Vibe Coding DiscoverElatoAI
View on GitHubRealtime Voice AI with 100+ Models on Arduino ESP32 with Secure Websockets and Edge Functions for AI Companions, and Devices
ElatoAI runs realtime speech-to-speech voice agents on ESP32/Arduino hardware via secure WebSockets and Deno/Cloudflare edge functions. It supports 100+ models (OpenAI Realtime, Gemini Live, Grok, ElevenLabs, Hume, Deepgram) plus a Next.js app for creating agents, managing devices, and transcripts.
Use Cases
Build voice AI companions and toys on ESP32 hardwareRealtime speech-to-speech conversation over secure WebSocketsCreate custom AI agents with distinct personalities and voicesSwitch between 100+ STT/LLM/TTS voice pipeline modelsManage and authenticate multiple ESP32 devicesOTA firmware updates and captive-portal WiFi setupTool calling from embedded devices to edge functionsDeploy low-latency global voice agents on Cloudflare Durable Objects
Built With
- Language
- TypeScript
- Frameworks
- Next.js · Deno · Cloudflare Workers · FastAPI · PlatformIO · Arduino · Supabase · Pipecat · Vercel
Tags
realtime-voice · speech-to-speech · esp32 · arduino · websockets · edge-functions · voice-agents · stt · tts · iot · cloudflare-workers · deno · tool-calling · opus-codec · ai-companions