From aff09d0e49ff8ddde0cd451598a9d364f29e3d4d Mon Sep 17 00:00:00 2001
From: mk <mk>
Date: Tue, 24 Mar 2026 00:02:17 -0300
Subject: [PATCH] fix: use Silero v5 model for 32ms frames and lower default
 thresholds

The legacy model is hardcoded to 1536 samples (96ms frames); v5 uses 512
samples (32ms), reducing gate open latency by 3x. Also lower default
positive/negative thresholds to 0.2/0.1 so the gate opens at the first
sign of speech rather than waiting for high model confidence.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---
 src/livekit/SileroVADGate.ts | 4 +++-
 src/settings/settings.ts     | 4 ++--
 vite.config.ts               | 4 ++++
 3 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/src/livekit/SileroVADGate.ts b/src/livekit/SileroVADGate.ts
index 101f8f1f..5a951d5e 100644
--- a/src/livekit/SileroVADGate.ts
+++ b/src/livekit/SileroVADGate.ts
@@ -61,7 +61,9 @@ export class SileroVADGate {
     ort.env.wasm.numThreads = 1;
 
     this.vad = await MicVAD.new({
-      ...getDefaultRealTimeVADOptions("legacy"),
+      // v5 model uses 512-sample frames (32ms) vs legacy's fixed 1536 (96ms),
+      // giving 3× faster gate response at the cost of a slightly larger model file.
+      ...getDefaultRealTimeVADOptions("v5"),
       audioContext,
       baseAssetPath: VAD_BASE_PATH,
       onnxWASMBasePath: VAD_BASE_PATH,
diff --git a/src/settings/settings.ts b/src/settings/settings.ts
index f097510e..c609812a 100644
--- a/src/settings/settings.ts
+++ b/src/settings/settings.ts
@@ -147,9 +147,9 @@ export const noiseGateRelease = new Setting<number>("noise-gate-release", 150);
 
 export const vadEnabled = new Setting<boolean>("vad-enabled", false);
 // Probability above which the VAD opens the gate (0–1)
-export const vadPositiveThreshold = new Setting<number>("vad-positive-threshold", 0.5);
+export const vadPositiveThreshold = new Setting<number>("vad-positive-threshold", 0.2);
 // Probability below which the VAD closes the gate (0–1)
-export const vadNegativeThreshold = new Setting<number>("vad-negative-threshold", 0.35);
+export const vadNegativeThreshold = new Setting<number>("vad-negative-threshold", 0.1);
 
 export const transientSuppressorEnabled = new Setting<boolean>(
   "transient-suppressor-enabled",
diff --git a/vite.config.ts b/vite.config.ts
index 5b64430b..c8236884 100644
--- a/vite.config.ts
+++ b/vite.config.ts
@@ -79,6 +79,10 @@ export default ({
           src: "node_modules/@ricky0123/vad-web/dist/silero_vad_legacy.onnx",
           dest: "vad",
         },
+        {
+          src: "node_modules/@ricky0123/vad-web/dist/silero_vad_v5.onnx",
+          dest: "vad",
+        },
         {
           src: "node_modules/onnxruntime-web/dist/*.wasm",
           dest: "vad",