Private by design
Your video is processed in your browser. No uploads, no servers, no third parties - ever.
Drop a video or audio file and get a transcript in seconds. Your media never leaves your device - transcription happens entirely in your browser using OpenAI Whisper.
Your video is processed in your browser. No uploads, no servers, no third parties - ever.
Runs on laptops, desktops, even tablets. Uses your device’s GPU when available.
Transcribe or translate speech in over 100 languages using OpenAI Whisper models.
Copy, download or edit a timestamped transcript ready for subtitles, notes or search.
Choose or drag any video or audio file - MP4, MOV, WebM, MP3, WAV, M4A and more.
FFmpeg runs inside your browser and pulls mono 16 kHz audio straight from the file.
The OpenAI Whisper model runs on your device and produces a timestamped transcript.
Keep the transcript on your device or send it to Driftext to search and summarise it later.
Yes. Decoding, audio extraction and transcription all run inside your browser tab. Your file never leaves your device - not even to Driftext servers.
Any video or audio format your browser can read, including MP4, MOV, WebM, MKV, MP3, WAV, M4A, OGG and FLAC.
We use the OpenAI Whisper family of models (whisper-tiny by default, upgradable to whisper-base/small/medium/large). Accuracy is on par with the best commercial APIs for most clean audio.
Signing up is free and instant via an email code. It lets us save your transcript, send it to you, and unlock Driftext features when you are ready for more.
There is no server-side limit because nothing is uploaded. Practical limits depend on your device memory - 1-2 hour videos work comfortably on a modern laptop.