asif00
/

Kokoro-Conversational

speech-to-speech,

conversational-ai,

Model card Files Files and versions Community

asif00 commited on 20 days ago

Commit

bf991a3

·

verified ·

1 Parent(s): b215e48

--base

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -60,9 +60,9 @@ To achieve that we use:
 - **Voice Synthesis**: Kokoro:hexgrad/Kokoro-82M (Version 0.19, 16bit)
 We use custom text processing and queues to manage data, with separate queues for text and audio. This setup allows the system to handle heavy tasks without slowing down. We also use an interrupt mechanism allowing the user to interrupt the AI at any time. This makes the conversation feel more natural and responsive rather than just a generic TTS engine.
-## Demo Video:
-A demo video is uploaded here. Either click on the thumbnail or click on the YouTube link: [https://youtu.be/x92FLnwf-nA](https://youtu.be/x92FLnwf-nA).
 [![On Device Speech to Speech AI Demo](https://img.youtube.com/vi/x92FLnwf-nA/0.jpg)](https://youtu.be/x92FLnwf-nA)

 - **Voice Synthesis**: Kokoro:hexgrad/Kokoro-82M (Version 0.19, 16bit)
 We use custom text processing and queues to manage data, with separate queues for text and audio. This setup allows the system to handle heavy tasks without slowing down. We also use an interrupt mechanism allowing the user to interrupt the AI at any time. This makes the conversation feel more natural and responsive rather than just a generic TTS engine.
+## GitHub: https://github.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI
+## Demo Video:
+A demo video is uploaded here. Click on the thumbnail or the YouTube link: [https://youtu.be/x92FLnwf-nA](https://youtu.be/x92FLnwf-nA).
 [![On Device Speech to Speech AI Demo](https://img.youtube.com/vi/x92FLnwf-nA/0.jpg)](https://youtu.be/x92FLnwf-nA)