- Product Overview
- Purchase Guide
- Introduction of Avatar
- Server API Integration
- Avatar aPaas API Calling Methods
- Avatar Image Customization and Voice Clone API Documentation - v 0.2.1
- Video Generation Service API Documentation - v 4.9.9
- Overview
- Digital Human aPaaS API Calling Methods
- Audio Production API
- Video Production API - Basic Edition
- Audio and Video Production Progress Query API
- Video Production API - Advanced Version
- Customer Resource Query Anchor API
- Querying All Images of a Specific Anchor
- Querying the Supported Timbres for VirtualmanKey (to Be Deprecated)
- Querying the Supported Actions for VirtualmanKey
- Appendix
- API Integration FAQs
- Interactive Digital Human Service API Documentation - v 5.0.3
- Overview
- Digital Human aPaaS API Calling Methods
- Live Session Management
- Creating a New Live Stream Session
- Using the Personal Asset Image to Create a Stream
- Querying the Session Status
- Starting Session
- Closing Live Session
- Querying the Conversation List under the Digital Human Project
- Querying the Conversion List under the Personal Asset Image
- Querying the Session List under UIN
- Instruction-driven
- Other APIs
- Error Code Description
- Best Practices demo
- Personal Asset Management API Documentation - v 1.1.2
- Overview
- Digital Human aPaaS API Calling Methods
- Querying for Avatar List by Pagination API
- Querying Supported Timbres for Avatars (to be Deprecated)
- Querying Customer Service Asset Information
- Querying Timbre Lists by Pagination
- Querying Image Asset Information - Query Anchor
- Querying Image Asset Information - Querying all Avatars under the Anchor
- Querying the List Of Actions Supported by the Avatar
- Appendix 1 - Service Asset Type
- Appendix 2 - Emotional Style
- Appendix 3 - Digital Human Type
- API Integration FAQs
- Client SDK Integration
- TCADH Platform Operation Guide
- FAQs
- Product Overview
- Purchase Guide
- Introduction of Avatar
- Server API Integration
- Avatar aPaas API Calling Methods
- Avatar Image Customization and Voice Clone API Documentation - v 0.2.1
- Video Generation Service API Documentation - v 4.9.9
- Overview
- Digital Human aPaaS API Calling Methods
- Audio Production API
- Video Production API - Basic Edition
- Audio and Video Production Progress Query API
- Video Production API - Advanced Version
- Customer Resource Query Anchor API
- Querying All Images of a Specific Anchor
- Querying the Supported Timbres for VirtualmanKey (to Be Deprecated)
- Querying the Supported Actions for VirtualmanKey
- Appendix
- API Integration FAQs
- Interactive Digital Human Service API Documentation - v 5.0.3
- Overview
- Digital Human aPaaS API Calling Methods
- Live Session Management
- Creating a New Live Stream Session
- Using the Personal Asset Image to Create a Stream
- Querying the Session Status
- Starting Session
- Closing Live Session
- Querying the Conversation List under the Digital Human Project
- Querying the Conversion List under the Personal Asset Image
- Querying the Session List under UIN
- Instruction-driven
- Other APIs
- Error Code Description
- Best Practices demo
- Personal Asset Management API Documentation - v 1.1.2
- Overview
- Digital Human aPaaS API Calling Methods
- Querying for Avatar List by Pagination API
- Querying Supported Timbres for Avatars (to be Deprecated)
- Querying Customer Service Asset Information
- Querying Timbre Lists by Pagination
- Querying Image Asset Information - Query Anchor
- Querying Image Asset Information - Querying all Avatars under the Anchor
- Querying the List Of Actions Supported by the Avatar
- Appendix 1 - Service Asset Type
- Appendix 2 - Emotional Style
- Appendix 3 - Digital Human Type
- API Integration FAQs
- Client SDK Integration
- TCADH Platform Operation Guide
- FAQs
What is Tencent Cloud AI Digital Human?
By using multiple AI technologies such as voice interaction and digital model generation, Tencent Cloud AI Digital Human has synchronized lip movements and pronunciation, and natural expressions and motions. It supports two types of usage scenarios: AI synthesis virtual image broadcast video and real-time voice interaction. The default virtual human image is used in virtual image broadcast, and the video file synthesized by AI can be generated by inputting text or audio on digital human platform. The lip movements of digital human are consistent with the pronunciation of the text, and the expressions and motions are natural. You can make real-time voice interaction with digital human in voice interaction scenarios.
What can Tencent Cloud AI Digital Human do?
It helps enterprises reduce labor cost during content production and improve product credibility and value. It also helps brands build differentiated IP and make products more attractive. It is widely used in famous teacher class, news anchor, customer service, voice assistant and other scenarios.
How does Tencent Cloud AI Digital Human charge?
Offline charging is adopted. You can contact our customer service for purchase consultation. For details, please refer to Contact Us.
How many languages does TCADH support?
TCADH currently supports multilingual scene applications, please contact us for more information and support.
Can I try Tencent Cloud AI Digital Human? How can I learn more about the product?
If you need to try out or learn more about the product, please contact the pre-sales customer service for demand communication, application scenarios and business negotiations.
How does Tencent Cloud AI Digital Human train a new image?
Tencent Cloud AI Digital Human uses motion capture, 3D modeling, Text To Speech and other technologies to highly restore the image of a real person. Driven by artificial intelligence, it has an image similar to a real person, realistic expression and movements, lip movements synchronized with voice in real time, and ability to express emotions and communicate. The highly anthropomorphic virtual digital image can interact with people like a real person, bringing a new sensory experience. According to the category, image training can be divided into 2D and 3D: 2D is divided into boutique image and small sample image:
① After about two weeks of training with motion materials recorded in professional studios, the boutique image will generate a digital human applied to broadcasting and interactive scenarios. You can randomly insert the text of a specified motion and other different motions into it. It can be driven by voice or text.
② 3-minute video is necessary in small sample image training. There is no strict requirement on recording environment, so it can quickly generate the same digital avatar as a real person to be used in broadcast. Its facial features, motions and expressions completely imitate a real person. You only need to enter text or voice to quickly generate digital human broadcast videos. According to your requirement, the facial features, hairstyle, clothing, accessories, etc. will first be set in original painting during 3D digital human production. Next, the modeling will start after you review and confirm the final image. After bone binding, rendering, UE tuning and other stages, a digital human that can be used for interaction and broadcasting will be produced. You can randomly insert a specified motion into it. It can be driven by voice or text.
How does the product charge?
Yes
No
Was this page helpful?