A WebRTC server that allows you to interact with an LLM using your speech and responds back with generated audio.
145
stars
36
commits
Python
primary language
Jun 18, 2024
updated
README
WebRTC AI Voice Chat
Overview
The goal of this project is to demo speech <-> langchain <-> audio workflow.
- Speech to text is using OpenAI's open source Whisper mini model.
- Chat model used for this demo is Microsoft's Phi3 model running locally using Ollama.
- Text to Audio is using Suno's open source Bark small model.
For interesting projects and related resources, checkout the Awesome Projects Page.
Demo
Unmute the audio to hear responses
Contributors
36 commits
Similar repos
Languages
Python
45.3%
CSS
21.5%
JavaScript
20.9%
HTML
12.2%
A WebRTC server that allows you to interact with an LLM using your speech and responds back with generated audio.
145
stars
36
commits
Python
primary language
Jun 18, 2024
updated
README
WebRTC AI Voice Chat
Overview
The goal of this project is to demo speech <-> langchain <-> audio workflow.
- Speech to text is using OpenAI's open source Whisper mini model.
- Chat model used for this demo is Microsoft's Phi3 model running locally using Ollama.
- Text to Audio is using Suno's open source Bark small model.
For interesting projects and related resources, checkout the Awesome Projects Page.
Demo
Unmute the audio to hear responses
Similar repos
Contributors
36 commits
Languages
Python
45.3%
CSS
21.5%
JavaScript
20.9%
HTML
12.2%