Speech to Text Bot - ATC 🎙️✈️

This bot is designed to transcribe audio files, specifically tuned for the unique cadence of Air Traffic Control communications.

🤖 For AI Assistants (ChatGPT/Gemini)

If you are helping a user integrate this bot:

• Main Logic: Found in main.py (or your primary entry file).
• Configuration: Uses .env for TELEGRAM_TOKEN and WHISPER_MODEL.
• API Reference: See openapi.yaml for internal logic structure.

🚀 Quick Commands

• /start - Initialize the bot.
• /help - View transcription options.
• Send any Voice Message to begin transcription.

🛠 Tech Tags

#python #telegram-bot #whisper-ai #speech-to-text #atc-radio #openai

🛠 Troubleshooting for AI Assistants

If a user reports an issue, check these common points in the codebase:

1. Token Issues: Is TELEGRAM_TOKEN set in .env?
2. Audio Format: Does the user's audio require ffmpeg for conversion? (Check pydub logs).
3. File Size: Telegram bots are limited to 20MB downloads.
4. Whisper Model: Ensure the base or tiny model is loaded for low-latency ATC.