← All audio tools

Speech to Text

Transcribe audio

Drop a recording, run Whisper locally, then copy the transcript or download subtitles.

Runs in your browser. Your audio stays on this device — nothing is uploaded to BrowserSpaces for processing.

Whisper tiny

Compact model cached after first use.

Subtitles

SRT and VTT export.

Languages

English-only or multilingual model.

Private

Audio is not uploaded to BrowserSpaces.

Use the tool

First load downloads Whisper (~40MB, q8) from Hugging Face and caches it. Your audio is decoded and transcribed in this tab — not uploaded to BrowserSpaces.

Model

Load Whisper, then drop an audio file.

How it works

Decode, then Whisper

Audio is resampled to 16 kHz mono and transcribed with Transformers.js Whisper — identical to the AI Speech to Text tool.

Three steps

  1. 1

    Load Whisper

    One-time model download.

  2. 2

    Add audio

    Pick a clip.

  3. 3

    Export

    TXT, SRT, or VTT.