Speech Kit, a scenario-based speech service, integrates voice AI capabilities including the TextReader for speech control and the AICaptionComponent for AI caption control. This seamless integration enhances user-device interaction and delivers the speech function for users.
The read control TextReader is widely used when it is inconvenient for a user to view texts on the screen, and the control will read news and provide information for the user.
The AICaption control offers a captioning service for users who are unfamiliar with the audio source language or when the audio is muted. It allows them to follow along with the content through captions.
| AI Capability | Constraint |
|---|---|
| TextReader | Supported language: Chinese |
| AICaption | Supported languages: Chinese and English Supported audio streams: - Audio type: Only PCM is supported. - Audio sampling rate: Only sampling rate 16000 is supported. - Audio channel: Only one audio channel is supported. - Audio sampling bit depth: Only 16-bit is supported. This control is not supported on some device models. If the call fails, the error code Initialization failed is returned. |