Burn captions on a silent product video with authored cues

A silent clip fails Sume captioning with caption_no_speech. Pass cues or segments with text, start and end to burn your own copy, no transcription step.

5 min readSume
All posts

If a product video has no speech, Sume's caption job fails as caption_no_speech, and the response points to next_action: use_overlay_captions. Pass cues (or segments) with text, start and end in seconds, and Sume burns exactly that copy at those times without running speech-to-text. See Video captions.

The two paths

Authored overlay is the right path for silent product loops, label callouts and price-free feature text.

Caption inputs, from the Sume docs (read 2026-10-03).
You passNeeds speech?Result
video_url onlyYesSpeech-to-text captions
script_textYesScript aligned to speech
cues or segmentsNoYour overlay copy, as written
wordsNoWord-level copy at your timings

Write the cues

Keep each cue short enough to read in its window. Choose a style explicitly (slam, punch, tiktok-green or korean-ad), or omit it and the wording decides: slam for Latin text.

Restyle without rebuilding

A later restyle can pass source_caption_id instead of video_url, which reuses the source video and its timings.

Sources

Related posts

More in Use cases

All Use cases posts

Written by Sume