Silero VAD - rapida.ai documentation

Silero VAD is a pre-trained ONNX model (~2 MB) for real-time voice activity detection. It is the default VAD provider in Rapida. Provider identifier: silero_vad

Source Location

api/assistant-api/internal/vad/internal/silero_vad/
├── silero_vad.go        # Main implementation
├── detector.go          # ONNX Runtime inference wrapper
├── models/
│   └── silero_vad_20251001.onnx   # Pre-trained model (~2 MB)

How It Works

Incoming LINEAR16 bytes are converted to float32 samples in the range [-1.0, 1.0]
Samples are fed to the Silero ONNX detector which produces speech segments with start/end timestamps
On speech onset, an InterruptionPacket is emitted (triggers barge-in)
On speech offset, an InterruptionPacket end event is emitted so EOS can release any pending final transcript

// Simplified flow
samples := linear16ToFloat32(pkt.Audio)
segments, _, _ := detector.Detect(samples)

if hasSpeechStart(segments) {
    callback(InterruptionPacket{...})   // barge-in
}
if hasSpeechEnd(segments) {
    callback(InterruptionPacket{...})   // end of active VAD speech
}

Parameters

Option Key	Default	Range	Description
`microphone.vad.confidence`	`0.7`	0.05–0.95	Speech probability threshold
`microphone.vad.start_secs`	`0.2`	0–2	Continuous speech duration before confirming speech start
`microphone.vad.stop_secs`	`0.2`	0–2	Continuous non-speech duration before confirming speech end

Internally, start_secs and stop_secs are rounded to Silero’s native frame windows: 512 samples at 16 kHz or 256 samples at 8 kHz.

Model Path

Source	Resolution
Environment variable	`SILERO_MODEL_PATH` — absolute path to the `.onnx` file
Default (Docker)	`./models/silero_vad/silero_vad_20251001.onnx`
Default (source)	`api/assistant-api/internal/vad/internal/silero_vad/models/silero_vad_20251001.onnx`

Local Source Setup

Silero VAD requires ONNX Runtime. The Docker base image includes it. For local builds:

# macOS (Homebrew)
brew install onnxruntime

# Linux — download from https://github.com/microsoft/onnxruntime/releases
# Extract and set:
export CGO_CFLAGS="-I/opt/onnxruntime/include"
export CGO_LDFLAGS="-L/opt/onnxruntime/lib -lonnxruntime"
export LD_LIBRARY_PATH="/opt/onnxruntime/lib:$LD_LIBRARY_PATH"

The model file is checked into the repository — no download needed.