Silero VAD does not require a GPU for installation or operation. It is specifically designed to run efficiently on the CPU, and by default, it uses the CPU for inference (

force_cpu=True

). For installation in a Python environment, use the following command:

pip install "livekit-agents[silero]~=1.0"

Requirements include: • Python >= 3.9 • onnxruntime >= 1.18 • numpy >= 1.26 • livekit-agents >= 1.1.5 Be sure to download the model weights before your first use:

python agent.py download-files

If you encounter installation issues, please share the specific error message for further assistance. Sources: examples/voice_agents/structured_output.py | Silero VAD plugin | LiveKit Docs

I don't have the answer you're looking for. You could also try asking your question: • in one of the other Slack channels or • to https://deepwiki.com/livekit/livekit_composite which is trained on all LiveKit source code If you find the answer, please post it here to help others!