๐ Uses faster_whisper and elevenlabs input streaming for low latency responses to spoken input.
Rename the .env_example
to .env
and enter your OpenAI and ElevenLabs API key values in the .env file
Make sure you have installed mpv player.
๐ฅ๏ธ Windows Users:
- ๐ฅ Download the latest mpv archive file from https://mpv.io/
- ๐ Extract the folder and rename it to mpv
- ๐ Copy the folder to "C:\Program Files"
- ๐ Give user permissions (right-click "mpv" folder, properties, security, Users --> Full Control checkbox)
- ๐โโ๏ธ Go to installer folder and run the installer as Administrator
- ๐ Copy the directory "C:\Program Files\mpv"
- ๐ Open "System Environment Variables" from the Windows search bar and click "Environment Variables"
- ๐ In System environment variables, find "Path", click "Edit"
- โ Add "C:\Program Files\mpv" to the list and click Ok on all windows
- ๐ Restart the system
๐ Mac Users:
Run: brew install mpv
๐ง Linux Users:
Install it yourself. You're not like Windows users and You are the chad and chads don't need help.. ๐
Install the required Python libraries:
pip install -r requirements.txt
Execute the main script:
python main.py
๐ฃ๏ธ Talk into your microphone and ๐ Listen to the reply
๐ Feel free to fork, improve, and submit pull requests. If you're considering significant changes or additions, please start by opening an issue.