Sunona: Next-generation voice AI infrastructure. Orchestrate intelligent, action-oriented voice agents that sound human and execute complex workflows via function calling. The faster way to build the future of talk.
# Sunona Voice AI <p align="center"> <strong>🎙️ Enterprise-Grade Voice AI Platform</strong><br> Build conversational voice assistants with real-time STT, LLM, and TTS </p> <p align="center"> <img src="https://img.shields.io/badge/Python-3.9+-blue.svg" alt="Python"> <img src="https://img.shields.io/badge/License-MIT-green.svg" alt="License"> <img src="https://img.shields.io/badge/Platform-Windows%20%7C%20Linux%20%7C%20macOS-lightgrey.svg" alt="Platform"> <img src="https://img.shields.io/github/stars/Sunona-AI-labs/sunona?style=social" alt="GitHub Stars"> </p> --- ## 🎬 Demo ### 🎤 Voice Assistant Examples https://github.com/user-attachments/assets/613a9942-7c3b-48ba-8a26-9f9614430424 > 🎙️ **This demo showcases Sunona's voice assistants** — `simple_assistant.py`, `voice_assistant.py`, and `text_only_assistant.py` with real-time STT, LLM, and TTS. --- ### 📞 Twilio Phone Call Demo https://github.com/user-attachments/assets/7f9da85f-72e3-4168-8021-eaf311e6fa3a > 📞 **This demo showcases Sunona's Twilio integration** — an AI campus recruiter (Priya) making real phone calls with voice conversation. ### 🔧 Required Setup to Replicate This Demo **1. Environment Variables (`.env`):** ```bash # LLM (Brain) - Primary: Groq (fastest), Fallback: OpenRouter GROQ_API_KEY=gsk_xxxxxxxx # https://console.groq.com/keys OPENROUTER_API_KEY=sk-or-v1-xxxxxxxx # https://openrouter.ai/keys (fallback) # STT (Ears) - https://console.deepgram.com/ DEEPGRAM_API_KEY=xxxxxxxx # TTS (Voice) - https://elevenlabs.io/app/settings/api-keys ELEVENLABS_API_KEY=xxxxxxxx # Telephony - https://www.twilio.com/console TWILIO_ACCOUNT_SID=ACxxxxxxxx TWILIO_AUTH_TOKEN=xxxxxxxx TWILIO_PHONE_NUMBER=+1xxxxxxxxxx TWILIO_WEBHOOK_URL=https://your-ngrok-url.ngrok-free.app # Ngrok (for local testing) - https://dashboard.ngrok.com/ NGROK_AUTH_TOKEN=xxxxxxxx ``` **2. Agent Configuration Used:** - **Config**: [`agent_data/example_recruiter/config_minimal.json`](agent_data/ex
HAL 分层混合模型工作流 — 强模型(Claude)负责理解/拆解/验收,低成本模型(DeepSeek)负责检索/提取/清洗。Hermes Agent skill。
An LLM agent fine-tuned on DeepSeek for spaced repetition, dynamically integrating knowledge points based on the Ebbinghaus forgetting curve.
基于 STM32F103 构建的端到端 AI 智能手表生态。自研“零重定位”原生机器码动态加载引擎与页面栈式 UI 框架;集成生产级 OTA 回滚保护机制与高带宽(921600 baud)串口协议栈。通过 Node.js 中继实现 DeepSeek AI 语义控制及 ASRPRO 语音全双工交互,是一个集成了分布式计算、现代存储管理与 AI Agent 的嵌入式全栈工程。
A Meta-Agent-Driven Self-Evolving Multi-Agent System for UAV Detection and Tracking
One command to run Hermes AI Agent with a browser UI. Zero prerequisites. 一行命令,AI 就位。
网页应用Agent,接入DeepSeek、Mimo等模型