Auto captions: text made from the speech
Auto captions are captions an app writes by itself from the speech in a video, timed to the words, ready to style or correct. As of 2026-09-25.
Vizard lists auto subtitling on every plan. VEED lists unlimited auto subtitles on its Creator plan. CapCut has an AI caption generator in its web editor.
The words differ from page to page, subtitles, captions, subtitling, but the feature is the same: speech turned into on-screen text.
Automatic captions still need a read-through. Names, slang and mixed languages are where transcription slips.
For short video they are close to essential, since many viewers scroll with the sound off.
Some apps, Vizard among them, also export the captions as a separate SRT file, which keeps them editable.
Captions made by the app also feed search inside the platforms, since the words become text the platform can read.
Where a pricing page lists captions on the no-charge plan, as Kapwing's does with a limit in minutes, the limit is usually in the fine print beside it.
| App | Feature | What the page says |
|---|---|---|
| Vizard | Captions | Automatic subtitles, with subtitle translation |
| VEED | Captions | Unlimited automatic subtitles on the Creator plan |
| CapCut | Captions | An AI caption generator in its web editor |
Inclusion rule. Readings from the register used on this page. Order. The order the text takes them in.
1From the apps' pages
Auto subtitling
Vizard pricing page
Unlimited Auto Subtitles
VEED pricing page
Use CapCut Web's AI caption generator to enhance viewer engagement today!
CapCut tools pages
- Plan comparisonAutomatic subtitles, with subtitle translation
- Creator planUnlimited automatic subtitles on the Creator plan
- AI Caption GeneratorAn AI caption generator in its web editor
Apps on this page: Vizard · VEED · CapCut
2A generator upstream of the app
Upstream of an app feature like “Auto captions”, SceneMixer describes its own generation steps:
SceneMixer turns a novel into a watchable short-drama series in one pipeline: upload the novel (Chinese or English) → AI extracts characters, scenes, and an episode-by-episode structure → generates consistent character and scene art → writes storyboard scripts → renders video segment by segment (16:9 by default, 9:16 in one setting) → composites full episodes.
SceneMixer, Turn a Novel into a Video Series with AI (read 2026-10-13)
Wan 3.0 is Alibaba Cloud's video generation model on the Model Studio platform, called through an asynchronous submit-then-poll API, in two tiers: the standard wan3.0-video and the faster wan3.0-video-prime.
SceneMixer, Wan 3.0 for AI Short Drama (2026): Parameters, Reference Limits, Moderation Rules and the 30-Second Take (read 2026-10-13)