⌘K

Kirin Custom Voices

kirin_custom_voices

Voice customization API for creating custom voices from audio/video files or historical work IDs.

Authentication

authorization string required

All APIs require authentication via Bearer Token.

Get API Key:

Visit API Key Management Page to get your API Key.

Usage:

Add to request header:

Authorization: Bearer YOUR_API_KEY

Parameters

model string required

Model ID used for the request

Value: kirin_custom_voices

voice_name string required

Voice name. Voices that are no longer needed can be deleted via API.

Note: Maximum length is 20 characters

voice_url string

URL to the voice data file

Supported formats: .mp3 / .wav / .mp4 / .mov
The audio must contain only one clean human voice with no background noise; duration must be between 5 and 30 seconds

video_id string

Historical work ID. Provides audio material by referencing a previously generated work.

Only videos meeting the following conditions can be used for voice customization:
Videos generated with V2.6 model with sound parameter set to on
Videos generated via the Digital Human API
Videos generated via the Lip Sync API

Note: The audio must contain only one clean human voice with no background noise; duration must be between 5 and 30 seconds

callback_url string

Callback URL

external_task_id string

Custom task ID. Does not override the system-generated task ID but can be used to query the task.

Note: Must be unique per user.

Polling

Since result generation takes time, you need to poll the task status after creating the task.

The initial response only returns information such as the task ID and initial status. The final result must be obtained by polling the task status endpoint using the task ID.

See the examples on the right for polling requests and responses.