Customization API

Last updated: 2025-07-03 11:34:06

Customization API

Last updated: 2025-07-03 11:34:06

Use this API to submit customization requests. Query the stages of customization and relevant information through the Progress Query API.
Calling Protocol
HTTPS + JSON
POST /v2/ivh/assetmanager/customservice/make
Header Content-Type: application/json;charset=utf-8
Request Parameters
Parameters
Type
Mandatory
Description
AnchorName
string
Yes
Anchor name:
1. This name is mainly used to identify the custom avatar/sound and can be customized depending on the actual situation.
2. Naming reference: If the number of customizations for the anchor is only 1, it can be named directly after the anchor, such as "Zhang San", or add the name of the clothing for better identification, such as "Zhang San blue suit".
3. No more than 50 characters, at least 2 characters. Only allow Chinese characters, letters, digits, underscores, and hyphens.
4. Must be unique.
MakeType
string
Yes
Customization categories:
1. IMAGE: 2D small sample - standard version (Studio Lip-Sync) avatar customization.
2. IMAGE_GENERAL: 2D small sample - standard version (general lip movement) avatar customization.
3. IMAGE_4K: 2D small sample - high-precision version (Studio Lip-Sync) avatar customization.
4. IMAGE_PHOTO: 2D small sample (photo avatar) avatar customization.
5. VOICE: Timbre Clone (Basic Version).
6. ZERO_SHOT_VOICE: Timbre Clone (Ultra-fast Version).
IdentityCosUrl
string
No
Except for the IMAGE_PHOTO and ZERO_SHOT_VOICE customization types, fill in either the IdentityWrittenCosUrl or another customization type, or both.
Requirements for the URL address of the video format authorization letter:
1. The URL address is the resource URL uploaded to the specified path via uploading material to Tencent Cloud COS, with the idcard path added. For example, domain name/customer-pipeline/{number}/{uuid}/idcard/a.mp4.
2. This format is mainly suitable for oral authorization letters, or you can submit written authorization letters as clear and complete videos.
IdentityWrittenCosUrl
string
No
Except for the IMAGE_PHOTO and ZERO_SHOT_VOICE customization types, fill in either the IdentityCosUrl or another customization type, or both.
Requirements for the URL address of the PDF format authorization letter:
1. URL address is the resource URL uploaded to the specified path by uploading material to Tencent Cloud COS, with the idcard path added. For example, domain name /customer-pipline/{number}/{uuid}/idcard/b.pdf.
2. This format is mainly suitable for "written authorization letter" and should be submitted as a clear and complete scanned copy.
MaterialCosUrl
string
No
Except for the ZERO_SHOT_VOICE customization type, all other customization types are required.
﻿
Avatar customization material URL address requirements:
1. URL address is the resource URL uploaded to the specified path via upload material to Tencent Cloud COS, with the video path added, such as /customer-pipline/{number}/{uuid}/video/c.mp4.
2. Video size, no more than 5GB, 4K not more than 10GB.
3. Video duration: exclusive lip sync version customization duration is 2-10 minutes; customizable duration for general lip sync version is 1-10 minutes; customization duration for high-precision version is 2-10 minutes.
4. Video resolution: 1080P or 4K (3840*2160); for high-precision version customization, it must be 4K.
5. Video aspect ratio: 16:9 (or 9:16)
