Overview of digital human

Digital human APIs cover asset uploads, public or private resources, text-to-speech and video synthesis. Submit tasks through POST /v1/tasks and manage assets through /v1/assets/uploads and /v1/assets/{asset_id}.

The scene entrance.

Assets Resources and Images upload image, audio and authorized media assets, reuse Asset ID. VoicesVoice assetsCreate or reference reusable voices from audio assets.AudioCreate audio tasksGenerate speech using public voices or voice assets.VideoCreate video tasksCombine avatar assets and audio into digital human videos.

Route List

Methodology	Path	Purpose
POST	/v1/assets/uploads	Upload or register digital human images, audio, authorized videos, etc. media assets.
GET	/v1/assets/{asset_id}	Find media assets details.
POST	/v1/tasks	Creates digital human audio, video or resource processing task.
GET	/v1/tasks/{task_id}	Ask for task status, cause of failure and result.

Basic processes

1. Prepares public resources ID, or uploads their image, audio, and authorized media assets.
2. Saves returned asset_id or Asset://asset_xxx.
3. Call POST /v1/tasks to generate audio or video.
4. Call GET /v1/tasks/{task_id} Query task Status.
5. Read URL after success; read fail_reason or error when failure.

Relevant Pages

• Digital human guide
• Resources and Images
• Voice assets
• Create Audio Job
• Create Video Job
• Uploading and Media Asset Overview
• Overview of mandate management
• API Reference