Open source / Modular digital-human conversations

OpenAvatarChat

A modular avatar-chat system with replaceable speech recognition, language-model, speech synthesis and avatar components.

Avatar chat · modular backends · browser frontendSelf-host required
View repository ↗
Source code</>

OpenAvatarChat

The unlock

Why this one is on the map.

Makes the complete conversational host pipeline inspectable across several avatar backends.

The clearest product signal is “Swap the face without rebuilding the conversation”. That interaction model—not a generic AI feature list—is the reason to compare it with the rest of this directory.

This is source code, not a hosted channel. You need to inspect, configure, and deploy it with your own keys and runtime before anything can broadcast.

How to read it

What happens when you open it.

Open the official destination and look for the current avatar chat · modular backends · browser frontend workflow. Controls, access and live activity can change after this editorial check.

Best for: Modular digital-human conversations

Access note: Read the repository setup and license before running. Hardware, model downloads and API access vary by project.

Sources & status

Keep the link, keep the caveat.

2026-09-05: Official README reviewed. Current architecture separates the WebUI; model, frontend and backend setup required. No demo conversation tested.

Explore similar projects

Suggest a correction ↗
← Back to the directory