6. Video frame rate: No less than 25 fps and no more than 60 fps.
7. Video format: MP4 and MOV
﻿
Customized Text To Speech material URL address requirements:
1.  URL address is the resource URL uploaded to the specified path via upload material to Tencent Cloud COS, with the audio path added, such as /customer-pipline/{number}/{uuid}/audio/c.zip.
2.  Compressed file format: zip format, one zip package for customizing one voice type; do not create new folders when compressing, select all wav files directly for compression.
3. Notes for audio files within a single zip file:
Audio quantity: A zip file can contain one or more wav formatted audio files, with a total amount no more than 10.
Audio size: The total size of the audio files in each zip file is no more than 1G.
Audio format: Each audio file must be in wav format. For other audio formats, convert to wav format before recompressing into zip.
Audio sample rate: The sampling rate should be equal to or greater than 24K, recommend 24K or 36K.
Audio naming: Name should not contain spaces or special characters, extension should be lowercase ".wav".
﻿
Photo Digital Human customization material URL address requirements:
1.  URL address is the resource URL uploaded to the specified path via upload material to Tencent Cloud COS, with the photo path added, such as /customer-pipline/{number}/{uuid}/photo/example.png.
2. Image name: at least 2 characters, only allow Chinese characters, letters, digits, underscores, hyphens. Image format: support jpg, jpeg, png, webp. Image size: no more than 16M. Image aspect ratio: support 1:1, 9:16, 16:9, 4:3. 
3. Clear front view of the person, face-centered, natural expression, mouth closed.
IsHaveBackground
bool
No
Image customization type: Whether the trained image retains the original background. The default is "No", meaning that the original background is not retained, and the background can be changed as needed during application.
SexType
string
Yes
Gender:
MALE: Male
FEMALE: Female
Notes
string
No
Customized remarks, within 100 characters.
TextDriver
string
No
Text content used to generate the driving demo, with a character length between 4 and 1000 (including SSML tags, each Chinese character counts as one character).
VoiceDriverCosFile
string
No
Requirements for the audio file path for generating the driving demo:
1. URL address is the resource URL uploaded to the specified path via upload material to Tencent Cloud COS, with the audio path added, such as /customer-pipline/{number}/{uuid}/audio/example.wav.
2. Audio file size cannot exceed 10M, format support wav, mp3, wma, m4a, aac.
AudioId
string
No
For the ZERO_SHOT_VOICE customization type, it is required to fill in the AudioId returned after passing the Query Audio Quality Inspection Task Progress.
﻿
Response Parameter
Parameters
Type
Mandatory
Description
TaskId
string
Yes
The created task ID. Access the Progress Query API with the TaskId to obtain the production progress and result.
Request Sample
{
    "Header": {},
    "Payload": {
        "AnchorName": "Jingxuan in a green dress, sitting pose",
        "MakeType": "IMAGE",
        "IdentityCosUrl": "XXXX",
        "MaterialCosUrl": "YYYY",
        "IsRemoveBackground": true
    }
}
Response Sample
{
    "Header": {
        "Code": 0,
        "DialogID": "",
        "Message": "",
        "RequestID": "123"
    },
    "Payload": {
        "TaskId": "666"
    }
}
 
