Skip to main content
When you submit a task to the Vocal Separation API, you can use the callBackUrl parameter to set a callback URL. When the task is completed, the system will automatically push the results to your specified address.

Callback Mechanism Overview

The callback mechanism eliminates the need to poll the API for task status. The system will proactively push task completion results to your server.

Callback Timing

The system will send callback notifications in the following situations:
  • Vocal separation task completed successfully
  • Vocal separation task failed
  • Errors occurred during task processing

Callback Method

  • HTTP Method: POST
  • Content Type: application/json
  • Timeout Setting: 15 seconds

Callback Request Format

When the task is completed, the system will send different format callback data based on the separation type you selected:

Status Code Description

integer
required
Callback status code indicating task processing result:
string
required
Status message providing detailed status description
string
required
Task ID, consistent with the taskId returned when you submitted the task
object
Vocal separation result information, returned on success

separate_vocal Type Field Description

string
Original mixed audio file URL
string
Instrumental-only audio file URL (vocals removed)
string
Vocals-only audio file URL (instrumental removed)

split_stem Type Field Description

string
Original mixed audio file URL
string
Vocals-only audio file URL
string
Backing vocals audio file URL
string
Drums audio file URL
string
Bass audio file URL
string
Guitar audio file URL
string
Keyboard audio file URL
string
Percussion audio file URL
string
Strings audio file URL
string
Synthesizer audio file URL
string
Effects audio file URL
string
Brass audio file URL
string
Woodwinds audio file URL

split_stem_advanced Type Field Description

array
An array of separation results for the original audio, containing extraction and removal information for multiple stem groups. Each element represents an independent stem group (e.g., Lead Vocal).
object
Information about the extracted target stem (isolates this stem while removing others).
number
The duration of the extracted audio, in seconds.
string
The download URL of the extracted target stem audio file.
string
The stem type group name (e.g., Lead Vocal), indicating which type of stem this group extracts.
string
The unique identifier for the extracted audio.
object
Information about the remaining audio after removing the target stem (removes this stem while keeping others).
number
The duration of the audio after removal, in seconds.
string
The download URL of the remaining audio file after the target stem has been removed.
string
The stem type group name (e.g., Lead Vocal), consistent with the corresponding extract entry.
string
The unique identifier for the remaining audio.

Callback Reception Examples

Here are example codes for receiving callbacks in popular programming languages:

Best Practices

Callback URL Configuration Recommendations

  1. Use HTTPS: Ensure your callback URL uses HTTPS protocol for secure data transmission
  2. Verify Source: Verify the legitimacy of the request source in callback processing
  3. Idempotent Processing: The same taskId may receive multiple callbacks, ensure processing logic is idempotent
  4. Quick Response: Callback processing should return a 200 status code as quickly as possible to avoid timeout
  5. Asynchronous Processing: Complex business logic should be processed asynchronously to avoid blocking callback response
  6. File Management: Separated audio file download and processing should be done in asynchronous tasks
  7. Type Detection: Determine separation type based on returned fields and apply corresponding processing logic

Important Reminders

  • Callback URL must be a publicly accessible address
  • Server must respond within 15 seconds, otherwise it will be considered a timeout
  • If 3 consecutive retries fail, the system will stop sending callbacks
  • Please ensure the stability of callback processing logic to avoid callback failures due to exceptions
  • Generated audio file URLs may have time limits, recommend downloading and saving promptly
  • split_stem mode produces more files, pay attention to storage space management
  • Ensure source audio file contains corresponding musical components for optimal separation results
  • Different separation types have different callback structures, requiring appropriate processing logic

Troubleshooting

If you do not receive callback notifications, please check the following:
  • Confirm that the callback URL is accessible from the public network
  • Check firewall settings to ensure inbound requests are not blocked
  • Verify that domain name resolution is correct
  • Ensure the server returns HTTP 200 status code within 15 seconds
  • Check server logs for error messages
  • Verify that the interface path and HTTP method are correct
  • Confirm that the received POST request body is in JSON format
  • Check that Content-Type is application/json
  • Verify that JSON parsing is correct
  • Ensure proper handling of different separation type data structures
  • Confirm that separated audio file URLs are accessible
  • Check audio download permissions and network connections
  • Verify audio save paths and permissions
  • Note how source audio file quality affects separation results
  • Confirm source audio file format is supported
  • split_stem mode requires checking more audio files

Alternative Solution

If you cannot use the callback mechanism, you can also use polling:

Poll Query Results

Use the get vocal separation details endpoint to regularly query task status. We recommend querying every 30 seconds.