Upload And Cover Audio
POST
/api/v1/jobs/createTask
Document updated
This API creates a cover version of an audio track by transforming it into a new style while retaining its core melody. It incorporates Suno's upload capability, enabling users to upload an audio file for processing. The expected result is a refreshed audio track with a new style, keeping the original melody intact.
Parameter Usage Guide
Character Limits
style (max 1000 chars), title (max 80 chars), lyrics / prompt (max 5000 chars)style (max 1000 chars), title (max 100 chars), prompt (max 5000 chars)style (max 1000 chars), title (max 100 chars), prompt (max 5000 chars)style (max 1000 chars), title (max 80 chars), prompt (max 5000 chars)style (max 200 chars), title (max 80 chars), prompt (max 3000 chars)image_urls. Cover does not support simple-mode reference images.upload_url, instrumental, modelupload_url), generation can proceed; lyrics (formerly used via prompt), title, and style are optionallyrics takes priority over prompt as lyrics. If lyrics is omitted, prompt is used as lyrics when providedinstrumental is true: generate instrumental music (no vocals). Do not pass lyrics, prompt, or vocal_genderupload_url specifies the source audio file; ensure the uploaded audio does not exceed 8 minutes in lengthDeveloper Notes
1.
2.
lyrics / prompt, style, and title to ensure successful processing.3.
text (text generation complete), first (first track complete), and complete (all tracks complete).4.
5.
upload_url parameter is used to specify the source audio file; please provide a valid URL.Optional Parameters
| Parameter | Type | Description |
|---|---|---|
lyrics | string | Lyrics for the covered audio. Optional. V6 maximum 5000 characters. Takes priority over prompt as lyrics. |
prompt | string | Used as lyrics only when lyrics is not provided. Optional. V6 maximum 5000 characters. |
style | string | Music style specification. Optional. V6 maximum 1000 characters. |
title | string | Track title. Optional. Maximum 80 characters. |
negative_tags | string | Music styles or traits to exclude from the generated audio. |
vocal_gender | string | Vocal gender preference. Use m for male, f for female. |
style_weight | number | Strength of adherence to style. Range 0–1, up to 2 decimal places. Example: 0.65. |
weirdness_constraint | number | Controls creative deviation. Range 0–1, up to 2 decimal places. Example: 0.65. |
audio_weight | number | Balance weight for audio features. Range 0–1, up to 2 decimal places. Example: 0.65. |
variety | integer | Diversity of generated results. Integer from 0–4, default 1. 0 off, 1 normal, 2 high, 3 extra, 4 max. |
persona_id | string | Persona ID or Voice ID to apply to the generated music. To create one, use Generate Persona. |
duration | integer | Audio duration in seconds. Range 10–360, default 20. Valid when model is |
Callbacks
Request
Body Params application/jsonRequired
Responses
Request Request Example
Shell
JavaScript
Java
Swift
curl --location 'https://api.kie.ai/api/v1/jobs/createTask' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"model": "ai-music-api/upload-and-cover-audio",
"callBackUrl": "https://api.example.com/callback",
"input": {
"upload_url": "https://storage.example.com/upload",
"prompt": "A calm and relaxing piano track with soft melodies",
"instrumental": true,
"model": "V4",
"style": "Classical",
"title": "Peaceful Piano Meditation",
"negative_tags": "Heavy Metal, Upbeat Drums",
"vocal_gender": "m",
"style_weight": 0.65,
"weirdness_constraint": 0.65,
"audio_weight": 0.65,
"persona_id": "persona_123",
"persona_model": "style_persona",
"lyrics": "[Verse]\nKeep the melody flowing\nInto a gentle bridge\n[Chorus]\nLet the piano rise and fall",
"variety": 1
}
}'Response Response Example
{
"code": 200,
"msg": "success",
"data": {
"taskId": "5c79****be8e"
}
}