Skip to content

Hillobar/PersonalityPlex

 
 

Repository files navigation

PersonalityPlex: Chat with Managed Personalities

PersonalityPlex builds upon PersonaPlex to allow you to create (and share) Personalities that are used in PersonaPlex. PersonalityPlex provides the following features:

  • Voice cloning from ~10s audio clips
  • Create a library of Personalities
  • Talk to your Personalities
  • Make edits to you Personalities for better behavior
  • Clean UI
Screenshot 2026-02-14 110657
Main Screen
Screenshot 2026-02-14 110712
Personality Screen
Screenshot 2026-02-14 111218
Clone a Voice
Screenshot 2026-02-14 110743
Talk to your Personality

Installation

See the Full Installation Guide (venv) to get up and running.

Usage

First-Time Setup

  1. Open your browser and go to https://localhost:8998
  2. Click Settings at the bottom of the left sidebar
  3. Enter the paths for the three required models:
    • Moshi Weights - path to the language model checkpoint
    • Mimi Weights - path to the audio codec model
    • Text Encoder - path to the tokenizer model
  4. Click Save, then wait for loading to complete (the status indicator turns green when ready). This step will be skipped if the paths have already been set.

Creating a Voice Embedding

  1. In the left sidebar, click the dropdown menu and select Create a voice embedding
  2. Click Select audio file and choose a voice sample (~10 seconds or more)
  3. Enter a name for the embedding and click Generate Embedding
  4. Optionally, type some test text and click Test Embedding to hear a preview of the cloned voice
  5. The embedding will be stored in the ./Personalities/Embeddings folder

Creating a Personality

  1. In the left sidebar, click the dropdown menu and select Create new personality
  2. Fill in the personality details:
    • Avatar - click to upload a custom image
    • Name - give your personality a name
    • Role (System Prompt) - describe how the personality should behave (e.g. "You are a pirate captain who loves telling sea stories")
    • Embedding - select the voice embedding to use
  3. Adjust generation parameters if desired (text/audio temperature, topK, seed)
  4. Click Save
  5. The Personality will be stored in the ./Personalities folder (an exmple Personality for Pam Beasley can be found on the Release Page)

Talking to a Personality

  1. Click a personality in the left sidebar to select it
  2. Click Talk to your Personality
  3. Grant microphone permission when your browser prompts you
  4. Start speaking — the personality responds in real-time with audio and text
  5. The conversation is full-duplex, meaning you can speak and listen at the same time
  6. Click Disconnect when you're done

About

A refactor PersonaPlex to add managed Personalities

Resources

License

Stars

Watchers

Forks

Packages

 
 
 

Languages

  • Python 69.6%
  • TypeScript 29.9%
  • CSS 0.2%
  • HTML 0.1%
  • Dockerfile 0.1%
  • JavaScript 0.1%