Chanjing Avatar

When to Use This Skill

Use this skill when the user wants to create lip-sync avatar videos with Chanjing Avatar.

Typical uses:

• - create text-driven lip-sync videos from a source avatar video
• create audio-driven lip-sync videos from a source avatar video plus uploaded audio
• upload video or audio assets and obtain INLINECODE0
• create a lip-sync generation task
• poll task status until completion and return the remote video URL

How to Use This Skill

This skill includes its own local configuration and authentication flow.

Local Configuration

This skill reads credentials from:

• - INLINECODE1
• or INLINECODE2

The credentials file should contain:

CODEBLOCK0

Supported environment variables:

• - CHANJING_CONFIG_DIR: custom local config directory
• INLINECODE4: custom API base URL, default is INLINECODE5

If credentials are missing or invalid, scripts return login guidance with the official Chanjing login URL (no browser auto-open by default):

• - INLINECODE6

Optional behavior:

• - set CHANJING_AUTO_OPEN_LOGIN=1 only when you explicitly want local scripts to try opening the login page in your default browser.

Standard Workflow

All API calls use JSON and UTF-8.

1. 1. Read local credentials and obtain a valid INLINECODE8
2. Upload the source avatar video and optional driving audio to obtain INLINECODE9
3. Create a lip-sync task with either:

- text-driven TTS input, or - uploaded audio input

1. 4. Poll the task status until success or failure
2. On success, return the remote video URL from the API response

By default, return the remote video URL only. Do not auto-download the generated video unless the user explicitly asks to save it locally.

Covered APIs

This skill currently covers:

• - INLINECODE10
• INLINECODE11
• INLINECODE12
• INLINECODE13
• INLINECODE14
• INLINECODE15

Scripts

Scripts are located in scripts/.

Script	Purpose
INLINECODE17	write or inspect local app_id / secret_key configuration
INLINECODE20

read local credentials and print a valid access_token |
| _auth.py | read local credentials, fetch or refresh access_token |
| get_upload_url | request an upload URL and return sign_url, mime_type, and file_id |
| upload_file | upload a local file, poll file_detail until ready, then print file_id |
| create_task | create a lip-sync task and print the returned task id |
| poll_task | poll task status until completion and print the remote video_url |

Usage Examples

TTS-driven lip-sync

CODEBLOCK1

Audio-driven lip-sync

CODEBLOCK2

API Notes

Access Token

Read app_id and secret_key from the local credentials file. If there is no valid token, request one from:

CODEBLOCK3

Request body:

CODEBLOCK4

Important response fields:

Field	Description
INLINECODE36	response status code
INLINECODE37

response message |
| data.access_token | valid token for subsequent calls |
| data.expire_in | token expiration timestamp |

Common status codes:

Code	Description
INLINECODE40	success
INLINECODE41

invalid parameter format |
| 40000 | parameter error |
| 50000 | system internal error |

Upload Media Files

Before creating a lip-sync task, upload the source avatar video and optional driving audio through the File Management API.

Get upload URL

CODEBLOCK5

Query parameters:

Parameter	Description
INLINECODE44	use lip_sync_video for avatar video and lip_sync_audio for driving audio
INLINECODE47

original file name with extension |

The response includes:

• - INLINECODE48
• INLINECODE49
• INLINECODE50

Use the returned sign_url with HTTP PUT to upload the file, and set Content-Type to the returned mime_type.

After upload completes, poll the file detail API until the file is ready:

CODEBLOCK6

Only use the returned file_id for task creation after the file status is ready.

Create Lip-Sync Task

Create a lip-sync task:

CODEBLOCK7

TTS-driven example

CODEBLOCK8

Audio-driven example

CODEBLOCK9

Important request fields:

Field	Description
INLINECODE56	uploaded avatar video INLINECODE57
INLINECODE58

output width, default 1080 |
| screen_height | output height, default 1920 |
| model | 0 basic, 1 high quality |
| audio_type | tts or audio |
| tts_config.text | text content for TTS-driven mode |
| tts_config.audio_man_id | voice ID for TTS-driven mode |
| tts_config.speed | speech speed, range 0.5 to 2 |
| tts_config.pitch | pitch, usually keep 1 |
| audio_file_id | uploaded driving audio file_id for audio-driven mode |
| callback | optional callback URL |
| volume | optional volume, range 1 to 100 |

Successful response:

CODEBLOCK10

Important response fields:

Field	Description
INLINECODE81	response status code
INLINECODE82

response message |
| data | task id used for polling |

Query Task List

List lip-sync tasks:

CODEBLOCK11

Request body:

CODEBLOCK12

Important response fields in each task item:

Field	Description
INLINECODE84	task id
INLINECODE85

0 pending, 10 generating, 20 success, 30 failed |
| progress | generation progress |
| msg | task message |
| video_url | remote generated video URL |
| preview_url | preview image URL |
| duration | video duration in ms |
| create_time | unix timestamp |

Poll Task Detail

Poll task status until completion:

CODEBLOCK13

Query parameter:

Parameter	Description
INLINECODE96	task id

Important response fields:

Field	Description
INLINECODE97	task id
INLINECODE98

0 pending, 10 generating, 20 success, 30 failed |
| data.progress | progress 0-100 |
| data.msg | task message |
| data.video_url | remote video URL |
| data.preview_url | preview image URL |
| data.duration | video duration in ms |
| data.create_time | unix timestamp |

Callback Notification

If a callback URL is provided, the system may send a POST request after task completion with the same task detail payload shape.

Output Convention

Default behavior:

• - return the remote video URL from INLINECODE110
• return task status and progress when polling
• do not auto-download the generated file unless the user explicitly asks