Incognito PrivoAI

Voice-to-text, AI chat, web translation, AI reading. Gemini API key or local AI — no backend, data stays in browser.

PrivoAI — a privacy-first, all-in-one AI toolbox. Built and maintained by one physician in his spare time — free, ad-free, no tracking, no subscription. ──────────────────────────────── 🆕 What's New (v28.8.0) ──────────────────────────────── ▶ Voice Notes, rebuilt with two modes Speech-to-text now lets you pick the right approach — fixing the occasional dropped words and disappearing text in the earlier live translation: • Basic Recording — records the whole session, then transcribes and translates it in one pass; the most reliable, nothing dropped (results appear after you stop) • Real-time transcription (Preview) — powered by Google's latest Gemini Live API, text appears as you speak, streaming an append-only transcript that never disappears (requires a Gemini API key with preview access) Both modes are lossless — choose reliability or real-time, whichever you prefer. ──────────────────────────────── ✨ Key Features ──────────────────────────────── 🌐 Webpage Translation (in-place / screenshot) What Chrome's built-in translation can't do: read bilingually, preserve journal and paper layouts, translate Kindle ebooks and comics, and translate any page with foreign-language images. One button picks the right method automatically. Layout, figures, math, and code stay untouched, and it translates as you scroll. Switch the target language anytime, choose which parts to translate (title / body / references…), or turn it off to restore the page. Specially tuned for complex single-page journal sites like Nature, JAMA, ScienceDirect, and arXiv — titles and body text translate correctly (including CJK titles). 🎙️ Voice Notes Record or upload audio and AI turns speech into text. Choose "Basic Recording" (records the whole session, then transcribes in one pass — most reliable, nothing dropped) or "Real-time transcription (Preview)" (powered by Gemini Live API, text appears as you speak). Auto-detects the language, handles mixed-language speech, and offers optional inline translation (original / translation columns). Uploaded files up to ~9.5 hours. Copy the transcript or send it to the Reader. Great for meetings, interviews, and multilingual notes. 💬 Incognito Chat A private Gemini chat window that leaves no record once closed. Four tabs for four models: • Gemini 3.1 Flash Lite — fastest, for everyday questions and translation • Gemini 3.5 Flash — balanced speed and quality, supports images and documents • Gemini 3.1 Pro (preview) — strongest reasoning, for deep analysis of long documents • Local model — connect Ollama / LM Studio for fully offline text chat Not sure which to pick? The default Flash Lite fits most cases. Supports 7 custom prompts. 🧰 Translation Workbench Paste text or upload an image screenshot for OCR and translation, optionally with an AI summary, opened in the Reader. 📖 Reader Turns cluttered pages into a clean, readable layout with click-to-translate paragraphs. Built-in read-aloud: pick a language and press play. Adjustable font size, line spacing, and background color. 🔊 AI Read-Aloud & Summary [Beta] Turn YouTube captions, audio files, webpages, or pasted text into natural speech or a spoken summary. Powered by Gemini TTS with a warm, steady tone; customizable reading instructions; WAV output. ──────────────────────────────── 🔒 Privacy by Design ──────────────────────────────── • No backend server: every AI request goes straight from your browser • No data collection: the developer never sees your input or output • Your key, your control: the Gemini API key stays on your machine — never uploaded or synced • Local AI support: text chat and translation can use Ollama / LM Studio, keeping data fully on-device ──────────────────────────────── 🌏 Multilingual Interface ──────────────────────────────── 13 interface languages: Traditional Chinese, English, Japanese, Korean, German, Spanish, Arabic (with RTL), Russian, Brazilian Portuguese, Turkish, Ukrainian, Vietnamese, Czech. ──────────────────────────────── 🚀 Getting Started ──────────────────────────────── 1. Install the extension 2. Get a free Gemini API key from Google AI Studio (aistudio.google.com) 3. Click the extension icon → Settings → paste your key 4. Start using it! Tip: Want to go fully offline? Switch to "Local model" in Settings and connect Ollama or LM Studio — text chat and translation need no Gemini key.