Timber (iOS) and Timber Tabs (Mac) – best offline read-aloud LLMs
Timber reads any article, book, PDF, or pasted text aloud in natural voices — 324+ free, across 71 languages, all on your iPhone. Built by a teacher. Free on the App Store.
In plain words
Timber is a free iOS app that reads articles, books, PDFs, and pasted text aloud using natural voices available offline on your device. It offers 324+ free voices across 71 languages, requires no account or subscription, and processes all content locally without sending data to external servers. Built by a teacher, it addresses accessibility needs for users who struggle with reading.
written from the facts on this page · September 2026
From the sources
Timber reads any article, book, PDF, or pasted text aloud, in natural voices that live on your iPhone. A teacher built it after watching a student struggle to read a page. No account, nothing to buy to start — and not one word of it sent to us. Timber reads any article, book, PDF, or pasted text aloud in natural voices on your iPhone. No account, nothing to buy — and not one word sent to us. “A young child asked me about the news — then struggled to read the article we pulled up. So I built the app I always wanted: the best free vocal reader for iOS.” Timber Tabs gathers the pile of tabs you keep meaning to read, groups them by site, and pre-selects the ones…from timberreader.com
Does the same job
all alternatives →
More commerce this month
the category →
Compare your startup equity grant for free.
Commerce · 26d ago · equitybee.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com