What’s new in Tagbox / automated video & audio transcripts

Our team is passionate about using state-of-the-art AI in a way that's both cool and extremely useful.

This month, we've been focusing on video and audio, together with some other treats:

‍

Automated transcription

Tagbox is great with images, but more and more of you have been asking about video & audio support.

Two months ago, OpenAI released their latest innovation, Whisper - a tool for automatically transcribing in 99 languages (!), at a never-before-seen accuracy rate.

We jumped on the opportunity, and integrated it into our upload flow - so that any video or audio you upload will have fully-searchable transcription.

You can see the transcript in the item preview screen (see image below).

Note that even the smartest machines take time - the transcript will be added within an hour after uploading. For a list of supported languages, see our help center article.

‍

‍

Tile view and infinite scroll

Many of you told us you weren't fans of the boxy, Google-Drive-looking main view of the app. You wanted to see the entire image in a beautiful, Pinterest-like view. Also, what was with that "load more" button - that's so 2005, right?

We hear you, loud and clear. Say hello to our new Tile View. Spare us the "I told you so" - you were right, as always.

We do our best to keep our UI clean and simple, so we've replaced our main view with this new one. Miss the old one and would like to have the option to choose? Let us know at hello@tagbox.io.

‍

‍

Up next

We're currently working on face recognition - allowing you to quickly search for all of the images/videos with a specific person in them.

Have any ideas or thoughts to share? We'd love to hear from you at hello@tagbox.io.

Looking to try tagbox.io for the first time? Start here.