Edits lyrics captions vs Sume video captions with script_text

Edits writes the lyrics for you from the track on your timeline. With Sume's video captions you bring the words: pass your lyric text as script_text, and Sume aligns the burned-in wording to it using speech-to-text timings.

Edits is from Instagram's creators blog; Sume behavior is from Video captions and Music 1.0, read 2026-10-01.

How does Edits make lyric captions?

Instagram says you add music to your timeline, tap Captions and select Lyrics, and Edits generates the lyrics from the selected track. They are styled like any other caption.

How does script_text work in Sume?

When script_text is provided, Sume keeps speech-to-text word timings as the timing source and aligns burned-in wording to your script. Speech-to-captions needs audible speech; a silent clip fails as caption_no_speech. Alignment can fail with script_alignment_mismatch or script_alignment_failed, and the suggested next action is to simplify script_text or omit it to burn the speech-to-text wording instead. The docs do not say how well timing holds on sung vocals, so test your track.

Which caption styles can I pick?

Can I use lyrics returned by a Sume music job?

Treat them with care. The Music 1.0 docs say provider lyrics may describe tempo and structure and that this is model-reported metadata, not an audio measurement. For a finished song, supply the text you own or wrote. A fuller build is in AI lyric video maker.