Conversational voice AI agents
Hermes Agent TTS and STT plugin for AllModels speech models and voices.
An open-source AI voice agent platform that turns conversations into 100% accurate, user-verified data via a visual form.
Full-stack LiveKit voice agent starter: a Python voice worker, FastAPI token server, and React frontend. Run, deploy, and swap each piece on its own. Ask for ShipVoice pro
Voice agent using LiveKit (orchestration), Cartesia (STT + TTS), and OpenAI (LLM)
Composite voice agent SDK with no extra infra requirements. Supports browser-native STT/TTS features.
StandIn: put your AI agent into Microsoft Teams calls as a real participant, in your own tenant. agent backends (OpenClaw, Hermes Agent, LiveKit, ElevenLabs, OpenAI Realtime, Deepgram, Cartesia)
Speakeasy: free, self-hostable generator for voicemail greetings, on-hold messages, and IVR prompts. Cartesia Sonic 3.5 TTS with voice cloning, 56 royalty-free background tracks, and client-side audio mixing. Bring your own API key. No signup, no paywall.
Live AI judge agent — watches hackathon demos in real-time via Gemini Live API, delivers British-accented commentary via TTS, scores with multi-model ensemble (Gemini + Claude + Groq), detects prompt injection attempts, and runs cross-team deliberation. Built for NEBULA:FOG 2026.
Onepin Python SDK + CLI — orchestrate, validate & ship production-ready voice audio across 100+ TTS models
🗣️ Build an interactive voice agent that leverages Speech-to-Text, a Large Language Model, and Text-to-Speech for real-time voice interactions.
Home Assistant custom integration for the Cartesia Sonic text-to-speech API
🎙️ Real-time AI Voice Assistant built with LiveKit Agents framework. Features smart home temperature control with natural voice interaction. Powered by Groq (STT/LLM) and Cartesia (TTS) - 100% free tier compatible!
📞 An always-on AI voice agent that answers a real phone and books clinic appointments end-to-end — real-time speech-to-speech at ~1.3s response latency. Built with Pipecat · Claude · Deepgram · Cartesia · LiveKit SIP, deployed 24/7 on Railway.
TypeScript starter kit for production voice agents: WebRTC, telephony, realtime model APIs, STT/TTS pipelines, barge-in, handoff, evals, and post-call workflows.
AI voice agent that joins online meetings in real-time. Driverless browser automation + Speech-to-Speech (Gemini/Deepgram) + Visual awareness + Meeting memory. No virtual audio drivers needed.
An autonomous voice agent that conducts real outbound sales calls for e-commerce website development.
To associate your repository with the cartesia topic, visit your repo's landing page and select "manage topics."