A server providing text-to-speech and speech-to-text functionalities using Windows' native speech services without external dependencies.
暂无评论. 成为第一个评论的人！
登录以参与讨论
Converts text to speech using Windows SAPI. Parameters: text (required), voice (optional), speed (optional, range 0.5 to 2.0, default: 1.0)
Records audio and converts it to text using Windows Speech Recognition. Parameters: duration (optional, default: 5, max: 60)
