Katama
群声Multi-Character Lip Sync

Multi-Character Lip Sync

Make entire casts speak — sync multiple faces to different voices in one scene, no rotoscoping required.

Make it with Shishō

Type your idea — Shishō builds it and drops you straight into the studio.

What it is

Multi-character lip sync extends single-face sync to full scenes. Upload a group shot or a sequence with several people, assign a voice to each face, and Katama drives every mouth independently. It is built for dialogue-heavy content — short films, explainer skits, podcast visualizers and ad creatives where more than one person talks.

How it works

  1. 01

    Upload or generate the scene

    Start from a group photo, a multi-person video clip, or a scene you generated inside Katama.

  2. 02

    Assign voices to faces

    Tag each person in the frame and pair them with a voice — upload audio or generate speech with AI TTS.

  3. 03

    Sync and export

    Katama drives each face independently, rendering accurate lip motion for every speaker in a single pass.

Why creators choose it

Multiple faces synced at once
Independent voice per character
Works on photos and video
Ideal for dialogue and skits

Frequently asked

How many faces can I sync at once?

The system handles scenes with several speakers — enough for dialogue, panels and group conversations.

Does each face get its own voice?

Yes. You assign a separate audio track or AI voice to each tagged face, and they move independently.

Can I use this for short films?

Absolutely — multi-character sync is designed for narrative scenes where realistic dialogue between characters matters.

Start creating now