Caption a week of Shorts: the batch cost at $0.20 a clip on Sume

Captioning a week of Shorts on Sume costs $0.20 per clip, so seven clips are $1.40 and thirty-five are $7.00. The video captions docs, read 2026-10-03, say each accepted standalone caption job reserves and captures $0.20 for videos up to 60 seconds under the current fixed estimate, and tell you to confirm live pricing in GET /v1/catalog.

What does a batch cost?

The fee is per job, not per word, so a 20-second clip and a 59-second clip cost the same. The docs state the figure for videos up to 60 seconds only; I found no stated rate for longer clips, so keep Shorts under a minute.

How do I avoid paying twice?

Restyling is the easy place to waste money. Pass source_caption_id instead of video_url and Sume reuses the source video and the word timings it already has, so no second speech-to-text runs. The docs are explicit that billing is unchanged, since a restyle is still a render, so test looks on one clip, not the whole week.

What should I check first?

• A silent clip fails as caption_no_speech; pass cues with text, start and end to burn authored copy without transcription.
• video_url must be a fetchable public HTTPS URL; private-network and signed URLs are rejected.
• Send an idempotency key per clip, such as the clip's own id, so a retried batch cannot caption the same video twice.