Henry-23/VideoChat

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1303 stars · 172 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A real-time voice-interactive digital human application that combines ASR, LLM, TTS, and talking-head generation (MuseTalk) into a low-latency conversational avatar. It supports customizable appearance and voice, including voice cloning, with first-packet latency as low as 3 seconds.

Use cases

• build a real-time talking avatar that responds to voice
• create a custom digital human with my own face and voice
• clone a voice for an interactive virtual assistant
• stream a lip-synced talking head from an LLM chatbot
• run an end-to-end voice-to-avatar pipeline locally
• demo a low-latency conversational digital human

When to choose

• you need a self-hosted real-time digital human with lip sync
• you want voice cloning and customizable avatar appearance
• you have a GPU (8GB+ for cascade, 20GB+ for end-to-end MLLM) and want low first-packet latency
• you want to swap in different ASR, LLM, or TTS components

When to avoid

• you have no GPU or limited VRAM
• you need a production-grade hosted service rather than a demo app
• you need non-Linux deployment support
• you want a polished no-code product instead of a Python/Gradio pipeline

Facets

application · maturity active

speech-recognition tts chatbot llm-inference agent-framework video-processing audio-processing machine-learning artificial-intelligence large-language-models speech-processing computer-vision chatbots deep-learning python self-hosted digital-human talking-head lip-sync voice-cloning real-time musetalk gradio asr thg multimodal linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Henry-23/VideoChat")