Subtitles in three languages: three caption jobs at $0.20 each

One Sume caption job burns one set of cues, so a 45-second video in English, Spanish and Korean is three jobs. The Video captions docs say each accepted standalone job reserves and captures $0.20 for a video up to 60 seconds under the current fixed estimate, so that is $0.60 for the three. Confirm the live price in GET /v1/catalog before you budget a batch.

Facts here come from the Sume Video captions page, read 2026-10-02. They describe the standalone endpoint, not the inline captions on Avatar Video, which are a separate add-on.

What does one language cost?

The figure covers a video up to 60 seconds. The docs give no price for longer clips on that page, so use the catalog for those.

A restyle of the same video through source_caption_id reuses the word timings and runs no second speech-to-text, but the docs say billing is unchanged because it is still a render.

How do I send a translated caption job?

Pass your translated text as cues, each with text, start and end in seconds. That is the authored overlay path and it skips speech-to-text. Keep the cue times from the original transcript and replace only the text; if a translated line is much longer, give it more time or split it.

Pick a style that can draw the language: Korean text on slam, punch or tiktok-green returns 400 with caption_hangul_text_latin_style, so use a Hangul style such as black-outline.

curl -X POST https://api.sume.com/v1/video-captions \
  -H "Authorization: Bearer $SUME_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: caption-ko-001" \
  -d '{
    "video_url": "https://media.sume.com/artifacts/example/clean.mp4",
    "style": "black-outline",
    "cues": [
      { "text": "안녕하세요, 새 제품을 소개합니다.", "start": 0.0, "end": 2.4 }
    ]
  }'

Can I skip a job by translating inside one caption?

No field in the docs translates for you: language is only a speech-to-text hint, so translation happens before the call, in your own step. Plan the cost as one job per language, and put each file in its own folder or name so the three outputs do not get mixed up. For a two-language overlay in one file, see bilingual subtitles.