Audio & video to text & summary — automatic speech transcription, key point extraction, and speech cleanup

Speech language:

Model:

📂

Or select any audio / video file (OGG, MP3, WAV, FLAC, M4A, MP4, WebM)

Lecture, meeting, or voice recording is processed directly on your device.

The first transcription downloads the selected offline Whisper model once, then it is cached. Your file never leaves your device.

📖 Vocabulary of specific terms and names (optional)

List specific terms, names, or titles from the audio separated by commas. The AI will actively 'listen out' for this list, significantly increasing the chance of recognizing them correctly.