Captions
Records, captions and edits talking-head video on your phone, including correcting your eye line so it looks like you're making eye contact with the camera.
What you'd use it for
Turning a phone-recorded talking-head video into something that looks like direct eye contact and reads with clean captions, without hiring an editor.
- Correct your eye line in post-production so a phone-recorded talking-head video looks like direct eye contact with the camera
- Auto-generate styled captions in your own brand style, in over 100 languages
- Remove filler words, dead pauses and background noise from a recorded take automatically
- Generate a talking-head video from a script using an AI avatar or your own AI twin, without filming anything
- Translate and subtitle a video into another language
The verdict
Captions earns its place through the eye-contact correction — a genuinely useful fix for anyone who has to talk to a lens for business video, and testable before paying since the free tier at least gets you a captioned clip. Beyond that it is turning into several tools at once — captioning, editing, and, more recently, full AI-avatar generation — and the parts added later feel less considered than the original gaze fix. It suits someone already filming themselves who wants that footage to look and sound better, more than someone hoping the AI-actor route replaces filming altogether.
What it costs
| Tier | Price | For | Includes |
|---|---|---|---|
| Free | $0 | Trying the recording, captioning and basic editing workflow. | Core recording and captioning tools at limited usage. |
| Pro | $24.99/mo | A creator or founder posting talking-head video regularly. | AI editing tools — filler-word removal, eye-contact correction, AI actors and generated footage — at standard generation speed. |
| Frontier | $69.99/mo (1x usage tier; 2x and 4x tiers available at $139.99 and $279.99/mo) | Heavy users who need to generate more video, faster, each month. | Everything in Pro at higher usage allowances and faster generation. |
Read from Captions's own pricing page on 25 Sep 2026. Vendors change prices without notice.
What you need to start
- Free account (Google, Apple, email or phone sign-up)
- iOS, Android or a browser to record or upload footage
- The $24.99/mo Pro plan for eye-contact correction, filler-word removal, AI actors and generated footage — the free tier has no AI credits
A few minutes to a free account and a captioned clip; the eye-contact correction and AI-avatar tools that are the actual draw sit behind the $24.99/mo Pro plan, since the free tier carries no AI credits.
Your first run Upload an existing take and Captions returns captions and eye-contact correction in seconds; generating a talking-head video from a script with an AI avatar takes a few minutes longer but needs no camera at all.
Where it breaks
None found.
Primarily a mobile app (iOS and Android) built around recording on your phone; a web version exists for editing and generating AI content without filming yourself first.
First entry in this reference. There is no previous check to compare it against.
When not to use it
Not for someone who wants a full non-linear video editor — the tools are built around a single talking-head clip, not multi-track production. And not for anyone hoping to try the eye-contact correction for free — it sits behind the $24.99/mo Pro plan, with the free tier limited to basic recording, trimming and captioning.
Captions solves the specific discomfort of talking to a phone camera: most people do not naturally hold eye contact with a lens, and the resulting video looks like someone reading off-screen because that is usually exactly what’s happening. Captions’ eye-contact correction fixes the gaze in post-production, which sounds like a small thing until you see a founder’s product video look confident and direct instead of shifty, from the same unedited take.
Beyond that signature feature, it is a fairly complete talking-head video toolkit: automatic captions in your brand style, filler-word removal, and — more recently — AI actors and fully generated footage, for content that does not require you to film anything at all.
What separates Free from Pro
Free lets you try the actual pipeline — record, caption, apply basic edits — at limited usage, which is enough to judge whether the eye-contact correction and captioning quality hold up before paying. Pro removes the cap and unlocks the AI-actor and generated-footage tools; Frontier is purely a speed and volume upgrade on the same feature set, aimed at someone producing daily or near-daily content rather than a weekly video.
Where it fits
Against OpusClip, which repurposes existing long video into clips, Captions is upstream of that — it is the tool that makes the original talking-head footage in the first place, before it ever gets cut down.
Alternatives
Marketing & socialAppsDescript
Edit video and podcasts by editing the transcript — delete a word from the text and the matching footage or audio disappears with it.
Marketing & socialAppsSynthesia
Turns a written script into a finished video with a talking AI presenter in 140+ languages, used for training videos, product explainers and sales outreach.
HeyGen
Turns a written script into a presenter-style video using an AI avatar, including a version trained to look and sound like you.
Marketing & socialAppsSubmagic
Takes a short video you already filmed and adds animated captions, b-roll and sound effects in one pass, so a raw phone clip comes out looking edited.
Get Captions
Buying the tool is not the hard part.
The ebook is about what to hand over, in what order, and how you find out when it goes wrong. One payment, no subscription.