# akdeb/ElatoAI

Realtime Voice AI with 100+ Models on Arduino ESP32 with Secure Websockets and Edge Functions for AI Companions, and Devices

Repository: https://github.com/akdeb/ElatoAI
Canonical: https://ross.abutalabs.com/products/elatoai
Homepage: https://www.elatoai.com
Language: TypeScript
License: NOASSERTION
License Family: other
Topics: ai, arduino, deno, esp32, hardware, openai, realtime, speech-to-speech, supabase, websocket, gemini, agents, elevenlabs, grok, cloudflare, hume, llm, stt, tts
Last push: 2026-08-19T14:57:56+00:00

## Health v2 (maintenance only)
Score: 64/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 35, longevity 36
- inputs: {"age_days": 512, "days_push": 14, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1933, forks 240 (observed 2026-08-28T04:05:56.302402+00:00)

## What it is
ElatoAI is an open-source platform for running realtime voice AI conversations on ESP32/Arduino hardware, supporting 100+ STT, LLM, and TTS models via secure WebSockets and edge functions. It enables building AI companions, talking toys, and voice-enabled devices with long (>20 minute) uninterrupted conversations.

## Use cases
- build a talking AI toy or plushie with realtime voice
- run speech-to-speech AI conversations on ESP32 hardware
- create an AI companion device with custom personalities
- stream STT, LLM, and TTS pipelines to embedded devices
- deploy low-latency voice AI globally with edge functions
- prototype voice assistants on Arduino with OpenAI Realtime API

## When to choose
- you want realtime voice AI on cheap ESP32 hardware
- you need long uninterrupted voice conversations with low latency
- you want flexibility across 100+ STT/LLM/TTS providers
- you are building AI toys, companions, or voice-enabled physical products

## When to avoid
- you need a purely software voice assistant with no hardware component
- you require a permissively licensed library for commercial embedding (license is non-standard)
- you need offline-only voice AI without cloud or edge services
- your target hardware is not ESP32/Arduino-based

## Facets
- artifact type: framework
- maturity: active
- function: speech-recognition, tts, llm-inference, agent-framework, websocket, chatbot, embedded
- domain: artificial-intelligence, speech-processing, iot, hardware, embedded-systems
- platform: embedded, iot, cross-platform, cpp
- tags: esp32, arduino, realtime-voice, speech-to-speech, supabase, edge-functions, openai-realtime-api, ai-toys, elevenlabs, pipecat, platformio, ai-agents, deno, web-server

## Member repositories
- akdeb/ElatoAI (main) score 64

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:56.302402+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:08:33.465442+00:00, confidence not recorded.
  - readme: https://github.com/akdeb/ElatoAI (fetched 2026-08-28T04:05:56.302402+00:00, sha 8d62b94fad33)
  - homepage: https://www.elatoai.com (fetched 2026-08-29T10:48:20.735456+00:00, sha e0eb5a8b0bdf)
  - site_page: https://www.elatoai.com/docs (fetched 2026-08-29T10:48:20.750433+00:00, sha 2a49db37eb28)
  - site_page: https://www.elatoai.com/home (fetched 2026-08-29T10:48:20.746416+00:00, sha 836ccdcb0aa1)
- Data as of 2026-08-30T08:39:29.467469+00:00.