Help
Nova Transcribe is a free tool that transcribes audio and video right in your browser. The AI model (Whisper) is downloaded to your browser and runs on your own device, so your audio is never uploaded anywhere.
How to use
Load an audio or video file, choose the accuracy (standard or light) and the language, then press Transcribe. The result appears with timestamps — click one to play from that point. Once you have fixed the text, export it as SRT, VTT, or plain text. The first run downloads a few dozen megabytes for the model, and transcription takes roughly a quarter of the audio's length.
Open Nova Transcribe →The audio and video you load are never sent to a server. All transcription happens inside your browser.
Read the privacy policy →