Edits bilingual captions vs Sume: language is only a STT hint
Edits translates captions into a second language. In Sume video captions, language only hints speech-to-text, so a second line comes from your own cues.

Setting language on a Sume caption job does not translate anything. The docs define it as a speech-to-text hint (ko, en, and so on), with automatic detection when omitted. If you want a second-language line like the one Edits generates, you write that text yourself and send it as authored cues.
Edits is from Instagram's creators blog; Sume behavior is from Video captions, read 2026-10-01.
What do Edits bilingual captions do?
Instagram says Edits translates your captions automatically into a secondary language, in 15 languages: English, Spanish, Portuguese, Hindi, Korean, Japanese, French, German, Indonesian, Russian, Gujarati, Bengali, Italian, Thai and Kannada. You tap Captions, then Bilingual captions, choose the language and tap Generate captions.
What does language do in Sume captions?
| Field | Meaning in the docs |
|---|---|
language | Speech-to-text hint; omit for automatic detection. Never selects the style or font |
style | Picks the look and motion, for example slam or punch |
script_text | Aligns burned-in wording to your script |
cues / segments | Authored overlay with text, start, end; skips speech-to-text |
How do I add a second-language line?
Translate the lines with whatever you trust, then send them as cues with text, start and end in seconds. The docs say this burns exactly that copy at those times with no second speech-to-text run. script_text, words, cues and segments are mutually exclusive, so pick one. The walkthrough is in add bilingual subtitles to video.
Does the language field choose a Hangul font?
No. The docs say a style you name is rendered as named, and that an omitted style follows the wording, with Korean copy resolving to black-outline. Choose style and font deliberately for Korean text.
Sources
Related posts
More in Use cases
- Extract audio from an Instagram video: Sume audio detach for intros
Edits can extract audio from a video and save it for later projects. In an API workflow, Sume audio detach returns the track as a new wav or mp3 artifact.
- Edits lyrics captions vs Sume video captions with script_text
Edits generates lyrics from a selected track and styles them as captions. With Sume you supply the lyric text as script_text and choose a caption style.
- Instagram carousel originality rule: make slides with n
Instagram now applies its originality rules to photos and carousels. Create your own slides: ask for several images per call with n, at 4:5 for portrait.
- iPhone 18 Pro screenshot size: 1206x2622 and 1179x2556
iPhone 18 Pro screenshots (6.3-inch) are 1179x2556 or 1206x2622. Neither fits Sume's multiple-of-16 image rule or its 2160 Timeline edge cap.
Written by Sume