutes. Local paths and blob: URLs are not supported.
number
required
Extension start time. Must be at least 1 second and strictly less than the source audio’s actual duration.
string
default:"v6"
Public version: v6 / v6-wild / v6-mini. Defaults to v6; omit this field when using custom_model_id.
string
The full UUID returned by the model-creation task. Mutually exclusive with version and persona_id.
string
Lyrics for the extension, up to 5,000 characters. If omitted, the extension is treated as instrumental.
string
Style description, up to 1,000 characters.
string
Title, up to 80 characters.
string
Styles to exclude.
number
Style weight, from 0 to 1.
number
Creativity weight, from 0 to 1.
number
Audio weight, range 0–1.
boolean
Whether to create a second version of the input lyrics.
string
Gender of voice: Male or Female.
string
Persona ID, mutually exclusive with custom_model_id.
integer
Target generation duration, from 10 to 360 seconds. The actual duration is determined by the task result.
string
Style variation: off / normal / high / extra / max.
boolean
default:"false"
Enables Max mode and is billed at twice the standard price.
string
Output format: mp3 / m4a / wav.
.

Response

integer
Response Status Codes.
array
Submission result. Read from data[0].task_id and poll the task query interface.