Add subtitles to a video in DaVinci Resolve, or with a caption API
Resolve 21 transcribes and translates speech to text in the app. Sume video-captions burns styled captions into a public MP4 URL for $0.20 up to 60 seconds.

To add subtitles in DaVinci Resolve 21, use its speech-to-text, which the product page lists as transcribe and translate. That puts a subtitle track in your timeline. If you want captions burned into the picture by an API instead, send the video to Sume's POST /v1/video-captions with a public HTTPS video_url and optionally a style. Both are valid; the difference is whether you want an editable track or a finished file.
What the caption route gives you
Ten styles are documented: slam, punch, tiktok-green, korean-ad, black-outline, weight-shift, highlight, pill-karaoke, clip-wipe and editorial-emphasis. If you omit style, Latin text gets slam and Korean gets black-outline. You can pass language, your own script_text, words, or phrase-level cues and segments, which skip speech recognition. Passing source_caption_id restyles an earlier job without transcribing again. Each job is $0.20 for videos up to 60 seconds; confirm in GET /v1/catalog.
| Question | Resolve 21 | Sume video-captions |
|---|---|---|
| Result | Speech to text in the app, per the product page | Captioned video file |
| Translate | Listed on the product page | Not offered; pass translated script_text |
| Edit text | Not stated on the page | Re-run with script_text or cues |
| SRT input | Not described on the page | SRT uploads unsupported; use cues |
| Silent clip | No speech to transcribe | Fails as caption_no_speech |
Korean and font notes
A font field exists, and it applies to Hangul only. Sending Korean text with a Latin style returns 400 caption_hangul_text_latin_style, so choose a Korean style such as korean-ad or 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: resolve-sub-001" \
-d '{"video_url":"https://media.sume.com/artifacts/example/clean.mp4","style":"highlight","language":"en"}'Honest limits
- Sume does not output a separate subtitle file in the docs; captions are burned into the video.
- Translation is not part of the caption route; translate the text first.
- Blackmagic's page lists the feature without language counts, so none are stated here.
Sources
Related posts
More in Media tools
- AI music from an image: Lyria 3.5 image_url mood still on Sume
Sume's Music Router takes an optional public HTTPS image_url as a mood still next to the prompt. How to send it, what it costs and what to expect back.
- AI music generator for covers: what Sume cannot do, and a swap
Sume cannot cover an existing song: no audio input and no song-to-song path. Licensed cover platforms are still in development. Here is an original-track swap.
- Apple Podcasts transcript speaker names: VTT, and Sume STT gaps
Apple shows speaker names when you provide a VTT. Sume STT has no speaker labels, so transcribe each track and merge with voice tags. Script included.
- Audio-only cut of a 5 minute episode: mp3 for $0.01
Turn a finished 5 minute video into a 128 kbps mp3 for $0.01 with audio-detach. Source up to 1800 s, output up to 900 s, and the silent-source error.
Written by Sume