With several previous reports hinting at a testing phase of this all-new feature, Instagram, on Tuesday, officially introduced auto-captions for stories that will essentially transcribe speech in videos. The sticker is now available in โ€œEnglish and English-speaking countriesโ€ and will soon roll out to other languages and countries.ย 


โ€œNow you can add a captions sticker in Stories (coming soon to Reels) that automatically turns what you say into text. Weโ€™re starting in a handful of countries and hope to expand soon,โ€ Instagram stated in a tweet, formally announcing the interesting new feature. The company also mentioned that it will start testing automated captions in Reels soon.

As reported by The Verge, thereโ€™s no option to highlight text in captions but you can still use the drawing tool or sticker behind the text. This feature is expected to get popular, and itโ€™s also helpful for people with hearing disabilities. Like other text options in Stories, users can adjust the style and color of the captions after theyโ€™re generated. People can also edit individual words in the captions to correct spelling, punctuation, or any words that werenโ€™t transcribed accurately. Auto captions rarely have perfect accuracy, especially for people with accents or atypical speech, so editing is crucial. Thereโ€™s currently no option to have the text highlighted for better visual contrast, but you can use the Draw tool or a sticker behind the captions to make them easier to see.

Source: CNET

To use the feature, creators will first record a new video using the Stories or Reels Camera in the Instagram app, or select a video to upload from their phoneโ€™s gallery. Then, youโ€™ll open the sticker tray and look for the new โ€œCaptionsโ€ sticker, which will convert your speech to text. You also can edit the style, position of the caption and the text and color so it matches your content. When you post, the captions will appear alongside your video for everyone to see.

Just weeks ago, TikTok also added an auto-caption feature in which the feature automatically translates the speech from a TikTok video in either American English and Japanese, but the text itself isnโ€™t customizable and can be turned on or off by the viewer from the appโ€™s share panel.




Rhea Sovani

Author Rhea Sovani

More posts by Rhea Sovani

Leave a Reply