Dub my videos into other languages in my own voice

“Dub my videos into other languages in my own voice”

Each chosen language version of the person's existing video, re-voiced in their own consented voice: speech separated from the music and effects, transcribed with speakers told apart, translated to fit each line's timing, spoken in the person's voice, remixed over the original music bed, lips re-synced and captions redone in that language, with every version labelled AI-generated and ready to post.

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: On the person's own computer through the Companion at no credits: Demucs and DeepFilterNet separate, whisper.cpp transcribes, translation runs offline, Kyutai Pocket TTS re-voices and MuseTalk 1.5 re-syncs lips on a 4 GB GPU; the person checks each line.

Paid: Conteenua's GPU workers separate and tell speakers apart (Demucs, pyannote), translate with each line's timing in mind, re-voice with Chatterbox Multilingual V3, Qwen3-TTS or CosyVoice3 and re-sync with InfiniteTalk or LatentSync 1.6, charged in credits by what it consumes and settled on the verified result (spec 7.3).