Skip to content

A Node.js WhatsApp Bot to automatically transcribe voice messages using whisper.cpp.

License

Notifications You must be signed in to change notification settings

lucaboy/whatsapp-audio-transcriber

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

whatsapp-audio-transcriber

A Node.js WhatsApp Bot to automatically transcribe voice messages using whisper.cpp.

Overview

This project uses:

Usage

  1. Download and install FFmpeg.

  2. Clone this repository, install dependencies and build the application git clone https://github.com/lucaboy/whatsapp-audio-transcriber.git && cd whatsapp-audio-transcriber && npm install && npm run build.

  3. Download the OpenAI's Whisper model converted to ggml format from here.

  4. Rename the .env.example file to .env and edit it with your configuration (make sure to edit the WHISPER_LOCAL_MODEL_PATH parameter with the path of the downloaded Whisper model).

  5. Start the application: npm start.

  6. Open the following URL in your browser: http://localhost:8080.

  7. Scan the QR code using the WhatsApp mobile app to authenticate.

  8. Test the application by reacting with "🤖" to a voice message and check the transcribed text.

About

A Node.js WhatsApp Bot to automatically transcribe voice messages using whisper.cpp.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published