Captions are the single biggest lever for watch time on silent-autoplay feeds — most viewers scroll with the sound off, so if the words aren't on screen the hook is lost in the first second. Versely transcribes the spoken audio in your video and burns the result on as styled, positioned text.
This is the tool for turning what someone SAYS into on-screen text automatically. If you instead want to place your OWN text (a headline, a CTA, a quote you wrote) that nobody says out loud, use add-text-overlay-to-video instead — that's a different tool.
Powered by
Add styled, auto-transcribed captions to a video using the VEED Subtitles model (fal.ai veed/subtitles). Burns aesthetic preset styles (Glass, Whisper, Fusion, Glide, etc.) — different from add_dynamic_captions, which is the word-level animated style. Use when the user wants polished social-ready captions with a chosen visual look, or asks for VEED captions specifically. Also offer this proactively as a finishing step after any video / movie / workflow run that produces video content. Two preset tiers: BASIC (1× credit cost, 21 presets — simple/plain/beans/corpo/etc.) and DYNAMIC (2× credit cost, 9 premium presets — glass/whisper/glide2/fusion/glide/terminal/handwritten/backdrop/backdrop2). Default to preset 'glass' for a modern look unless the user specifies a vibe. Supports 165 language codes for transcription (en-US, en-GB, es-ES, es-MX, fr-FR, de-DE, it-IT, pt-BR, ja-JP, ko-KR, zh, ar-SA, ru-RU, etc.).
What to tell the agent
Versely's agent maps this plain-English request directly onto add_veed_captions. You don't need to know the parameter names — just describe what you want.
“Add captions to this video using the glass style, positioned at the bottom.”
How it works
1. Upload or generate your video
Bring any video with spoken audio — a talking-head clip, a UGC ad, a voiceover-led edit.
2. Pick a preset
Choose from 21 BASIC presets (simple, plain, beans, corpo, and more) or 9 DYNAMIC presets (glass, whisper, glide, fusion, terminal, handwritten, backdrop). Not sure which look fits? Ask the agent to render a short preview first with preview_caption_style before committing to a full-length render.
3. Set the language
add_veed_captions transcribes in whatever language code you set — 165 are supported, from en-US and es-MX to ja-JP and ar-SA. It transcribes what's spoken; it doesn't translate into a different language (for that, see translate-video-to-another-language).
4. Render
Versely transcribes the audio, times each line to the speech, and burns the styled captions into the video. You get back a finished MP4.
What it costs
Pricing is tiered by preset: BASIC presets run at the standard 1× credit rate, DYNAMIC presets (the 9 premium looks like glass, glide, and fusion) cost 2× that. Ask the agent to run estimate_cost before a full render if you want the exact number for your video's length.
The formula behind that number: What do captions cost across a month of clips? — multiplies one base render by a style tier, so an aesthetic choice doubles the bill.
Limits & things to know
- This is a transcription tool, not a translation tool — the caption language should match the language actually spoken in the video.
- Accuracy depends on audio clarity; heavy background noise or overlapping speakers will degrade the transcript.
- DYNAMIC presets cost twice as much as BASIC presets — factor that into which look you pick for a long-form video.
- add_dynamic_captions (Versely's older in-house captioner) is retired; VEED is the only captioning engine live in the app now.
Who uses this
- TikTok and Reels hooks watched on mute
- UGC ads that need on-screen proof of the script
- Talking-head YouTube Shorts
- Course and tutorial clips for accessibility
- Podcast video clips
Frequently asked questions
Does this tool transcribe the audio automatically?+
Yes. add_veed_captions runs speech-to-text on the video's own audio track and times the resulting captions to the speech — you don't type or time anything by hand.
What caption styles are available?+
21 BASIC presets (simple, plain, beans, corpo and more) at standard pricing, plus 9 premium DYNAMIC presets (glass, whisper, fusion, glide, glide2, terminal, handwritten, backdrop, backdrop2) at 2× the credit cost.
Can I preview a style before rendering the whole video?+
Yes. preview_caption_style trims the first few seconds of your video and renders just that clip in the style you're considering, so you can compare looks cheaply before committing to a full render.
Does it work in languages other than English?+
Yes — 165 language codes are supported for transcription, covering everything from Spanish and French to Japanese, Korean, Arabic and Chinese.
What happened to Versely's old caption style?+
The in-house dynamic captioner (add_dynamic_captions) has been retired. VEED captioning (add_veed_captions) is the only subtitle engine live in the app now.
Related Versely tools
Related editing jobs
Add Captions to a Video inside Versely
The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync in a single app.