Silero VAD v5

Silero VAD v5 — a lightweight voice activity detection model in ONNX format, packaged for use with the RunAnywhere SDK.

Format: Single ONNX file (~2.2 MB)

Usage with RunAnywhere SDK

Swift (iOS / macOS)

import RunAnywhere

RunAnywhere.registerModel(
    id: "silero-vad-v5",
    name: "Silero VAD v5",
    url: URL(string: "https://huggingface.co/runanywhere/silero-vad-v5/resolve/main/silero_vad.onnx")!,
    framework: .onnx,
    modality: .audio,
    memoryRequirement: 5_000_000
)

// Use VAD in voice pipeline
let isVoice = try await RunAnywhere.detectVoiceActivity(audioChunk, modelId: "silero-vad-v5")

Kotlin (Android / JVM)

import com.runanywhere.sdk.RunAnywhere
import com.runanywhere.sdk.models.*

RunAnywhere.registerModel(
    id = "silero-vad-v5",
    name = "Silero VAD v5",
    url = "https://huggingface.co/runanywhere/silero-vad-v5/resolve/main/silero_vad.onnx",
    framework = InferenceFramework.ONNX,
    modality = ModelCategory.AUDIO,
    memoryRequirement = 5_000_000L
)

val isVoice = RunAnywhere.detectVoiceActivity(audioChunk, modelId = "silero-vad-v5")

Web (TypeScript)

import { RunAnywhere, LLMFramework, ModelCategory } from '@anthropic/runanywhere-web';

RunAnywhere.registerModels([{
  id: 'silero-vad-v5',
  name: 'Silero VAD v5',
  url: 'https://huggingface.co/runanywhere/silero-vad-v5/resolve/main/silero_vad.onnx',
  files: ['silero_vad.onnx'],
  framework: LLMFramework.ONNX,
  modality: ModelCategory.Audio,
  memoryRequirement: 5_000_000,
}]);

await RunAnywhere.downloadModel('silero-vad-v5');
await RunAnywhere.loadModel('silero-vad-v5');

React Native (TypeScript)

import { RunAnywhere } from 'runanywhere-react-native';

RunAnywhere.registerModel({
  id: 'silero-vad-v5',
  name: 'Silero VAD v5',
  url: 'https://huggingface.co/runanywhere/silero-vad-v5/resolve/main/silero_vad.onnx',
  framework: 'onnx',
  modality: 'audio',
  memoryRequirement: 5_000_000,
});

Flutter (Dart)

import 'package:runanywhere_flutter/runanywhere_flutter.dart';

RunAnywhere.registerModel(
  id: 'silero-vad-v5',
  name: 'Silero VAD v5',
  url: 'https://huggingface.co/runanywhere/silero-vad-v5/resolve/main/silero_vad.onnx',
  framework: InferenceFramework.onnx,
  modality: ModelCategory.audio,
  memoryRequirement: 5000000,
);

Model Details

Attribution

Original model by Silero Team.