https://github.com/aviaryan/voice-transcribe-summarize-telegram-bot
Telegram bot to generate transcriptions and summarise voice notes
https://github.com/aviaryan/voice-transcribe-summarize-telegram-bot
groq llama3 llm llms telegram-bot whisper
Last synced: 3 months ago
JSON representation
Telegram bot to generate transcriptions and summarise voice notes
- Host: GitHub
- URL: https://github.com/aviaryan/voice-transcribe-summarize-telegram-bot
- Owner: aviaryan
- License: mit
- Created: 2025-02-11T03:54:07.000Z (8 months ago)
- Default Branch: master
- Last Pushed: 2025-02-16T14:49:48.000Z (8 months ago)
- Last Synced: 2025-07-06T04:43:11.803Z (3 months ago)
- Topics: groq, llama3, llm, llms, telegram-bot, whisper
- Language: Python
- Homepage:
- Size: 50.8 KB
- Stars: 66
- Watchers: 1
- Forks: 14
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Voice Note Transcription and Summarizer Bot for Telegram 🎙️📝
A powerful Telegram bot that transcribes and summarizes voice notes using state-of-the-art AI models. Built with Python and powered by Groq's API with Whisper and Llama 3 model for transcription and summarization.
## Screenshots 📸
| Transcription Example | Summary Example |
|:---:|:---:|
| 
| 
|
## Features ✨
- Transcribe voice notes from forwarded messages
- Handle direct voice note recordings
- Generate accurate transcriptions using Whisper
- Provide concise summaries of the transcribed content using Llama 3
- Support for multiple audio formats
- Well-formatted, easy-to-read output
## Prerequisites 📋
- Python 3.10 or higher
- pipenv (Python package manager)
- Telegram Bot Token (from [@BotFather](https://t.me/botfather))
- Groq API Key ([Get it here](https://console.groq.com))
## Installation 🚀
1. Clone the repository:
```bash
git clone https://github.com/aviaryan/voice-transcribe-summarize-telegram-bot.git
cd voice-transcribe-summarize-telegram-bot
```
2. Install dependencies using pipenv:
```bash
pipenv install
```
3. Create a `.env` file in the root directory:
```bash
cp .env.copy .env
```
4. Fill in your environment variables in the `.env` file:
```
TELEGRAM_BOT_TOKEN=your_telegram_bot_token
GROQ_API_KEY=your_groq_api_key
```
5. Configure authorized users:
- Open `bot.py` and locate the `AUTHORIZED_USERS` array
- Add your Telegram user ID to the array (you can get your ID by messaging @userinfobot on Telegram)
```python
AUTHORIZED_USERS = [your_telegram_id] # Add more user IDs as needed
```
## Usage 🎯
1. Activate the virtual environment:
```bash
pipenv shell
```
2. Start the bot:
```bash
python bot.py
```
3. In Telegram:
- Forward any message containing a voice note to the bot
- Record and send a voice note directly to the bot
- Wait for the bot to process and return both transcription and summary
## How it Works 🔄
1. The bot receives a voice note through Telegram
2. Audio is processed and sent to Groq's API
3. Whisper model transcribes the audio content
4. Another pass through Groq's API generates a concise summary using Llama 3 model
5. Both transcription and summary are returned to the user in a well-formatted message
## Contributing 🤝
Contributions are welcome! Feel free to:
- Open issues for bugs or feature requests
- Submit pull requests
- Improve documentation
- Share feedback
## License 📄
This project is licensed under the MIT License - see the LICENSE file for details.