🚀 The best real-time interactive AI avatar(digital human) with on-premise deployment and <1.5 s latency.
-
Updated
Aug 5, 2026 - C++
🚀 The best real-time interactive AI avatar(digital human) with on-premise deployment and <1.5 s latency.
LAM Gaussian-Splat Avatars for AI voice agents. Realistic avatars for interview/support/sales agents.
SOTA real-time interactive AI avatar platform for multimodal conversational digital humans.Next-generation realtime multimodal conversational AI avatar system with streaming digital human interaction.
Live voice and video characters you can interrupt. Full-duplex realtime avatars for web, React and React Native.
Local-first realtime Russian voice avatar. Local STT, Qwen, TTS and Audio2Face with LiveKit and a browser VRM interface.
Free, open-source AI English tutor for Windows with a real-time MuseTalk talking-head teacher. SpeakTosi Mini coaches spoken English one-on-one: cloned voices, live conversation, session review and long-term memory. Self-host it (MIT), bring your own LLM key. Custom avatars and voices: speaktosi.com
Live avatar widget using facemarket.ai SDK
Realtime Avatar (realtimeavatar.ai) for the DeepSeek Harness (dsh): harness-held API key, public docs as skills, rta_* tools, /rta onboarding, zero runtime dependencies
Realtime webcam avatar generator for VTubers and streamers — drive a live AI avatar from your face, no green screen or subscription needed.
To associate your repository with the realtime-avatar topic, visit your repo's landing page and select "manage topics."