Caption a 45-second reel for 20 cents: script_text or speech-to-text
A standalone Sume caption job is $0.20 for a clip up to 60 seconds, so a 45-second reel is 20 cents. Send script_text to keep your exact wording.
The price and the call
Each accepted standalone caption job reserves and captures $0.20 for videos up to 60 seconds, so a 45-second reel costs 20 cents. You send a public HTTPS video_url to POST /v1/video-captions and get a captioned video back. The docs say to confirm the live price in GET /v1/catalog.
Two ways to get the words
With no text sent, Sume runs speech-to-text and burns what it hears. With script_text, Sume keeps the speech-to-text word timings as the source of time and aligns the burned-in text to your script, so brand names and spellings come out as you wrote them. Alignment can fail with typed public job errors, so check the docs list before relying on it in automation.
If the clip has no audible speech, the job fails with caption_no_speech and next_action use_overlay_captions. That is not a policy rejection.
| Input you send | Speech-to-text runs? | Cost |
|---|---|---|
| Only video_url | Yes | $0.20 |
| video_url plus script_text | Yes, for timing; text aligned to your script | $0.20 |
| video_url plus words, cues or segments | No | $0.20 |
| source_caption_id (restyle) | No, reuses timings | $0.20 |
Budget for a weekly batch
Ten reels a week is 10 x $0.20 = $2.00 for captions; 52 weeks is $104. Clips over 60 seconds are outside the fixed estimate, so check the live catalog price for longer cuts. Only one of script_text, words, cues and segments may be sent per request.
Reference: Video captions.
Source video requirements
The video_url must be a public HTTPS URL. Put the finished edit there, since captions are burned in and cannot be removed later. If you plan to change the edit after captioning, wait: a new edit means a new caption job at $0.20.
The create call accepts the usual mode, webhook_url and wait_timeout_seconds fields, and you read the captioned video_url and artifacts when the job finishes.
Choosing between STT and script
If your reel is a voice-over from a known script, send script_text. You keep exact punctuation and spelling, and timing still comes from the audio. If the speaker ad-libs or the script changed during editing, let speech-to-text run and correct specific words afterwards with a restyle that sends words, which keeps the price at the same $0.20 per render.
Sources
More in Media tools
- Caption a 75-second clip: the $0.20 estimate is for 60 seconds
Sume's standalone caption job lists $0.20 for videos up to 60 seconds. For a 75-second clip, read the live catalog price or split the cut first. Budget table.
- caption_no_speech: why a caption job fails on a silent clip
A Sume caption job returns caption_no_speech when the clip has no audible speech. The fix is cues, segments or words, not a retry.
- Change one caption color: design.colors.active and what it accepts
A Sume caption design override changes one token for one request. Colors take hex, rgb(), rgba() or transparent; other CSS is rejected at request time.
- Captions from a video's speech: $0.20 a job, no SRT needed
Sume's video-captions endpoint transcribes the speech and burns styled captions for $0.20 a job on clips up to 60 s. Optional script_text corrects the wording.
Written by Sume