StarmoonAI/Starmoon
A conversational, AI device + software framework for companionship, entertainment, education, healthcare, IoT applications, and DIY robotics. Built with Python, NextJS, Arduino, ESP32, LLMs (GPT-4o), Deepgram STT and Azure TTS 🤖
**Technical Summary:** Implements real-time bidirectional voice AI on resource-constrained ESP32-S3 devices using I2S audio peripherals for simultaneous microphone input and speaker output, with emotion detection via conversational analysis. The backend integrates GPT-4o for inference, Deepgram for speech-to-text, and Azure TTS for audio synthesis, while a NextJS web dashboard provides device management and custom character configuration. Architecture supports local WiFi provisioning and API-based authentication, enabling fully self-hosted deployments with end-to-end encryption for privacy-sensitive applications.
544 stars. No commits in the last 6 months.
Stars
544
Forks
62
Language
TypeScript
License
GPL-3.0
Category
Last pushed
Feb 25, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/StarmoonAI/Starmoon"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
tuya/TuyaOpen
Next-gen AI+IoT framework for T2/T3/T5AI/ESP32/and more – Fast IoT and AI Agent hardware integration
OpenMOSS/MOSS
An open-source tool-augmented conversational language model from Fudan University
sekift/so-vits-models
收集有关so-vits-svc、TTS、SD、LLMs的各种模型、应用以及文字、声音、图片、视频有关的model。
derdacavga/Esp32-Ai-Voice-Assistant
In this project I will share with you Complately Free Ai Voice Support Assistant. You can build...
small-cactus/M.I.L.E.S
M.I.L.E.S, a GPT-4-Turbo voice assistant, self-adapts its prompts and AI model, can play any...