Documentation Index
Fetch the complete documentation index at: https://doc.rapida.ai/llms.txt
Use this file to discover all available pages before exploring further.
Voice Activity Detection (VAD) runs on every audio frame before STT. It determines whether the caller is speaking, emits interruption signals for barge-in, and sends speech activity heartbeats that keep the End of Speech timer from firing during active speech.
All three VAD providers run locally using ONNX or native C libraries. No external API calls, no credentials, no added latency.
VAD Interface
Every provider implements the Vad interface:
// api/assistant-api/internal/type/vad.go
type Vad interface {
Name() string
Process(ctx context.Context, pkt UserAudioPacket) error
Close() error
}
Factory Function
// api/assistant-api/internal/vad/vad.go
func GetVAD(ctx, logger, callback, options) (Vad, error)
microphone.vad.provider from the assistant’s audio options and returns the matching implementation. If no provider is set, Silero VAD is used as the default.
Provider Identifiers
| Identifier | Provider | Model |
|---|
silero_vad | Silero VAD | silero_vad_20251001.onnx (~2 MB) |
ten_vad | TEN VAD | Native C library (no model file) |
firered_vad | FireRed VAD | fireredvad_stream_vad_with_cache.onnx (~5 MB) |
Shared Parameters
All three providers use the same configuration keys:
| Option Key | Type | Default | Description |
|---|
microphone.vad.provider | string | silero_vad | Provider selection |
microphone.vad.threshold | float | 0.5 | Speech probability threshold (0.3–1.0). Lower = more sensitive. |
microphone.vad.min_silence_frame | float | 20 | Consecutive silence frames before ending a speech segment. Each frame = 10 ms. Default 20 = 200 ms. |
microphone.vad.min_speech_frame | float | 8 | Consecutive speech frames before confirming speech onset. Each frame = 10 ms. Default 8 = 80 ms. |
Model Files
VAD models are bundled in the Docker image at build time. For source builds, models are resolved from the source tree relative to each provider’s Go package directory.
Docker
Models are copied into the runtime image and referenced via environment variables:
SILERO_MODEL_PATH=./models/silero_vad/silero_vad_20251001.onnx
FIRERED_VAD_MODEL_PATH=./models/firered_vad/fireredvad_stream_vad_with_cache.onnx
LD_LIBRARY_PATH="/opt/ten_vad/lib:..."
From Source
When running go run cmd/assistant/assistant.go, each provider resolves its model path using runtime.Caller to find the source directory:
| Provider | Default path (relative to package dir) |
|---|
| Silero VAD | api/assistant-api/internal/vad/internal/silero_vad/models/silero_vad_20251001.onnx |
| FireRed VAD | api/assistant-api/internal/vad/internal/firered_vad/models/fireredvad_stream_vad_with_cache.onnx |
| TEN VAD | No model file — requires libten_vad.so in the library path |
LD_LIBRARY_PATH / DYLIB_LIBRARY_PATH.
To override model paths, set the environment variables:
export SILERO_MODEL_PATH=/path/to/silero_vad.onnx
export FIRERED_VAD_MODEL_PATH=/path/to/fireredvad.onnx
CGO Dependencies
All VAD providers use CGO for inference:
| Provider | CGO dependency | Build flags |
|---|
| Silero VAD | ONNX Runtime (libonnxruntime) | -I/opt/onnxruntime/include -L/opt/onnxruntime/lib -lonnxruntime |
| FireRed VAD | ONNX Runtime (libonnxruntime) | Same as Silero |
| TEN VAD | TEN VAD library (libten_vad) | -I/opt/ten_vad/include -L/opt/ten_vad/lib -lten_vad |
rapidaai/rapida-golang) includes all CGO dependencies pre-installed. For local source builds, you need ONNX Runtime and the TEN VAD shared library installed on your system.
Providers
| Provider | Approach | Best for |
|---|
| Silero VAD | ONNX model, 100+ languages | General purpose — the default |
| TEN VAD | Native C library, 16 ms frame hops | Lowest per-frame latency |
| FireRed VAD | DFSMN model, 4-state postprocessor | Noisy environments, precise boundaries |
