ElatoAI is a real-time AI voice agent platform built around IoT hardware (ESP32) that enables continuous speech-to-speech conversations using state-of-the-art multimodal voice models with minimal latency and global performance via edge computing. The system integrates voice synthesis and recognition by connecting an ESP32 device through secure WebSockets to edge server functions written in Deno, allowing users to speak naturally with AI agents hosted through cloud APIs including OpenAI’s Realtime API, Gemini’s Live API, xAI’s Grok Voice Agent API, and others. It includes a web client (built with Next.js) for managing devices, controlling volume, and viewing conversation transcripts, while the hardware runs optimized firmware to deliver responses in near real time — even supporting >15-minute uninterrupted conversations.

Features

  • Real-time speech-to-speech AI conversations
  • ESP32 firmware with secure WebSocket connectivity
  • Support for multiple AI voice APIs
  • Next.js web control interface
  • OTA updates for hardware devices
  • Customized voice personalities and features

Project Samples

Project Activity

See All Activity >

Categories

Voice Assistants

License

MIT License

Follow ElatoAI

ElatoAI Web Site

Other Useful Business Software
Cut Data Warehouse Costs by 54% Icon
Cut Data Warehouse Costs by 54%

Easily migrate from Snowflake, Redshift, or Databricks with free tools.

BigQuery delivers 54% lower TCO with exabyte scale and flexible pricing. Free migration tools handle the SQL translation automatically.
Try Free
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of ElatoAI!

Additional Project Details

Programming Language

TypeScript

Related Categories

TypeScript Voice Assistants

Registered

2026-01-27