Speech to Text

Speech to Text offers two independent engines for the same goal. Real-time mode taps the Web Speech API — the SpeechRecognition interface built into modern browsers — and streams words onto the page as you talk: interim guesses first, then a finalized line once you pause. Audio File mode instead loads a Whisper AI model into your browser and transcribes a recording you already have, without listening to a microphone at all.

Reach for real-time dictation when you want to capture thoughts hands-free: meeting notes, a rough draft, or a quick memo you would rather speak than type. It shines during short, live sessions where seeing text appear immediately keeps you in flow.

Audio File mode is the better fit for material that already exists — an interview, a lecture, a voice memo, or the audio track of a video. Once the Whisper model has been downloaded, your browser keeps it, so repeated jobs start without another download, which suits long recordings and batches of files.

For live work, pick your spoken language from the dropdown, press Start Recording, and grant microphone access when the browser asks; your speech fills the transcript and you can edit it afterward. For a recording, switch to the Audio File tab, choose a model — Tiny for speed, Small for stronger multilingual accuracy — and drop in an MP3, WAV, MP4, or similar file. The first run tells you how much the model will download before you press Transcribe; when it finishes, the text is ready to copy or download.

Real-time recognition depends on the browser: Chrome, Edge, and Safari implement the Web Speech API, while Firefox does not, so use Audio File mode there. Recent Chrome versions can install an on-device language model, keeping microphone audio local; otherwise real-time speech is handled by the browser vendor's speech service. Both modes share one list of 22 choices covering 18 languages (English, Spanish, Portuguese, and Chinese each come in two regional variants), so choose the one you speak before you start: Audio File mode uses your choice instead of detecting the language, and ignores the region. Audio files accept common audio and video formats up to 500MB; for video, pulling the audio out first speeds things up and improves the result.