A Dockerized Telegram bot that downloads YouTube videos as MP3 audio and transcribes them using OpenAI Whisper

• 🤖 Telegram bot interface
• 🎵 Download YouTube videos as MP3 audio
• 📝 Transcribe audio using OpenAI Whisper
• 🔄 Automatic cleanup of temporary files
• 📱 Support for long transcriptions (split into multiple messages)
• 🐳 Docker containerized for easy deployment

1. Clone the repository:

   git clone <repository-url>
   cd yt-transcript

2. Create environment file:

   # Create .env file
   echo "TELEGRAM_TOKEN=your_telegram_bot_token_here" > .env
   echo "WHISPER_MODEL=base" >> .env

3. Run with Docker Compose:

   docker-compose up -d

# Build the image
docker build -t yt-transcript-bot .

# Run the container
docker run --env-file .env yt-transcript-bot

1. Start the bot using Docker
2. Open your Telegram bot and send a YouTube URL
3. The bot will:
   • Download the video as MP3
   • Transcribe the audio using Whisper
   • Send you the transcription

• https://www.youtube.com/watch?v=VIDEO_ID
• https://youtu.be/VIDEO_ID
• https://youtube.com/embed/VIDEO_ID
• https://youtube.com/v/VIDEO_ID

• /start - Show welcome message and instructions
• /help - Show detailed help information

You can change the Whisper model size by setting the WHISPER_MODEL environment variable:

• tiny - Fastest, least accurate
• base - Good balance (default)
• small - Better accuracy
• medium - High accuracy
• large - Best accuracy, slowest

TELEGRAM_TOKEN=1234567890:ABCdefGHIjklMNOpqrsTUVwxyz
WHISPER_MODEL=base

# Start the bot
docker-compose up -d

# View logs
docker-compose logs -f

# Stop the bot
docker-compose down

# Rebuild and restart
docker-compose up -d --build

If you like this project or directly benefit from it, please consider buying me a coffee:
🔗 bc1qd0qatgz8h62uvnr74utwncc6j5ckfz2v2g4lef
⚡️ derogab@sats.mobi
💶 Sponsor on GitHub

YT-Transcript is made with ♥ by derogab and it's released under the MIT license.