Skimlane
Free · Open source
Researchers and analysts needing consistent page structures
Browser reading modes strip ads but leave you fighting PDFs, losing your place in long articles, and sending text through a cloud API you'd rather not trust with private research. This extension runs the full stack — extraction, summarization, and text-to-speech — entirely on your device.
The extension processes web articles and PDFs through a local readability pipeline, strips clutter, highlights sentences as they're read aloud, and stores documents in an on-device library with semantic search. No external API calls means no data leaves the browser. The sentence-level TTS highlighting keeps you oriented in long-form content where cloud read-aloud tools often lose sync. The library persists processed documents and lets you export paginated PDFs. Where it breaks: the on-device model footprint limits summarization quality compared to hosted LLMs, and users needing cross-device sync or team-shared libraries find nothing here for them.
Bottom line: Pick this for private, offline research reading on a single machine; plan a different setup when your team needs shared annotations, cloud sync, or summarization quality that on-device models can't yet match.
Find your fit
More options in Summarizers. Compare pricing, platforms, and features side by side.
Free · Open source
Researchers and analysts needing consistent page structures
Free · Open source
Self-hosted homelab users
The extension installs as a Manifest V3 browser extension, no account or server required. When you open a cluttered article or PDF, it extracts the readable content, renders it in a clean view, and optionally runs an on-device summarization pass. Text-to-speech plays back with sentence-by-sentence highlighting so you can follow along without losing your place — a meaningful difference from tab-switching to a separate reader or copy-pasting into a TTS tool. Processed documents land in a local library with semantic search powered by on-device embeddings.
The defining architectural choice is full locality. Every step — extraction, embedding, summarization, TTS — runs inside the browser with bundled models. The source includes a dedicated embedding worker, a TTS worker, and a YOLO-based layout model for PDFs, according to the repository file structure. For researchers handling sensitive documents, that means no terms-of-service review of what a cloud vendor does with your text. It also means the tool works offline once installed.
This fits a solo researcher or privacy-focused individual who reads heavily on the web and wants one place to capture, listen to, and search that reading — all without touching a server. It does not fit teams: there is no sharing layer, no sync across machines, and no collaboration on annotations. The on-device summarization model, while functional, produces shorter and less nuanced summaries than hosted alternatives — teams with a high quality bar for summarization will hit that ceiling quickly and move to a pipeline that calls an external LLM. The tool is free and open-source with no paid tier gating any feature.
PDF handling uses PDF.js under the hood alongside the YOLO layout model, which means mathematical content gets a render pass through KaTeX and tables get OCR treatment, according to the repository’s file listing. YouTube transcripts are also supported via a dedicated module. Export produces paginated PDFs, so content captured for later reference can leave the library in a portable format.
Sign in to rate this tool or suggest an edit.