Browse documentation

Modular Local AI Engine

For maximum privacy, Zaya includes a split modular pipeline that runs entirely on-device without any cloud internet calls:

Microphone → WebRTC VAD → faster-whisper → Local LLM (Ollama) → Piper ONNX → Speaker

Setup Steps

  1. Install local speech dependencies:
.\.venv\Scripts\python.exe -m pip install -r requirements-local-speech.txt
  1. Install Ollama and pull your model:
ollama run qwen2.5:14b
  1. In Zaya Settings > AI ENGINE, select LOCAL PIPELINE, choose Ollama, and supply your Piper ONNX model path.

Something unclear or not working?

Troubleshooting guide ↗Report a problem ↗