Persona: Desktop 3D Avatar Companion for Voice Interactions

Repositoryxikhar/personaTool

Persona is an open-source Electron desktop app that gives real-time voice conversations an expressive 3D character presence. It captures output audio from selected applications to animate VRM models in real time.

Key points

  1. Core functionality: Listens to playback audio of specific processes and drives 3D avatar animations (VRM/VRMA) while speech is playing.
  2. Privacy-preserving design: Does not access microphones, transcribe speech, store audio, or transmit data over the network.
  3. Cross-platform audio capture: Integrates with Core Audio on macOS, WASAPI process-loopback on Windows, and PipeWire on Linux.
  4. Desktop overlay: Features transparent click-through windows for background desktop presence, with native click handling on Windows and macOS.
  5. Tech stack: Built with TypeScript, Electron, Node.js 24+, and hardware-accelerated 3D graphics.

Why it matters

As voice-based AI assistants proliferate on desktop systems, visual feedback is often lacking. Persona provides an unobtrusive, local-first visual persona that overlays the desktop without requiring custom integrations into the voice model itself.

Analysis

Persona targets users and creators of voice assistants or VTuber setups who want an expressive companion on their screen. The design choice to act purely as an audio output tap makes it agnostic to the underlying speech engine and keeps privacy intact. With nearly 1,000 GitHub stars, the codebase is functional and well-structured, though Linux window handling remains experimental.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Repository:jamiepine/voicebox

    Voicebox: Open-Source Local AI Voice Studio and Dictation Tool

    Voicebox is a local-first, open-source voice studio combining text-to-speech, voice cloning, and system-wide dictation. It serves as a self-hosted alternative to proprietary cloud solutions such as ElevenLabs and WisprFlow.

    55.6kstarsTypeScript

    AI & LLMs· Tool

  • Repository:nirholas/three.ws

    three.ws: Browser-Native 3D AI Agents via Three.js and MCP

    three.ws is an open-source platform designed to create and embed interactive 3D agents directly in the browser. It allows developers to turn text, images, or sketches into rigged GLB avatars, attach LLM reasoning via the Model Context Protocol (MCP), and embed them anywhere using a single Web Component.

    224starsJavaScript

    AI & LLMs· Tool

  • Repository:huggingface/speech-to-speech

    Hugging Face Speech to Speech: Modular Open-Source Voice Agent Pipeline

    Hugging Face has released speech-to-speech, a modular open-source framework designed to build voice agents with open-source models. The pipeline spans VAD, STT, LLM, and TTS, exposing the core OpenAI Realtime GA event set over WebSocket and WebRTC.

    13kstarsPython

    AI & LLMs· Tool

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.