Recommended Free Tools
iTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
Chad Vocab is a self-hosted vocabulary trainer demonstrated for English-to-Polish practice. Its creator, Allan Dorr, describes a workflow that combines typed or spoken answers, local Gemma assistance, and photo-based vocabulary suggestions that learners review before adding to a deck. The October 4, 2026 project article presents these as features of a demonstration—not independently tested results.
What Chad Vocab does
Dorr describes building Chad Vocab for a friend learning Polish. The learner practices with a cue in one language and supplies the answer in another; the showcased deck runs from English cues to Polish answers. The author says users can add other language pairs and decks.
The project is intended to bring several parts of vocabulary study into one self-hosted practice loop: answering cards, getting help with near-miss responses, speaking answers, and turning photographed textbook material into proposed vocabulary pairs.
Outdated Drivers Are Slowing You Down
One free scan finds every outdated or missing driver and matches the right update for your exact hardware.Free scan · exact hardware matchPC Slower Than It Used to Be?
A free scan shows the junk files, broken settings and background clutter dragging Windows down - then fixes them in one click.Free scan · Windows 10 & 11How a practice session works
Type an answer and get help with near misses
A learner types a response to a vocabulary cue. According to the project article, Gemma evaluates near-miss answers, rather than limiting practice to a strict exact-match check. The article does not report an accuracy study or explain how the app handles every kind of spelling, grammar, or translation variation.
#1 Best Overall
Speak an answer
The described setup uses local Scriberr/Whisper as its speech-to-text path. The article also describes ElevenLabs Scribe as an optional alternative when the user supplies an API key. In other words, the local speech-recognition route is the stated fallback; the optional service is not presented as a requirement for the core practice flow.
Make draft cards from a textbook photo
Gemma vision can propose vocabulary pairs from a photo of a textbook page. The learner reviews the proposals before importing them into a deck. That review step matters: the feature produces suggestions, not a guarantee that every extracted word or pair is correct.
Practice cards in a priority queue
The author says the queue puts cards needing practice first, makes learned cards rare, and mixes the last five cards with review. The article describes this as the project’s review behavior; it does not provide measured evidence that the queue improves retention.
Free tools Windows power users keep installed
One-click scans. No signup required.
What the reported setup requires
The project article names Vite and React for the interface, Hono for the API, and SQLite for storage. Its quick-start list calls for Node.js 20 or later, local Scriberr, and LM Studio with an open model loaded. Photo import requires a vision-capable Gemma model, according to the author.
These are article-reported setup details, not verified build instructions. The linked repository was not available for code-level verification, so check the project’s current source and documentation before relying on a particular installation process or dependency version.
- Software: Node.js 20+, Scriberr, and LM Studio with a model loaded, as listed in the article.
- For photo import: A vision-capable Gemma model.
- Hardware: The article mentions a household laptop but specifies no validated minimum for memory, graphics, processor, or other hardware.
Privacy: local by design, not independently audited
Dorr’s stated goal is to keep speech and textbook photos on a household laptop and avoid requiring a paid cloud model for the core practice flow. The article reports that the demonstration app was exposed through a Cloudflare Tunnel while LM Studio and Scriberr remained on localhost.
This describes the author’s intended and reported arrangement, not a security audit or a guarantee that every deployment keeps all data local. The optional ElevenLabs speech service is an external processing route, so users who choose it should account for that difference when deciding how to handle audio. The article does not independently verify data flows, tunnel configuration, or security properties.
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
What to weigh before trying it
- Setup effort: This is a self-hosted project with several named software dependencies, rather than a ready-made hosted trainer.
- Model capability: Photo-based suggestions depend on having a vision-capable Gemma model; ordinary text-model capability alone is not enough for that feature.
- Speech path: Local Scriberr/Whisper is the described fallback. The optional API-key route adds an external service to the setup.
- Speed: Dorr comments that local recognition felt slower than a phone app in their experience, including when using the optional API. No controlled benchmark or timing data is supplied, so this is an anecdote, not a general performance result.
- Learning evidence: The article describes the feature design but provides no measured learning outcomes or comparative accuracy study.
Project status and license claims
The project article identifies Chad Vocab as MIT licensed and says the source would remain open even if a hosted offering were developed later. Because the repository and license text were not independently checked, treat that as the author’s article-reported description rather than a verified statement about the repository’s current state. The article is dated October 4, 2026, and the demo’s availability or setup may change.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
