End-to-end realtime stack for connecting humans and AI

The open-source voice synthesis studio powered by Qwen3-TTS.

Production ready toolkit to run AI locally

Open Vision Agents by Stream. Build Vision Agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.

The Self-Coding System for Your App — Alan AI SDK for Web

The Self-Coding System for Your App — Alan AI SDK for iOS

The Self-Coding System for Your App — Alan AI SDK for Flutter

The Self-Coding System for Your App — Alan AI SDK for Ionic

Just a Better Chatbot. Powered by Agent & MCP & Workflows.

Optimized Whisper models for streaming and on-device use

Rapida is an open-source, end-to-end voice AI orchestration platform for building real-time conversational voice agents with audio streaming, STT, TTS, VAD, multi-channel integration, agent state management, and observability.

100M parameter lightweight conversational text-to-speech model with breaths, laughter, multi-speaker dialogue, voice cloning, and streaming. Llama-based, on-device.

The Self-Coding System for Your App — Alan AI SDK for React Native

Worlds first open-source real-time end-to-end spoken dialogue model with personalized voice cloning.

Make your meetings accessible to AI Agents

Leverage the OpenAI Realtime API (12-17-2024) with this Next.js 15 starter template featuring shadcn/ui components, tool-calling & localization. Use starter to build Voice AI apps with WebRTC.

The Self-Coding System for Your App — Alan AI SDK for Power Apps

Official Python SDK for Deepgram.

🎙️ Speak with AI - Run locally using Ollama, OpenAI, Anthropic or xAI - Speech uses SparkTTS, OpenAI, ElevenLabs or Kokoro

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.

Official JavaScript SDK for Deepgram.

PlayHT Python SDK - AI Text-to-Speech Streaming & Voice Cloning API

Full stack voice chatbot

Sayna is a unified Voice Layer for AI Agents with a seemless integration to an existing agentic frameworks

Self-hosted AI voice agent

Voice AI components using OpenAI Realtime API to copy and paste into your Nextjs projects built with TailwindCSS for building modern Voice AI applications with WebRTC.

Python sdk for Murf text to speech API

Recipes for on-device voice AI and local LLM

Vapi Blocks is a library of components & api snips to copy and paste into React applications built with TailwindCSS for integrating Voice AI into your application using Vapi.ai. Vapi let's you develop voice AI fast, Vapi Blocks helps you implement faster.

Official Go SDK for Deepgram.