The changelog:
- Support mobile and PC browser. v1.0.0
- Request microphone permission when starting. v1.0.2
- Support single assistant to talk with. v1.0.3
- Dispose recorder and stream when record done. v1.0.4
- Setup the website title to AI Talk whatever. v1.0.6
- Limit the response words to 50 words by default. v1.0.10
- Support multiple assistants and select before start. v1.0.11
- Setup model and robots by environment variables. v1.0.12
- Fix Android browser select button label issue. v1.0.13
- Add micWorking and attention state to avoid data loss. v1.0.14
- Refine the UI for mobile browser. v1.0.15
- Fast require microphone permission. v1.0.16
- Save user select robot to local storage. v1.0.17
- Refine the UI and history message style. v1.0.18
- Limit to 30 words and config in robot. v1.0.19
- Use css to draw a microphone icon. v1.0.20
- Refine the data loss before and after record. v1.0.21
- Add text tips label to use microphone. v1.0.22
- Refine the startup waiting UI. v1.0.23
- Support setup chat AI model for each robot. v1.0.24
- Support setup chat window for each robot. v1.0.25
- Alert error when not HTTPS. v1.0.26
- Support HTTPS proxy for OpenAI. v1.0.27
- Support official OpenAI API without proxy. v1.0.28
- Always use HTTPS proxy if not specified. v1.0.29
- Do not require some variables. v1.0.30
- Refine the logs for user and bot. v1.0.31
- Detect user silent and warning. v1.0.32
- Refine bot log for the first time. v1.0.33
- Allow user retry when error. v1.0.34
- Refine badcase for user input. v1.0.35
- Fix bug for setting window for robot. v1.0.36
- Support setup API proxy and key for ASR,Chat,TTS. v1.0.37
- Support Tencent Speech to speed up. v1.0.37
- Support share logging text mode. v1.0.38
- Fix some badcase for sentence determine. v1.0.39
- Speed up the ASR, without transcode. v1.0.40
- Refine the stat for elapsed time cost of upload. v1.0.41
- Refine the log label. v1.0.46