Ynnk Voice Lipsync – voice-to-lip-sync plugin for Unreal Engine

Ynnk Voice Lipsync Free Download: Voice-to-Lip-Sync Plugin for Unreal Engine

Ynnk Voice Lipsync is a code plugin for Unreal Engine that generates lip-sync curves from SoundWave assets or PCM audio using voice recognition, without requiring subtitles.

Ynnk Voice Lipsync is a voice-to-lip-sync plugin for Unreal Engine, created by Yuri N Kalinin. Instead of relying on subtitle text, it uses a voice recognition engine to analyze speech from SoundWave assets or raw PCM audio data. The resulting lip-sync is saved as curves in data assets and can be played back at runtime alongside the audio. The plugin is distributed as a code plugin with 8 C++ classes and no Blueprints, and it is suited to dialogue-heavy games, narrative projects and any character that needs to speak convincingly.

Specifications

SellerYuri N Kalinin
TypePlugin
CategoryAnimations
EnginesUnreal Engine 4.26–5.8
DistributionCode plugin
FormatsUnreal Engine
File types.uasset, .uproject, .uplugin
Unreal target platformsAndroid, HoloLens 2, Windows
C++ classes8
Network replicatedNo
LicensesPersonal, Professional
Published2026-08-11

Key features

  • Generates lip-sync from SoundWave assets or PCM audio data
  • Lip-sync saved as curves in data assets, played with audio at runtime
  • Works offline without subtitles
  • Runtime lip-sync generation on Windows and Android
  • Editor generation of Anim Sequence assets with lip-sync
  • Supports Pose Asset (universal) and morph target lip animation
  • Asynchronous audio recognition and lip-sync building
  • Eight C++ classes across two modules

Voice-Driven Lip-Sync Without Subtitles

The plugin works from the audio itself rather than from a text transcript, so lips follow the spoken sound. Lip-sync curves are stored in data assets, which keeps the animation separate from the audio and easy to play at runtime together with the voice clip.

Lip-sync can be generated at runtime, but not in real time: the plugin does not process a microphone or other streamed audio for lip-sync. For speech-to-text, a separate microphone recognition feature is available at runtime on Windows and Android.

Language support covers English, Chinese, Korean and Japanese as fully supported, with Russian, Italian, German, French, Spanish, Portuguese and Polish also supported.

Engine Versions, Platforms and Packaging

Ynnk Voice Lipsync supports Unreal Engine 4.26, 4.27 and 5.0 through 5.8. It is distributed as a code plugin with the file types .uasset, .uproject and .uplugin. The supported development platform is Win64, and the target build platforms are Win64 and Android; HoloLens 2 is also listed among the Unreal target platforms.

The plugin uses two modules: YnnkVoiceLipsync at runtime and YnnkVoiceLipsyncUncooked for uncooked-only use. An example project is available for Unreal Engine 5.5, 5.2 to 5.4, and a MetaHuman 5.5 variant, along with an executable demo and documentation.

A Whisper add-on, YnnkWhisperRecognizer, can be used instead of the default Vosk recognizer.

Use cases

  • Dialogue-heavy RPGs
  • Narrative adventure games
  • Character voice-over previews
  • Mobile and PC runtime dialogue

Ynnk Voice Lipsync FAQ

Which Unreal Engine versions does Ynnk Voice Lipsync support?

The plugin supports Unreal Engine 4.26, 4.27, and 5.0 through 5.8. Example projects are provided for Unreal Engine 5.5, 5.2 to 5.4, and a MetaHuman 5.5 variant.

Does Ynnk Voice Lipsync need subtitles?

No. The plugin generates lip-sync from the voice audio itself, so subtitles are not required.

Which languages are supported?

English, Chinese, Korean and Japanese are fully supported. Russian, Italian, German, French, Spanish, Portuguese and Polish are also supported.

Is the plugin a Blueprint or C++ package?

It is a C++ code plugin with 8 C++ classes and no Blueprints. It is not network replicated.