One photo, one line of text — and the face on it says your words out loud. No app to install, nothing to edit afterwards.
No complex settings, no long waits. Fewer clicks, better results.
A portrait with a clearly visible face, JPG or PNG. The sharper it is, the better the lip-sync.
Type a line and choose a voice — or upload your own audio for narration.
Ready in 30–60 seconds: an MP4 with speech and lip-sync. Download or share.
Real videos made by revideo.ai users. Click a card to watch.
The idea is simple and old: a still image that speaks. What changed is the effort — instead of animation software and hours of keyframing, you upload a picture, type a sentence and wait about ten minutes.
People use it in very different ways. Some make a pet deliver a one-liner for a family chat. Some bring an old photograph of a grandparent to life for a family gathering. Others use it commercially — a portrait becomes the host of a channel or the face of a landing page.
The Pro plan starts at $12.99/month with 40 credits; a talking clip costs from 2 credits. Photo animation without speech is available for free, no card required.
Old family pictures are the most common emotional use case, and they need care. Scans work fine if the face is in focus and large enough in the frame; heavy grain, creases across the face or a very small head in a group shot will show in the result.
A short line works better than a long speech here — a few seconds of a familiar face speaking carries more than a full monologue.
It animates a face, not a body: hands, posture and background stay as they were. Full-body gestures are outside what a single still can produce.
Faces in profile, partially covered or very small in the frame produce weaker results — the model needs a clear view of the mouth and eyes.
And one rule that is not technical: using someone else's face without their consent is off limits, whatever the purpose.
From a two-second joke to a full landing page host.
A cat or dog delivering a line for social media.
An old photograph speaking a short message.
A personal message instead of a forwarded card.
A recurring character who reads the script.
A portrait narrating a fact for a class.
Upload the photo, type what it should say and pick a voice. The clip is generated in five to fifteen minutes with the lip movement matched to the speech.
Yes, as long as the face is in focus and takes up a reasonable part of the frame. Heavy grain or creases across the face will be visible in the result.
Yes — animal faces work, and short lines look the most convincing.
Photo animation without speech is free and needs no card. Adding voice is part of the Pro plan from $12.99/month.
The clip length follows your script, and credits are charged by duration — a couple of sentences costs from 2 credits.
Pay for results — a credit is spent only when the video succeeds.
No subscription traps.
Launched in 2026 — we build for bloggers and sellers, teachers and SMM agencies.
“Made an animated product card for my online store in 2 minutes — CTR almost doubled. I used to pay a designer $50 for every video.”
“I use a talking avatar in Reels — I don’t feel like filming my own face, and engagement stays the same. Setup took a couple of minutes.”
“I animated an old photo of my grandmother — she burst into tears. Before that I spent a month trying to get Kling working, with no luck. Here it worked on the first try.”