Google’s speech recognition browser tool helps children learn to read


Google has released a browser version of its Android app, Read Along, which offers digital picture books with tools to help kids learn to read. Kids can choose one of the hundreds of stories at different levels, read into the microphone, and watch as the site rates their performance. Words turn blue once read to help you find your place. If you mispronounce words completely, a red underline will appear to alert you to your problem. The read-along mascot Diya will appear on-screen to show you the correct pronunciation.

Previously Read Along 2019 was available in India under the name Bolo. The next year it was published worldwide as a read-along. Since then, Google says it has helped more than 30 million children read 120 million stories. It is available in ten languages: English, Portuguese, Spanish, Hindi, Marathi, Bengali, Tamil, Telugu, Gujarati and Urdu. The last six languages ​​are widely spoken in South Asia.

It should complement The product, aimed at learner readers ages five and up, isn’t branded as a comprehensive replacement for human teachers or the connection to parents. Instead, it can help fill in the gaps when one-to-one adult classes aren’t available.


The Google team is interested in making the service fun for children. “In addition to the website launch, we are also adding some brand new stories. We’ve partnered with two well-known YouTube content creators, ChuChu TV and USP Studios, to convert some of their popular videos into a storybook format,” reads a post.

The difference between this and the existing app — It is more suitable for use in schools that may have computer labs. Unlike the app, the browser version does not support offline use. The browser version also requires a Google account to sign in, which can track kids’ progress and provide in-game incentives. But otherwise, the browser version is similar to the Android app. And both the app and the web version process speech recognition locally instead of sending speech data to servers.


Comments are closed.