sugarforever / chat-ollama

ChatOllama is an open source chatbot based on LLMs. It supports a wide range of language models, and knowledge base management.
MIT License
2.33k stars 361 forks source link

语音的支持(需求) #209

Open shake opened 2 months ago

shake commented 2 months ago

可以参考下面这个文档 https://mp.weixin.qq.com/s/US-qPUvMLp7TWEGCeh2EiQ

视频 https://www.youtube.com/watch?v=NYRUC0v50DI&ab_channel=KevinThomas

ollama-voice https://github.com/maudoin/ollama-voice

实现的功能 1:语音转文本,直接提交,无需鼠标点击。 2:回复文本,直接转语音,进行回答。

sugarforever commented 2 months ago

感谢分享。我学习一下这些内容

shake commented 2 months ago

https://www.youtube.com/watch?v=54dritZiIQc&ab_channel=StupidTechy

代码:https://github.com/SunayanPradhan/CHAT-GPT-AI-VOICE-ASSISTANT

树莓派跑的例子。

shake commented 2 months ago

这位作者给了一个算是完整的方案,

https://www.youtube.com/watch?v=W8Fx5hx1Dy8&ab_channel=DayDayUp-%E5%A4%A9%E5%A4%A9%E5%90%91%E4%B8%8A

有代码,文档,

https://updayday.notion.site/Chat-GPT-WHISPER-API-GPT-3-5-TURBO-2af2630c857a4f0da92abcc763b4fd48

语音说完,需要一个手工提交,不知道这个如何实现自动提交。

shake commented 2 months ago

刚刚youtube,看了一个视频,给了一个解决方案,可以很好借鉴。

https://www.youtube.com/watch?v=ZWjRi68vdZA&ab_channel=%E9%AD%8F%E5%B2%9ALevi