﻿

Was this page helpful?

You can also Contact Sales or Submit a Ticket for help.

Yes

Feedback

Parameters	Type	Mandatory	Description
AnchorName	string	Yes	Anchor name: 1. This name is mainly used to identify the custom avatar/sound and can be customized depending on the actual situation. 2. Naming reference: If the number of customizations for the anchor is only 1, it can be named directly after the anchor, such as "Zhang San", or add the name of the clothing for better identification, such as "Zhang San blue suit". 3. No more than 50 characters, at least 2 characters. Only allow Chinese characters, letters, digits, underscores, and hyphens. 4. Must be unique.
MakeType	string	Yes	Customization categories: 1. IMAGE: 2D small sample - standard version (Studio Lip-Sync) avatar customization. 2. IMAGE_GENERAL: 2D small sample - standard version (general lip movement) avatar customization. 3. IMAGE_4K: 2D small sample - high-precision version (Studio Lip-Sync) avatar customization. 4. IMAGE_PHOTO: 2D small sample (photo avatar) avatar customization. 5. VOICE: Timbre Clone (Basic Version). 6. ZERO_SHOT_VOICE: Timbre Clone (Ultra-fast Version).
IdentityCosUrl	string	No	Except for the IMAGE_PHOTO and ZERO_SHOT_VOICE customization types, fill in either the IdentityWrittenCosUrl or another customization type, or both. Requirements for the URL address of the video format authorization letter: 1. The URL address is the resource URL uploaded to the specified path via uploading material to Tencent Cloud COS, with the idcard path added. For example, domain name/customer-pipeline/{number}/{uuid}/idcard/a.mp4. 2. This format is mainly suitable for oral authorization letters, or you can submit written authorization letters as clear and complete videos.
IdentityWrittenCosUrl	string	No	Except for the IMAGE_PHOTO and ZERO_SHOT_VOICE customization types, fill in either the IdentityCosUrl or another customization type, or both. Requirements for the URL address of the PDF format authorization letter: 1. URL address is the resource URL uploaded to the specified path by uploading material to Tencent Cloud COS, with the idcard path added. For example, domain name /customer-pipline/{number}/{uuid}/idcard/b.pdf. 2. This format is mainly suitable for "written authorization letter" and should be submitted as a clear and complete scanned copy.
MaterialCosUrl	string	No	Except for the ZERO_SHOT_VOICE customization type, all other customization types are required. Avatar customization material URL address requirements: 1. URL address is the resource URL uploaded to the specified path via upload material to Tencent Cloud COS, with the video path added, such as /customer-pipline/{number}/{uuid}/video/c.mp4. 2. Video size, no more than 5GB, 4K not more than 10GB. 3. Video duration: exclusive lip sync version customization duration is 2-10 minutes; customizable duration for general lip sync version is 1-10 minutes; customization duration for high-precision version is 2-10 minutes. 4. Video resolution: 1080P or 4K (38402160); for high-precision version customization, it must be 4K. 5. Video aspect ratio: 16:9 (or 9:16) 6. Video frame rate: No less than 25 fps and no more than 60 fps. 7. Video format: MP4 and MOV Customized Text To Speech material URL address requirements:* 1. URL address is the resource URL uploaded to the specified path via upload material to Tencent Cloud COS, with the audio path added, such as /customer-pipline/{number}/{uuid}/audio/c.zip. 2. Compressed file format: zip format, one zip package for customizing one voice type; do not create new folders when compressing, select all wav files directly for compression. 3. Notes for audio files within a single zip file: Audio quantity: A zip file can contain one or more wav formatted audio files, with a total amount no more than 10. Audio size: The total size of the audio files in each zip file is no more than 1G. Audio format: Each audio file must be in wav format. For other audio formats, convert to wav format before recompressing into zip. Audio sample rate: The sampling rate should be equal to or greater than 24K, recommend 24K or 36K. Audio naming: Name should not contain spaces or special characters, extension should be lowercase ".wav". Photo Digital Human customization material URL address requirements: 1. URL address is the resource URL uploaded to the specified path via upload material to Tencent Cloud COS, with the photo path added, such as /customer-pipline/{number}/{uuid}/photo/example.png. 2. Image name: at least 2 characters, only allow Chinese characters, letters, digits, underscores, hyphens. Image format: support jpg, jpeg, png, webp. Image size: no more than 16M. Image aspect ratio: support 1:1, 9:16, 16:9, 4:3. 3. Clear front view of the person, face-centered, natural expression, mouth closed.
IsHaveBackground	bool	No	Image customization type: Whether the trained image retains the original background. The default is "No", meaning that the original background is not retained, and the background can be changed as needed during application.
SexType	string	Yes	Gender: MALE: Male FEMALE: Female
Notes	string	No	Customized remarks, within 100 characters.
TextDriver	string	No	Text content used to generate the driving demo, with a character length between 4 and 1000 (including SSML tags, each Chinese character counts as one character).
VoiceDriverCosFile	string	No	Requirements for the audio file path for generating the driving demo: 1. URL address is the resource URL uploaded to the specified path via upload material to Tencent Cloud COS, with the audio path added, such as /customer-pipline/{number}/{uuid}/audio/example.wav. 2. Audio file size cannot exceed 10M, format support wav, mp3, wma, m4a, aac.
AudioId	string	No	For the ZERO_SHOT_VOICE customization type, it is required to fill in the AudioId returned after passing the Query Audio Quality Inspection Task Progress.

tencent cloud

Calling Protocol

Request Parameters

Response Parameter

Request Sample

Response Sample