Auris Reader features
Three adaptive engines.
One quiet reader.
Auris Reader is a text-to-speech EPUB and PDF reader with real-time contextual translation — built around three engines that adapt to every document you open.
Available for Windows and Linux. Android coming soon.
Adaptive engine 01
Adaptive Predictive Pipeline
Speech that flows. The pause between sentences disappears.
Most text-to-speech readers synthesize one sentence at a time: the voice stops, the next request goes out, and you hear the seam. Over a chapter, those gaps add up to listening fatigue.
Auris Reader measures two speeds — how fast the voice engine generates audio and how fast you are listening — and pre-generates the next sentences in the background. The buffer grows and shrinks on its own, so the reading keeps flowing through long paragraphs, dialogue and footnotes alike. There is no setting to configure.
- The next 3–5 sentences are buffered before you need them
- Speed changes apply instantly, without pitch artifacts
- Your reading position is remembered per book, across sessions
Adaptive engine 02
Contextual Translation Memory
Translation that remembers who is who.
Translate a novel sentence by sentence and the cracks show fast: a character called Hope becomes the word “hope”, technical terms drift between synonyms, pronouns lose their owner. Generic translators have no memory of the page before.
Auris Reader translates with a sliding context window and a per-book glossary of entities. Character names, places and recurring technical terms are detected once and kept consistent for the rest of the book — chapter after chapter. Translation runs alongside the voice, so you can listen in one language while reading in another.
- Sliding context window across sentences and paragraphs
- Persistent per-book glossary of names and terms
- 50+ languages online today; downloadable offline packs arrive in 2026
Adaptive engine 03
Adaptive PDF Content Detection
PDFs without the noise.
Academic papers and technical PDFs are full of things you never want to hear: running headers, page numbers, watermarks, URLs, column breaks mid-sentence. Ordinary readers speak all of it.
Auris Reader analyzes the layout of each document and builds a per-document profile of what is content and what is furniture. Headers and footers are filtered, multi-column text is read in the right order, footnotes are re-ordered so they stop interrupting sentences, and broken hyphenation is repaired before the voice reaches it. In our tests, fixed filtering rules top out around 80% on real-world PDFs; the adaptive per-document profile reaches about 95%.
- Multi-column scientific papers read in reading order
- Footnote and caption re-ordering on the fly
- Hyphenation and line-break repair
And around the engines
Everything a daily reader needs.
Voices and languages
Over 300 neural voices across 50+ languages. Spanish is ready out of the box with Spain and Mexico accents; pick the voice, and the reading follows your language.
- Adjustable speed, pitch and pause length
- Offline fallback voice on Windows
- More languages rolling out throughout 2026
Reading experience
The highlight follows the voice word by word, so your eyes can follow along or rest. Open a book and you are back on the exact sentence where you stopped.
- Synced highlight while the voice reads
- EPUB 2/3 and PDF, including multi-column scientific
- Per-book position memory
Private by design
Your books stay on your device. The app does not track what you read, and your account exists only to manage your plan and your devices.
- Library and reading history stay local
- No ads, no data sales
- Windows 10/11 and Linux (.deb)
Hear your next book.
Start a 14-day free trial and put the three engines to work on your own shelf. Cancel anytime before day 15 and you pay nothing.
14-day free trial · Cancel anytime · Windows and Linux