3 items
Reads any web page aloud in a natural voice, highlighting each sentence as it goes. Runs fully on your device. Chickadee reads any web page aloud in a natural, human-sounding voice, and it does it entirely on your own computer. Nothing you read is ever uploaded, and there is no account, no subscription and no API key. Open an article and press Alt+R, or click the Chickadee button, and it starts reading from the top, highlighting each sentence on the page itself as it goes. Right-click any word and choose "Read aloud from here" to start partway through. A small floating bar lets you pause, step back and forth between sentences, and change the speed from 0.9x to 2x. Alt+P plays and pauses. Most read-aloud tools send your page text to a server to generate the speech. Chickadee runs the Kokoro speech model directly in your browser using WebGPU, so the words never leave your machine. There are twelve voices to choose from, American and British, and the one you pick is remembered. The first time you use it, Chickadee downloads the voice model once (about 310 MB). After that it works offline: on a plane, in a tunnel, anywhere. It needs a Chrome-based browser with WebGPU support on reasonably recent hardware, and it checks on first run and tells you plainly if your machine can't run it. Chickadee collects nothing and sends nothing. No analytics, no telemetry, no server. It is open source under the Apache 2.0 licence: https://github.com/sahilmahendrakar/chickadee
Sep 6, 2026
rating_count is the Chrome Web Store ratings count, not a written-review count.
Media assets
Screenshots and videos on the listing.
Has promo video
Whether the listing includes at least one video.
Languages
Declared language locales.
Developer website
Listing exposes a developer website URL.
Contact email
Listing exposes a contact email.
Keyword in name
Case-insensitive substring match in the name.
Keyword in description
Case-insensitive substring match in the description.
Keyword occurrences in description
Count of case-insensitive occurrences in the description.
Category user-count percentile
Share of same-category extensions with fewer users (null if unknown).
These are transparent listing completeness / keyword signals, not a prediction of Chrome Web Store search ranking.