Turn a single photo into a lip-synced talking avatar video. Upload a face and a short voice clip, and the engine animates the face to match the speech — right in your browser. Free, no sign-up, no install. A free, Hedra-style alternative for making talking-avatar videos.
A sharp, front-facing photo with good lighting and one visible face gives the cleanest lip-sync. Avoid sunglasses and heavy shadows.
Start with a 5–10 second voice clip with clear speech and little background noise. Longer clips take longer to render.
The first launch may take up to a minute while the GPU warms up. After that, avatars render faster.
No rigging, no 3D software, no editing timeline — just a face and a voice.
Drop in a clear, front-facing photo of the person or character you want to bring to life.
Upload the audio you want lip-synced — record it, use a voice memo, or export it from a text-to-speech tool.
Press generate; the engine lip-syncs the face to the audio and gives you a talking video to download.
Turn a headshot into a presenter that reads your script — for ads, explainers and product demos.
Give an illustrated character or avatar a face that moves and speaks along with your audio.
Make quick talking-head clips for Reels, Shorts and TikTok without filming yourself.
A talking avatar is only as good as its two inputs: the photo and the voice clip. For the photo, use a clear, front-facing shot of a single face, evenly lit, with the eyes and mouth visible and unobstructed — no sunglasses, no heavy shadows, no group shots. A high-resolution portrait animates far more cleanly than a small or blurry one.
For the audio, a short clip of clear speech with little background noise gives the best lip-sync. You can record yourself on a phone, use a voice memo, or export narration from a text-to-speech tool and upload the file. Starting with five to ten seconds is a good way to preview the result before committing to a longer clip.
Talking avatars are a fast way to make explainers, product intros, UGC-style ads and social clips without filming — you can turn a headshot into a presenter that reads your script, and they bring illustrated characters and mascots to life too.
One important rule: only upload photos and voices you own or have permission to use. Creating a talking video of a real person without their consent is not what this tool is for, and you are responsible for what you make.
Yes — free with no account, supported by ads on the page. Because it runs on shared GPU infrastructure, it can queue at busy times.
A clear front-facing photo of one face and a short voice clip (an audio file of the speech you want lip-synced). The engine animates the face to match the audio.
Record yourself, use any voice memo, or create speech with a text-to-speech tool and download it as an audio file, then upload it here.
Whatever you generate is yours to use, subject to the underlying open model's licence. Only use photos and voices you have the right or consent to use.
Generate a portrait with our free AI Image Generator, then bring it to life here.