Key Capabilities
- Accepts uploadUrl of an existing audio file (usually vocals or stems).
- Supports fine-grained customization via parameters such as:
- tags and negativeTags (musical style controls)
- styleWeight, audioWeight, weirdnessConstraint (stylistic & creative blending)
- vocalGender, title, callBackUrl for metadata & workflow control .
- Returns a taskId for tracking, and results are retained for 14 days. Callback workflow includes three stages: text, first, and complete .
Typical Use Cases
- Singers or melody writers who want instant fuller arrangements around their vocal inputs.
- Applications like karaoke platforms, demo-generation tools, or co-creation interfaces that allow users to experiment with accompaniment styles easily.
Parameter Usage Guide
Required parameters for all requests:uploadUrl
: Valid audio file URL (MP3, WAV, or other supported formats)title
: Title for the generated instrumental track (80 characters max)tags
: Desired style and characteristics for the instrumentalnegativeTags
: Styles or instruments to excludecallBackUrl
: URL to receive completion notifications
vocalGender
: Preferred vocal gender for any vocal elements (‘m’ or ‘f’)styleWeight
: Style adherence weight (0.00-1.00)weirdnessConstraint
: Creativity/novelty constraint (0.00-1.00)audioWeight
: Audio consistency weight (0.00-1.00)model
: Model version used for generation. Allowed values:V4_5PLUS
(default),V5
- File Format: MP3, WAV, or other supported audio formats
- Quality: Higher quality input generally produces better instrumental results
- Accessibility: Ensure uploaded audio URLs are publicly accessible and stable
Developer Notes
- Generated instrumental files are retained for 15 days before being deleted
- Ensure you have proper rights to use the uploaded audio content
- Be specific with tags to get the desired instrumental style (e.g., “acoustic guitar, soft piano, ambient”)
- Use negative tags effectively to avoid unwanted elements
- Callback process has three stages: text (text generation), first (first track complete), complete (all tracks complete)
- You can use the Get Music Generation Details endpoint to actively check task status instead of waiting for callbacks
Authorizations
🔑 API Authentication
All endpoints require authentication using Bearer Token.
Get API Key
- 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
The URL of the uploaded music file to add instrumental to.
- Required.
- Must be a valid audio file URL accessible by the system.
- The uploaded audio should be in a supported format (MP3, WAV, etc.).
"https://example.com/music.mp3"
The title of the music track.
- Required.
- This will be used as the title for the generated instrumental track.
"Relaxing Piano"
Music styles or traits to exclude from the generated instrumental.
- Required.
- Use to avoid specific styles or instruments in the instrumental version.
Example: "Heavy Metal, Aggressive Drums"
"Heavy Metal, Aggressive Drums"
Music style and characteristics for the instrumental.
- Required.
- Describe the desired style, mood, and instruments for the instrumental track.
Example: "Relaxing Piano, Ambient, Peaceful"
"Relaxing Piano, Ambient, Peaceful"
The URL to receive task completion notifications when instrumental generation is complete. The callback process has three stages: text
(text generation), first
(first track complete), complete
(all tracks complete). Note: In some cases, text
and first
stages may be skipped, directly returning complete
.
For detailed callback format and implementation guide, see Add Instrumental Callbacks
- Alternatively, you can use the Get Music Generation Details interface to poll task status
"https://api.example.com/callback"
Preferred vocal gender for any vocal elements. Optional. Allowed values: 'm' (male), 'f' (female).
m
, f
"m"
Style adherence weight. Optional. Range: 0-1. Two decimal places recommended.
0 <= x <= 1
Must be a multiple of 0.01
0.61
Creativity/novelty constraint. Optional. Range: 0-1. Two decimal places recommended.
0 <= x <= 1
Must be a multiple of 0.01
0.72
Relative weight of audio consistency versus other controls. Optional. Range: 0-1. Two decimal places recommended.
0 <= x <= 1
Must be a multiple of 0.01
0.65
Model version to use for generation. Optional. Default: V4_5PLUS.
V4_5PLUS
, V5
"V4_5PLUS"
Response
Request successful
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
200
, 400
, 401
, 404
, 405
, 413
, 429
, 430
, 455
, 500
200
Error message when code != 200
"success"