WorkspaceAudio — speech and voice
Whisper (speech to text) and Kokoro (text to speech) run entirely in your browser — no external services.
Dictate or upload an audio file — Whisper recognition runs entirely in your browser, the audio never leaves your computer. On first use a model (~80 MB) is downloaded and cached by the browser.
Drop an audio file here or click to browse
MP3, WAV, OGG, M4A, WebM · up to 25 MB · recording up to 5 min