Captions free plan vs trim and captions by API at 22 cents

The Captions app's free plan includes basic editing such as trim, transitions and captions, but it has no AI usage credits, and the page says its listed prices reflect iOS plans only. If you want trim plus captions as an API call, Sume charges $0.02 for a video trim and $0.20 for a caption job, so one trimmed and captioned clip is $0.22.

The same two steps, two ways

How the Sume chain runs

Both calls are asynchronous and need an Idempotency-Key on submit. If the trimmed URL is not publicly fetchable, host a copy where it is before the caption step.

• Import the source clip with POST /v1/media-imports, since trim takes workspace media URLs.
• Trim with start and duration. The result is a new MP4, and the source is unchanged.
• Send the trimmed clip's public URL to the caption endpoint, which takes a public HTTPS video_url.
• Poll each job with GET /v1/jobs/:id/status and read the result when it is ready.

When free beats $0.22

For one person editing a few videos by hand, the free app plan costs nothing and wins. The API makes sense when a program does the editing: a hundred clips is $22 on Sume, and no one has to open an app. Keep an eye on the 60-second limit for captions, since a longer clip has to be cut into pieces first, which is another $0.02 a piece.

A note on style and language

Sume's caption job takes a style, an optional font, and a language hint for speech-to-text. If you send no style, Latin text renders as slam, the default. You can also pass your own words or cues with start and end times, in which case Sume skips speech-to-text, which suits silent clips. Each accepted standalone job is $0.20 whatever the style, and a restyle of an already captioned video is another render at the same price.

One more difference is control: the app offers presets chosen by hand, while the API makes the same choice reproducible in code, so a hundred clips come out with the same style and the same font without anyone reviewing each setting.