Skip to content

Lipsync Studio - Audio-Driven Mouth Animation

by Skava·Motion Graphics

Images © Skava. Used for product review; image policy.

Why we like it

Stands out in the Superhive library for shipping a Python-only add-on that downloads just the Rhubarb binary it needs on first run, about 8 MB, instead of bundling a heavier binary in the download.

What is Lipsync Studio - Audio-Driven Mouth Animation?

LipSync Studio generates mouth animation from audio inside Blender. It offers three analysis engines: a built-in energy analysis that is fast and language-agnostic but less precise, Rhubarb Lip Sync for phoneme-accurate, text-aided results, and OpenAI Whisper for speech-to-text plus phonemes (currently English only). Rhubarb installs through a one-click download that detects your platform and fetches the official release, about 8 MB rather than a bundled binary.

Six viseme rig presets — Generic, ARKit 52, FACEIT, Preston Blair, MetaHuman and CC4 — map all 17 viseme slots to the shape-key names your rig already uses, with an Auto-Detect option that scans shape keys when no preset fits. After a build, Push to NLA drops the lip-sync action into a dedicated strip on the mesh's shape-key track so it blends with other actions, and the step is fully reversible. An additive emotion overlay keyframes Happy, Sad, Angry or Surprised expressions on top of the speech with an adjustable strength slider.

Analysis runs on worker threads driven by a modal timer, keeping Blender's UI responsive. Results export to FBX, glTF or JSON for Unity, Unreal or custom pipelines.

Who is Lipsync Studio - Audio-Driven Mouth Animation best for?

Lipsync Studio - Audio-Driven Mouth Animation is best for character artists animating dialogue in Blender who want to bake audio into blendable NLA strips and export the result to Unity, Unreal or a custom pipeline.

How much does Lipsync Studio - Audio-Driven Mouth Animation cost?

Lipsync Studio - Audio-Driven Mouth Animation is completely free to download and use.

Key features

  • Three analysis engines: built-in energy analysis (fast, language-agnostic, less precise), Rhubarb Lip Sync (phoneme-accurate, text-aided) and OpenAI Whisper (speech-to-text plus phonemes, English only)
  • Six viseme rig presets (Generic, ARKit 52, FACEIT, Preston Blair, MetaHuman, CC4) that map all 17 viseme slots, plus an Auto-Detect option that scans shape-key names
  • Push to NLA drops the lip-sync action into a dedicated strip on the mesh's shape-key track for blending with other actions, and is fully reversible
  • Additive emotion overlay keyframes Happy, Sad, Angry or Surprised expressions over the speech with an adjustable strength slider
  • Modal threaded analysis runs Whisper and Rhubarb on worker threads so Blender's UI stays responsive during long audio
  • Auto blend with configurable ease-in and ease-out per viseme keyframe and an adjustable intensity multiplier
  • Export to FBX, glTF or JSON for Unity, Unreal or custom pipelines

Tags

#lip-sync#Blender#character animation#viseme#Rhubarb#shape keys#gamedev#Whisper

Frequently asked questions

Does LipSync Studio work with Blender 4.2?

LipSync Studio supports Blender 3.2 and later, and the developer notes it is tested on 3.6 LTS and 4.2 LTS, so 4.2 is covered. It runs on Windows, macOS on both Intel and Apple Silicon, and Linux. For phoneme-accurate analysis it uses Rhubarb, which works with any recent build downloaded from the preferences panel, while the OpenAI Whisper engine relies on the Whisper package in Blender's Python. Check the developer's page to confirm details for your exact setup.

How do I install LipSync Studio and set up Rhubarb?

LipSync Studio installs like a standard Blender add-on: open Preferences, go to Add-ons, click Install, pick the downloaded ZIP and enable it. The LipSync sidebar tab then appears in the 3D Viewport, which you open by pressing N. For Rhubarb analysis, open the add-on preferences and click Download Rhubarb; it auto-detects your platform and fetches the official binary, about 8 MB, so nothing extra needs to be installed by hand. The download ships as Python only, with no binary bundled in.

Does OpenAI Whisper support non-English audio in LipSync Studio?

LipSync Studio's OpenAI Whisper engine, which handles speech-to-text plus phonemes, is currently English only. For other languages, the built-in energy analysis engine is language-agnostic and fast, though less precise. Rhubarb Lip Sync provides phoneme-accurate, text-aided results and installs through the one-click downloader. That leaves three analysis engines available, with only Whisper limited to English at the moment. See the developer's page for the latest on language support.

Can I use LipSync Studio for free and in commercial projects?

LipSync Studio is listed as free here, and it is released under GPL-3.0, the standard license for Blender add-ons. The Rhubarb binary it downloads is MIT-licensed, which means the animation you produce can be shipped in any commercial project. The package also includes free updates for the v1.x series and support through marketplace messaging. For the current licensing terms and anything specific to your use, check the developer's page before relying on it.

Can I export LipSync Studio results to Unity or Unreal?

LipSync Studio exports finished results to FBX, glTF or JSON. The FBX output carries shape-key animation for Unity and also targets Unreal, while the JSON option provides a viseme timeline for any custom pipeline. Because Push to NLA places the lip-sync action on the mesh's shape-key track, you can blend it with other actions such as idle breathing or expression layers before exporting. The v1.2.0 release adds support for rigs with split left and right shape keys. See the developer's page for pipeline specifics.

Similar plugins