Tap the microphone to start transcribing
Your speech will appear here in real-time
Drag & drop audio file here
or click to browse
Supports: MP3, WAV, M4A, WebM, OGG, FLAC
Connecting to Whisper server...
Run py whisper_server.py first
To transcribe audio files, you need to run a local server. Follow these steps once:
Open Command Prompt and run:
winget install ffmpeg
Mac: brew install ffmpeg
pip install flask flask-cors openai-whisper
This may take a few minutes
Click here to view → Click "Raw" → Save as whisper_server.py
py whisper_server.py
Keep this window open while using file upload
Once the server shows "Running on http://localhost:5000", come back here and upload your file!
You have an unsaved audio recording.
Would you like to save it?
You have a transcript from a previous session.
Would you like to continue or start fresh?