syntithenai/hermod
voice services stack from audio hardware through hotword, ASR, NLU, AI routing and TTS bound by messaging protocol over MQTT
# Technical Summary for Hermod Microservices architecture using MQTT as the central bus, enabling modular deployment across single containers or distributed ARM devices like Raspberry Pi; services run in a single-threaded asyncio event loop optimized for resource-constrained hardware. Integrates RASA for intent/slot extraction and dialogue management, supports multiple ASR backends (Deepspeech, IBM Watson, Google), and includes a vanilla JavaScript web client using MQTT over WebSockets for browser-based voice interaction. Offers both offline-capable local deployments and cloud-connected configurations, with Docker Compose for multi-container orchestration and pre-built RASA models for Wikipedia search tasks.
No commits in the last 6 months.
Stars
93
Forks
21
Language
Python
License
—
Category
Last pushed
Jul 21, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/syntithenai/hermod"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
asiff00/On-Device-Speech-to-Speech-Conversational-AI
This is an on-CPU real-time conversational system for two-way speech communication with AI...
VideotronicMaker/LM-Studio-Voice-Conversation
Python app for LM Studio-enhanced voice conversations with local LLMs. Uses Whisper for...
voice-engine/make-a-smart-speaker
A collection of resources to make a smart speaker
FR33TR1ST/VoiceAssistant
A VoiceAsistant with WhisperAI speech recognition
bold-ronin/lira
A Voice-First AI Companion