Not every piece of on-screen text is a subtitle. A hook line at the top of a TikTok, a 'SWIPE UP' CTA, a branded badge in the corner — these are text YOU write, not words the speaker says. add_video_captions is built for exactly that: one fixed line of text, burned onto a standalone video.
If you need speech transcribed into subtitles instead, use add-captions-to-video or add-subtitles-automatically. If you need several DIFFERENT lines of your own text appearing and disappearing at specific timestamps, use add-timed-text-overlays-to-video instead.
Powered by
Burn a fixed TEXT OVERLAY onto a standalone video — a hook line, headline, badge, CTA, quote or branded label that you supply. This is NOT a subtitle tool: it does not transcribe speech. For spoken-word subtitles use add_veed_captions. Call list_caption_fonts first when the user wants a specific font.
What to tell the agent
Versely's agent maps this plain-English request directly onto add_video_captions. You don't need to know the parameter names — just describe what you want.
“Add the text 'WAIT FOR IT...' to the top of this video in white bold text with a dark background.”
How it works
1. Write your line
One piece of text — a hook, headline, quote, badge or CTA. This isn't transcription, so type exactly what you want to appear.
2. Choose a position
Top, center or bottom placement is required by the tool — pick based on where your subject's face and any existing captions sit.
3. Set the look
Font size, font color and an optional background block are all controllable. Call list_caption_fonts first if you want a specific typeface named rather than a default.
4. Render
The text is burned directly into the video frames and a finished MP4 is returned.
What it costs
add_video_captions is a standard editor operation billed per render — ask the agent to run estimate_cost against your video before confirming if you want the exact credit number.
The formula behind that number: What does editing a video cost if I keep changing it? — charges per finished export, so iteration is free and the count is the whole bill.
Limits & things to know
- This burns ONE fixed line of text for the whole clip — it does not transcribe speech and does not change over time.
- For multiple lines that change at different timestamps, use add-timed-text-overlays-to-video instead.
- Position is constrained to top, center or bottom — there's no free-form pixel placement.
Who uses this
- TikTok/Reels hook lines
- Branded badges and watermarked-style labels
- Quote cards over B-roll
- 'Swipe up' / 'link in bio' CTAs
- Chapter or segment titles
Frequently asked questions
Is this the same as adding subtitles?+
No. add_video_captions burns in text YOU supply — it doesn't transcribe anything. For auto-transcribed subtitles, use add-captions-to-video instead.
Can I add more than one line of text?+
This tool is built for a single fixed line for the whole video. If you need multiple lines that change at specific timestamps, use add-timed-text-overlays-to-video, which is built for exactly that.
Can I pick a specific font?+
Yes — call list_caption_fonts first to see the full registry (sans-serif, serif, display, handwriting, monospace) and pass a font_id rather than leaving it to the default.
Where can the text be positioned?+
Top, center, or bottom of the frame — position is a required parameter on every call.
Related Versely tools
Related editing jobs
Add a Text Overlay 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.