Is it possible to generate a real-time processed voice?

[leogogog]

Use case: Meeting with foreigners

[Zengyi-Qin]

This is doable but with a lot of engineering effort. You can actually do real-time video chat with some bots on MyShell such as this one https://app.myshell.ai/bot/vEvm2q/6958

[leogogog]

Thanks~ this case could significantly enhances the global company's efficiency.

[printlin]

我已经完成了实时语音生成的工作，您可以查看：https://github.com/myshell-ai/OpenVoice/issues/54 I have completed the real-time voice generation work, you can check it: https://github.com/myshell-ai/OpenVoice/issues/54

[leogogog]

Amazing！ I'll feedback after try!!

[Arunprakaash]

I have created a streaming websocket server where it outputs audio chunks as it being processed and also accepts text streaming as input and outputs audio stream

github: https://github.com/Arunprakaash/openvoice.streaming.server