Your personal voice interface for any app. Speak naturally and your words appear wherever your cursor is, with fully customizable AI voice dictation. Open source alternative to Wispr Flow.

Build Agentic AI solutions on AWS, using latest OSS Agentic Frameworks.

Fully autonomous speaking bots built using the MeetingBaas API and Pipecat.

This repository shows you how to build real-time, voice-enabled AI agents with Pipecat and Amazon Bedrock

Telephony Server is a powerful bridge that connects telephony providers (Twilio, Vonage, Plivo, etc.) with real-time communication platforms (LiveKit, Jay.so, Pipecat, etc.). It enables seamless call routing, robust metrics collection, and observability features for enhanced telephony operations.

An AI voice agent to help you call your political representatives.

Voice-first AI agent with persistent memory, background reflection, and hierarchical summarization.

A Pipecat Starter Kit that uses the Pipecat React Pipecat SDK and Vapi Blocks

A telephonic game to discover who likes you, using Pipecat, Pipecat Cloud, Gemini Multimodal Live, and Twilio.

YC Gemini X Pipecat hackathon live agent for iOS utilzing pipecat.

Simple llm function calling with Gemini Multimodal Live, multiple llm prompts (parallel pipecat pipelines), and a smidge of whimsy.

Demonstrates a real-time voice agent that answers a basic support inquiry (case status) and conditionally allows escalation based on explicit decision rules. The goal is to show how voice interaction, AI reasoning, and policy-based decisioning can be cleanly separated in a minimal, easy-to-understand setup.

just another weather bot tool-calling demo using Pipecat AI & Gemini Multimodal Live API

A real-time Swedish voice assistant demo built with Pipecat and Evroc cloud services.

A Pipecat AI Assistant integration example with Nextgenswitch SIP Server

Voice controlled AI assistant with a lot of functions to extend functionality

Real-time voice AI agent built with Pipecat, featuring RAG knowledge retrieval and MCP tool integration. Sub-400ms latency with Deepgram STT, Claude LLM, and Cartesia TTS.

Python SDK for Shunyalabs Real-Time, Batch, Flow, and TTS APIs - Pipecat

Research and dev into the Multimodal LLMs, and utilizing them to create Real time interaction applications.

demo app for voice transcription and sentiment analysis using pipecat and Cartesia voice api