Vizard credits are one minute each: what a Sume caption job costs
A Vizard credit is one minute of video; Free has 60. Sume burns captions for $0.20 per job on videos up to 60 seconds (confirm in GET /v1/catalog).

On Vizard's pricing page one credit equals one minute of video, and the Free plan includes 60 credits. Sume does not meter by source minute for captions: each caption job is a fixed $0.20 for a video up to 60 seconds, so a one-minute clip costs the same $0.20 either way.
Different units, different jobs
A Vizard credit pays for the whole repurposing flow on a source video, not only captions. A Sume caption job covers one thing: take a finished clip at a public HTTPS URL and burn captions into it.
That makes the comparison only fair for the caption step. If you already have the clip, the Sume job is the closer match.
| Item | Vizard | Sume |
|---|---|---|
| Billing unit | 1 credit = 1 minute of video | One caption job |
| Free allowance | 60 credits | Plan wallet, no free minutes promised here |
| Caption price for a 60 s clip | 1 credit | $0.20 per job |
| Longer clip | Credits scale with minutes | Price quoted for up to 60 s; check the catalog |
How the arithmetic works
Twenty 45-second clips cost 20 caption jobs on Sume, which is $4.00. On Vizard the same twenty clips total 15 minutes of video, so 15 credits against the Free allowance of 60.
The cheaper option depends on whether you need Vizard's clip selection as well. If you only need captions on clips you have already cut, paying per job avoids buying minutes of source video.
What a Sume caption job needs
The video_url must be a fetchable public HTTPS URL. Speech is transcribed unless you pass cues or segments, and a silent clip fails with caption_no_speech. To restyle without a second transcription, send source_caption_id; the restyle is still billed as a render.
Burned-in captions cannot be switched off by the viewer, which is the trade for them looking the same on every platform.
curl -X POST https://api.sume.com/v1/video-captions \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: clip-001-captions" \
-d '{"video_url":"https://media.sume.com/artifacts/example/clean.mp4","style":"slam"}'Sources
Related posts
More in Comparisons
- Vizard Free exports 720p up to 10 minutes: Sume trim limits compared
Vizard Free caps exports at 720p and 10 minutes. Sume's video trim takes a source up to 1,800 seconds and outputs up to 900 seconds, for $0.02 per job.
- Wan 3.0 or MiniMax H3 Max: which to pin for reference-to-video
Both take image, video and audio references on Sume. Wan runs 2 to 30 seconds with 5 reference videos; H3 Max runs 5 to 15 seconds with always-on stereo audio.
- Wan 3.0 or Seedance 2.5: which is cheaper for a 10-second 720p clip?
Wan 3.0 is cheaper: a 10-second 720p clip is $1.00 at fal list ($1.25 on Sume) against about $4.62 ($5.78 on Sume) for Seedance 2.5, roughly 4.6x.
- Which image and video models on Sume have open weights?
Sume's catalog is hosted. Where vendors publish weights for families Sume lists (Qwen-Image, MiniMax H3, FLUX.2) and why a null hugging_face_id proves nothing.
Written by Sume