Read anything aloud, pick a voice, and save an MP3 — works with no internet (except image OCR).
📄 File
📝 Paste text
🖼️ Image / Screenshot
Drag & drop a document — or click to choose
.docx.pdf.txt.md.html
Drop an image / screenshot — or click to choose
Reads text out of a picture (OCR). Needs internet the first time per language. .png.jpg
Get a free key at aistudio.google.com/apikey (no credit card).
The image is sent to Google Gemini to read it — needs internet. Don’t use AI extract on confidential images.
Tip: select any text below and a “Read” button pops up. Click a sentence to start there.
Your text will appear here…
READ‑ANYWHERE ON YOUR SCREEN
• Screenshot → Image tab: capture any app/window and drop it above — OCR reads it.
• Bookmarklet: drag the purple button to your bookmarks bar; then on any web page, select text and click it to hear it.
Show the bookmarks bar with Cmd‑Shift‑B if hidden.
Notes. Reading files, the System voice, the Downloadable voice and MP3 export all work fully offline.
Only image OCR needs internet the first time each language is used (to fetch that language pack). The Downloadable voice sounds more synthetic than the System voice — that’s the trade‑off for being savable.
Everything runs on your device. Nothing is uploaded.