Does this transcribe text visible on screen?
No. It transcribes speech from the video soundtrack; it does not perform OCR on frames.
Transcribe a video soundtrack locally and export timestamped text.
Transcribe a video soundtrack locally and export timestamped text.
Supported formats and codecs depend on your browser and source file.
Choose a local video file with a clear audio track.
Wait for the local Whisper model to load if this is the first run.
Transcribe the soundtrack and save the timestamped text.
Create a text transcript from speech in a local video without sending the video to a server.
No. It transcribes speech from the video soundtrack; it does not perform OCR on frames.
Background noise, overlapping speakers, accents, and low volume can reduce transcription accuracy.
No. The audio is processed by the model in your browser.