You think out loud. ThinkAloud writes it down.
Hit record and just talk: a passing idea, a meeting, a whole lecture. When you stop, you can play the recording back and decide whether it's worth keeping before anything happens to it. Only then does the on-device AI turn it into a real note, with a title, some structure, tags, and links to the related notes you already have.
Here's the part that matters. All of this happens on your phone. ThinkAloud runs Google's Gemma model locally, so your voice and your notes never get uploaded anywhere. There's no account to create, no server in the middle, and nothing to pay every month. You download the model once, and after that it works offline.
Your notes are just Markdown files in an ordinary folder, the same format Obsidian uses. Point ThinkAloud at a vault you already have, or let it keep one for you. Either way you can open, edit, or back them up with any app you like. Nothing is trapped inside.
What it's good at:
- Voice, photos, or quick text go in; clean, tagged notes come out
- Ask your notes a question in plain language and get an answer with its sources listed, so you can tap straight through to where each fact came from
- A knowledge graph that builds itself as your notes start linking up
- Full-text search, tags, folders, and checklists
- Optional sync to your own Google Drive or iCloud. Your account, a private folder, no servers of mine in between.
No ads, no analytics, no tracking, no accounts. I made ThinkAloud because I wanted a notebook that was actually mine. That's the whole idea.
The on-device model needs around 3 GB of free space and a fairly recent device.
평가 및 리뷰
이 앱은 개요를 표시할 만큼 충분한 리뷰 또는 평가를 받지 않았습니다.
Transcription in 25 languages
The on-device speech engine now understands 25 European languages and detects which one you're speaking. No setting to change, and everything still runs privately on your device.
Search in any language
Notes written in Cyrillic, Greek, accented Latin or CJK scripts are now indexed properly, so search and Ask can find them.
Smarter Ask
Ask now surfaces the right note even when your question shares no keywords with it.
A faster, steadier AI engine
The on-device AI runtime has been updated, bringing fixes for stalls during long recordings and for garbled output on some graphics chips.
Already have the speech models?
They keep working. Settings shows an Update button when the multilingual models are available. The old ones are removed only after the new set has fully downloaded.
Also in this release
• Reclaim space from interrupted downloads in Settings
• Smaller app: the semantic search index is a quarter of its previous size
• Screen-reader labels for retrieval settings, better contrast, and layouts that hold up at large text sizes
• Clearer messages when a recording segment can't be transcribed
버전 1.2.0
Ghanashyam Vinod Tatti 개발자가 아래 설명된 데이터 처리 방식이 앱의 개인정보 처리방침에 포함되어 있을 수 있다고 표시했습니다. 자세한 내용은 개발자의 개인정보 처리방침 을 참조하십시오.
데이터가 수집되지 않음
개발자가 이 앱에서 데이터를 수집하지 않습니다.
개인정보 처리방침은 사용하는 기능이나 사용자의 나이 등에 따라 달라질 수 있습니다. 더 알아보기
