whisper webCLI

offline-first 100% local. Audio never leaves your browser. Fork on GitHub
Engine ready · the selected model downloads on your first transcription, then runs fully offline.
Step 1 · Select Audio or Video
File No file selected
Size -
Duration -
Step 2 · Configure

Larger = more accurate, slower, more RAM.

Auto-detect, or pick explicitly.

Whisper can translate non-English audio to English.

Advanced Settings

0 = deterministic, 1 = more creative.

Higher = slower but more accurate.

Process multiple files sequentially.

Affects transcript export format.

Supported: --language, --beam-size, --temperature, --translate, --model. One per line or space-separated.

First transcription downloads the model (~39–244 MB depending on selection).

About

whisper webCLI is a privacy-preserving browser application that runs OpenAI's Whisper speech-recognition model entirely on your device via Transformers.js and ONNX. No audio is uploaded anywhere. It is the second tool in the webCLI family, alongside ffmpeg-webCLI.

GitHub · Transformers.js · OpenAI Whisper