Getting Started

Experimental Features

Overview

Get early access to new features before they’re released to everyone. These features are fully functional but still being refined based on user feedback before transitioning to general availability.

Enable Experimental Features

2

Toggle Experimental Features

Under the Experimental Features section, toggle the switch to enable access to experimental features and early previews.

3

Start Using New Features

Once enabled, experimental features will appear throughout the Sync Studio with a preview badge.

Available Experimental Features

Speaker Selection

Status: Experimental | Released: November 2025

Take full control over who gets lipsynced in your videos. While Active Speaker Detection automatically identifies speakers, Speaker Selection lets you manually choose specific characters directly from your video for targeted lipsync.

Key Benefits

  • Precise Control - Click to select exactly who should be lipsynced
  • Multi-speaker Support - Handle complex scenes with multiple people speaking
  • Visual Selection - See identified characters and select speakers directly from the video player

How to Use Speaker Selection

1

Choose your assets

Select your video and audio assets in Studio.

2

Activate Speaker Selection

Enable “Speaker Selection” by clicking the face icon in the video player controls.

3

Click to Select

Wait for faces to be identified, then select the face you want to target.

4

Generate

Hit Generate (big blue button ;) to process your video with the selected speaker lipsynced.

Speaker Selection is currently in experimental phase. We’re actively gathering feedback to improve accuracy and user experience before general availability.

Feedback

Your input shapes these features. Found a bug or have suggestions?