Post

Voice Chat AI

Voice Chat AI

Voice Chat AI is a project that allows you to interact with different AI characters using speech. You can choose between various characters, each with unique personalities and voices. You can run all locally, you can use openai for chat and voice, you can mix between the two.

Ai-Speech

Features

  • Supports both OpenAI and Ollama language models: Choose the model that best fits your needs.
  • Provides text-to-speech synthesis using XTTS or OpenAI TTS or ElevenLabs: Enjoy natural and expressive voices.
  • No typing needed, just speak: Hands-free interaction makes conversations smooth and effortless.
  • Analyzes user mood and adjusts AI responses accordingly: Get personalized responses based on your mood.
  • You can, just by speaking, have the AI analyze your screen and chat about it: Seamlessly integrate visual context into your conversations.
  • Easy configuration through environment variables: Customize the application to suit your preferences with minimal effort.
  • WebUI or Terminal usage: Can be ran with either

Installation

Requirements

  • Python 3.10
  • CUDA-enabled GPU
  • Ollama models or Openai API for chat
  • XTTS or Openai API or ElevenLabs API for speech
  • Microsoft C++ Build Tools on windows
  • Microphone
  • A sense of humor

So I built this AI Speech app you can use either in the terminal or in a webui. You can talk with any character you want to make, it comes with some characters that I have made. You can see all the options to run the app in the .env file.

More details here: voice-chat-ai-github

Watch the Demos

Watch the video

Click on the thumbnail to open the video☝️

GPU - 100% local - ollama llama3, xtts-v2

Watch the video

Click on the thumbnail to open the video☝️


CPU Only mode CLI

Alien conversation using openai gpt4o and openai speech for tts.

Watch the video

Click on the thumbnail to open the video☝️


This post is licensed under CC BY 4.0 by the author.

© bigsk1. Some rights reserved.

AI | Tech | HomeLab | Crypto | Docker and more 🚀