Talk To AI with FastRTC enables natural, real-time voice conversations with AI using WebRTC, offering customizable voices, interfaces, and local or cloud-based API integration.

A simple POC of FastRTC, a framework to use voice mode in python!

Realtime voice-enabled AI assistant that can engage in natural conversations

Real-time conversational AI with voice cloning and emotion detection. Analyzes conversation context to deliver dramatically expressive responses using your cloned voice. Built with FastRTC and Chatterbox TTS for natural, emotionally-aware voice interactions.

A PyPI package that wraps Whisper.cpp for speech-to-text (STT) transcription, compatible with FastRTC

FastRTC implementation across few use cases. This is a basic initial version created only to demonstrate capabilities.

A FastRTC-compatible wrapper for Microsoft's [VibeVoice-Realtime-0.5B](https://huggingface.co/microsoft/VibeVoice-Realtime-0.5B) text-to-speech model, enabling real-time voice streaming in fastRTC

React component library for WebRTC voice chat, built on top of FastRTC.

Real Time ASR Interface (HISI)

Real-time speech-to-text and audio-capture demo using FastRTC, Gradio, and the ElevenLabs API.

The compact version of FastRTC, the realtime communication library for Python

A FastAPI-based backend service for my portfolio website featuring voice-enabled Retrieval Augmented Generation (RAG) capabilities.

DRIA V2 is a local-first Deep Research and Intelligence Agent. It combines a FastRTC voice UI, local llama.cpp-compatible reasoning, SearXNG search, self-hosted Firecrawl scraping, markdown agent skills, optional Anam avatar video, and background multi-agent research jobs into a Docker-ready personal AI workspace.

A FastRTC wrapper for the Kyutai Pocket TTS model

Build a real-time communication using Fasttrc, ollama, kokoro and etc

Simple voice agent using Gradio and FastRTC

Realtime voice + WhatsApp ordering agent — customers order by call, chat, or a photo of a handwritten list, in their own language.