Catalogue

Framework

LiveKit Agents

Voice

livekit

Framework for building realtime, server-side voice agents with pluggable STT, LLM, and TTS and WebRTC/telephony support

webrtctelephonyreal-timestt

Tool

Supabase

MemoryDeployment

supabase

Open-source Postgres development platform with auth, auto-generated APIs, realtime, storage, and a vector toolkit

postgresreal-timeauthpgvector

Tool

LiveKit

VoiceDeployment

livekit

WebRTC transport and infrastructure for real-time audio/video agents.

webrtcsfureal-timetelephony

Framework

Pipecat

Voice

pipecat-ai

Python framework for real-time voice and multimodal conversational agents, with composable pipelines over WebSockets or WebRTC

real-timemultimodalwebrtcvoice-agent

Tool

AgentRQ

Interface

agentrq

AgentRQ: Human-in-loop realtime conversational task manager for AI Agents.

productivityhuman-in-the-looptask-managementreal-timemobile

Tool

OpenLive

VoiceGenerative Media

katipally

Opensource, on-device voice + vision layer for AI agents. Bring any model or coding agent; the whole speech loop (VAD, STT, TTS, barge-in) r

sttttsbarge-invoice-cloning

Tool

Inworld

VoiceGenerative MediaTraining

inworld-ai

Realtime speech-to-speech and expressive TTS-2 text-to-speech.

ttsfine-tunespeech-to-speechreal-time

Ably AI Transport

Deployment

Managed realtime transport keeping agent/LLM streaming sessions continuous and resumable across disconnects and devices.

real-timewebsocketsession-continuitystreaming

AI Coustics

Voice

Real-time speech enhancement and standalone voice-activity detection for agent audio streams.

audiospeech-enhancementvoice-activity-detectionreal-timeaudio-processing

Tool

Anam

VoiceGenerative Media

Real-time video-avatar service synchronising audio and video.

videoavatarlip-syncreal-timechatbot

AssemblyAI

Voice

Real-time and file speech-to-text via AssemblyAI's Universal models.

sttreal-timevoice-agent

Async

VoiceGenerative Media

Text-to-speech via Async's WebSocket and HTTP APIs.

ttswebsocketreal-timelow-latency

Beyond Presence

VoiceGenerative Media

Real-time video-avatar transport for voice agents.

videoavatarreal-timelivekit

Cartesia

VoiceGenerative Media

Real-time speech-to-text and text-to-speech via Cartesia's streaming APIs.

ttssttreal-timestreaming

App

Claw3D

InterfaceMonitoring

iamlukethedev

Self-hosted 3D virtual office that visualizes AI agents reviewing code, running standups, and executing tasks in real time

virtual-world3d-visualizationlocal-firstreal-time

Daily

Voice

WebRTC transport for real-time audio/video agent communication.

videowebrtcpipecatreal-time

Deepgram

VoiceGenerative Media

Real-time speech-to-text (Nova/Flux) and Aura text-to-speech.

sttttsreal-time

App

Doit

Interface

erasmus

iOS app for Hermes agents where you create a todo, hand it to an agent, and watch the work stream back in real time

iosmobiletask-managementreal-time

Gladia

Voice

Real-time speech-to-text via Gladia's live API.

sttapimultilingualreal-time

Gradium

VoiceGenerative Media

Low-latency streaming speech-to-text and text-to-speech via Gradium.

sttttsreal-timevoice-cloning

Krisp VIVA

Voice

Audio voice-isolation filter using Krisp's VIVA model.

voice-isolationnoise-reductionreal-timemeeting-assistant

LemonSlice

VoiceGenerative Media

AI-avatar video service for adding LemonSlice avatars to real-time rooms.

videoavatarreal-timeapi

OpenChat

Interface

Hosted social network where AI agents post, follow, and connect with other agents in real time

social-mediareal-time

Pinch

VoiceGenerative Media

Real-time speech-to-speech translation for voice agents.

translationdubbingreal-timespeech-to-speech