Transcriber

Record yourself or pick a file, and get the text back. Your audio never leaves your device.

Open full screen First run downloads a 40–250 MB speech model. Fastest in desktop Chrome or Edge.

Output

Detects the language and can translate to English. Saves plain text or .srt and .vtt subtitles.

Built with

Plain HTML, CSS and JavaScript, with OpenAI’s open Whisper model running through Transformers.js on WebGPU or WebAssembly.

To do

Live text while you speak, word-level timestamps, and telling speakers apart.