AI voice assistant

voice-chat-pdf is an example based on the LlamaIndex project and built using Next.js. It allows users to interact with PDF documents through voice through a simple RAG system. This project requires an OpenAI API key to access the real-time API and generate embedding vectors of documents within the project for voice interaction. It demonstrates how advanced machine learning techniques can be applied to improve the efficiency and convenience of document interaction.

LiveKit Agents is an end-to-end framework that enables developers to build intelligent multi-modal voice assistants (AI agents) that can interact with users through voice, video and data channels. It provides a quick start guide to creating voice assistants by integrating OpenAI's real-time API and LiveKit's WebRTC infrastructure, including pipelines for speech recognition (STT), language models (LLM), and text-to-speech (TTS). Additionally, it supports the ability to create voice-to-voice agents, answer and respond to incoming calls, and make calls on behalf of users.

Open-LLM-VTuber is an open source project designed to interact with large language models (LLM) via speech, with real-time Live2D facial capture and cross-platform long-term memory capabilities. The project supports macOS, Windows, and Linux platforms, allowing users to choose from different speech recognition and speech synthesis backends, as well as custom long-term memory solutions. It is particularly suitable for developers and enthusiasts who want to implement natural language conversations with AI on different platforms.