Transform Speech into Text with AI Precision
Multi-Source Input
Microphone, audio/video files, YouTube, TikTok & Instagram
AI Processing
Gemini API powered transcription & correction
Secure & Private
Local processing & secure API key handling
Supported Platforms
YouTube
Public & private videos (requires credentials if private)
TikTok
Video & audio extraction
Stories & Reels support (requires credentials)
Get Started in 3 Steps
1
Install Requirements
pip install -r requirements.txt
2
Configure API
Set your Gemini API key in config.py
3
Start Transcribing
python main.py