What is the Convai Unreal Engine plugin
Understand what the Convai Unreal Engine plugin adds to a project: Blueprint components, a real-time voice pipeline, and opt-in feature add-ons.
The Convai Unreal Engine plugin connects Unreal Engine 5 projects to Convai so in-scene actors can speak, listen, reason, and act in real time. A player speaks into a microphone or sends text; the plugin captures input, streams it to Convai for speech recognition and language understanding, generates a response with text-to-speech, and plays it back on the character with synchronized lip sync, facial emotion, and optional in-scene actions. The plugin targets Unreal developers building training simulations, interactive experiences, and games.
What it includes
The plugin ships with a complete conversation pipeline and a set of opt-in feature add-ons.
Conversation pipeline
Always active once connected:
Real-time voice input — microphone capture through
UConvaiAudioCaptureComponent, streamed to Convai over WebRTCLanguage understanding and generation — Convai processes speech and responds in character
Text-to-speech playback — voice generated by Convai, played back through
UConvaiChatbotComponent
Feature add-ons
Opt-in, each configured through Blueprint or the Details panel:
Character actions — characters execute structured in-scene commands (
Move To,Follow, custom) dispatched from ConvaiDynamic context — push live world state and events into character knowledge at runtime
Emotion — Convai infers emotion from conversation and drives blendshape expressions on the character
Long-term memory — characters remember each player across sessions using an end-user ID
Narrative design — trigger scripted conversation branches and sections by name from Blueprint
Scene metadata — tag level actors so characters are aware of and can act on them
Vision — stream camera frames to Convai so characters can describe what they see
Gaze attention — route the object in the player's gaze direction as context to the active character
Lip sync — Convai-provided face animation data drives blendshape mouth movement in sync with speech audio, with selectable
Viseme Based,MetaHuman Blendshapes,ARKit Blendshapes, andCC4 Extended Blendshapesmodes for different rigs
Editor tooling
The ConvaiEditor module adds an in-editor configuration window for API key setup, the character dashboard browser, and Blueprint graph utilities such as the Create Convai Action Handler right-click entry.
Relationship to Convai
Convai hosts the language model, voice synthesis, narrative design engine, long-term memory store, and character configuration. The plugin is a client-side integration layer: it captures audio or text from the player, streams it to Convai over WebRTC, and delivers the response back to the character's audio and animation pipeline.
The plugin runs client-side integration logic inside the game process, including session routing, audio playback, action handling, dynamic context, gaze attention, and scene metadata. It does not bundle a local language model or Convai decision engine. Character configuration and conversation decisions remain in Convai, so dashboard-side changes do not require recompiling the Unreal project.
Voice → Convai → character flow
UConvaiPlayerComponent captures microphone audio and sends it through a player session proxy. UConvaiChatbotComponent holds a character session proxy. UConvaiSubsystem owns the underlying Convai client and routes data between those proxies and Convai. The chatbot receives response data and coordinates audio playback, lip-sync processing, and Blueprint action handlers.
Blueprint-first design
The main gameplay workflows are exposed to Blueprint graphs. C++ access is available but secondary; most projects can build character logic through Blueprint components, events, and callable nodes, then use C++ only for project-specific extensions.
Requirements
Unreal Engine
5.0
Platforms
Win64, Android
Network
Internet connection to Convai
API key
Account at https://convai.com
Android requires microphone permission handling. The plugin bundles the AndroidPermission engine plugin as a dependency and requests RECORD_AUDIO permission automatically when it connects to Convai.
For the full platform and engine version support matrix, see Compatibility and requirements.
Next steps
Install the plugin and add your first AI character.
To understand the module and component structure before building, see the architecture page.
For a one-screen overview of every feature and links to the corresponding guides, see the feature map.
Last updated
Was this helpful?