Make videos of me talking without filming

“make a video of me talking without filming”

A video of the person's own face, made from one photo or a short clip they recorded, speaking any script in their own cloned voice with matching lips, expressions and head and body motion; long videos are generated in segments that join without drift, the same video can be re-voiced and lip-synced into other languages, and every version is labelled AI-generated with provenance attached.

Start

Opening the preview…

Part of this works today

You get a real first result now. The remaining steps are being built; when they are released, people who asked for this are told.

What you bring

Nothing to prepare. Start with what you have; Conteenua asks for more only when a step needs it.

Free and paid

Free: Everything can run on the person's own computer through the Companion at no credits: Kyutai Pocket TTS clones the voice on the CPU, EchoMimic V3 (12 GB GPU) animates and MuseTalk 1.5 (4 GB GPU) re-syncs each language, and translation runs offline; the person reviews every take.

Paid: Conteenua's GPU workers clone with Chatterbox Multilingual V3 or Qwen3-TTS, animate at 720p with InfiniteTalk or LongCat-Video-Avatar 1.5 for minutes-long takes and re-sync each language with LatentSync 1.6 or InfiniteTalk, charged in credits by what it consumes and settled on the verified result (spec 7.3).