EasySTT — Speech to Text made simple!

Get EasySTT

Install from the product page or load the extension manually during development.

From Chrome Web Store

Visit the Chrome App Store to get EasySTT for your browser.

Go to Chrome App Store

Manual install (developer mode)

Open chrome://extensions in Chrome.
Enable Developer mode (top-right).
Click Load unpacked and select the EasySTT folder.
Pin the extension and click its icon to open the UI.

Why EasySTT

Designed for meetings, study, and productivity. Minimal UI, powerful engines, and privacy-first by default.

Real‑time transcription

See words appear as you speak. Copy text instantly when you stop.

Microphone + System audio

Transcribe your mic, your computer’s audio, or both (screen share with “Share audio”).

Local processing

Audio is processed in your browser. No accounts, no cloud by default.

Two engines

Use Whisper AI (WASM/WebGPU) for accuracy and system audio, or Web Speech API for lightweight mic-only.

Fast and simple UI

Clean layout, one-click start, theme toggle, and editable results area.

Privacy‑first

Minimal permissions and no tracking. Your words stay on your device.

How it works

1
Pick your engine

Whisper AI for system audio support and accuracy, or Web Speech API for quick mic-only.
2
Select audio source

Microphone, Computer audio, or Both. Enable “Share audio” in the picker for system sound.
3
Start listening

Click the mic, speak or play audio, and watch text appear in real-time.
4
Copy and use

Edit the text area, copy with Ctrl/Cmd+C, and paste anywhere.

Screenshots

EasySTT interface screenshot — Main interface with toolbar, live transcription, and settings.

Privacy Policy

Effective date:

EasySTT is designed to process speech locally in your browser. We minimize permissions and do not collect, store, or sell personal data.

Data processing

Audio input (microphone and/or system audio) is captured only when you click Start.
When using Web Speech API, recognition is handled by the browser’s built-in engine (mic-only).
When using Whisper AI, models run locally via WebAssembly/WebGPU. The first run may download a pre-trained model to your browser cache from a model host.
No account is required. Transcripts remain in the page until you copy or clear them.

Permissions we use

Microphone access to capture your voice when you opt in.
Display capture (with “Share audio”) to capture system audio when you select Computer audio or Both.
Storage to remember your preferences (theme, language, engine, etc.).
Context menus to provide quick actions (if enabled by the extension).

What we don’t do

No analytics, tracking pixels, or third‑party ads.
No cloud upload of your audio or transcripts by default.
No background recording—capture starts only when you click.

Third‑party components

EasySTT may leverage browser technologies such as Web Speech API, WebAssembly, WebGPU, and ONNX Runtime Web to run models locally. Model files may be fetched from a trusted host on first use and cached by your browser.

Children’s privacy

EasySTT is intended for general productivity use and is not directed to children. Do not use the extension where applicable laws restrict consent.

Updates

We may update this policy as features evolve. Material changes will be reflected on this page.

Contact

Questions or requests? Open an issue on the Chrome Web Store page.

FAQ

Does EasySTT work offline?

Yes, after the initial model download for Whisper AI is cached by your browser, many features continue to work offline.

Can I capture system audio?

Yes—choose Computer audio or Both and select a screen/tab with “Share audio” enabled. This requires the Whisper AI engine.

Is my audio sent to a server?

By default, no. Audio is processed locally in the browser. Your browser may download models on first use, but transcripts aren’t uploaded by EasySTT.

Which languages are supported?

Languages depend on the selected engine. Whisper supports many languages; Web Speech API support varies by browser/OS.