pheonix-delta/axiom-voice-agent
Run a <400ms latency Voice Agent on just 4GB VRAM. Fully offline, no API keys required. Optimized for GTX 1650 and edge robotics with zero-copy inference. (Apache 2.0)
Combines SetFit-based intent classification with semantic RAG and Sherpa-ONNX speech models (Parakeet STT, Kokoro TTS) in a FastAPI WebSocket pipeline. Features zero-copy inference that streams tensors directly between STT and LLM stages, alongside interactive 3D WebGL visualization and multi-turn conversation history management for robotics lab environments.
Stars
68
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 22, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/pheonix-delta/axiom-voice-agent"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
labring/FastGPT
FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of...
RunanywhereAI/RCLI
Talk to your Mac, query your docs, no cloud required. On-device voice AI + RAG
ragpi/ragpi
🤖 An open-source AI assistant answering questions using your docs
theaiautomators/insights-lm-local-package
Open-source, fully private and local alternative to NotebookLM. Chat with your documents,...
AstraBert/PapersChat
An agentic AI application that allows you to chat with your papers and gather also information...