TelBuddy

FrontDeskOS is an AI virtual receptionist that answers calls, books appointments, and captures leads 24/7. It aims to reduce missed calls and increase bookings without requiring additional staff or hardware. The system integrates with existing business processes to provide automated front desk support. It helps businesses avoid losing potential revenue from unanswered calls.

AlwaysReddy is an LLM voice assistant accessible via a hotkey. It is designed as a personal project to improve programming skills. The creator encourages users to identify issues and suggest improvements to the code.

JARVIS is a personal voice assistant that converts voice to text, uses an LLM to generate a response, and converts the response to speech. It is displayed in a web interface and uses tools like Deepgram, OpenAI, and ElevenLabs. JARVIS is open-source and free to use.

ASR-LLM-TTS is a speech interaction system built on an open-source model. It integrates Automatic Speech Recognition (ASR), Large Language Models (LLM), and Text-to-Speech (TTS) in sequence. The ASR model is SenceVoice, the LLM models are QWen2.5-0.5B/1.5B, and the TTS models include CosyVoice, Edge-TTS, and pyttsx3.

aisearch-openai-rag-audio is a sample implementation of the VoiceRAG pattern. It powers interactive voice generative AI experiences using RAG with Azure AI Search and Azure OpenAI's gpt-4o-realtime-preview model. This tool allows developers to create voice-based applications.

Pipecat is an open-source Python framework for building real-time voice and multimodal conversational agents. It allows developers to orchestrate audio and video, integrate AI services, and manage different modalities. Pipecat is designed to simplify the creation of complex conversational AI applications.