---
license: mit
tags:
  - voice-activity-detection
  - silero
  - vad
  - coreml
  - apple-silicon
  - mlx-audio
base_model: snakers4/silero-vad
library_name: coreml
pipeline_tag: voice-activity-detection
---

# Silero VAD v6 (256ms) — CoreML for mlx-audio

CoreML conversion of Silero VAD v6 unified 256ms variant, used as the default
VAD pre-processor in [mlx-audio](https://github.com/Blaizzy/mlx-audio) for
hallucination prevention on long-form ASR (e.g. Cohere Transcribe on real-world
calls with silent intros / music outros).

## Variant

- **Architecture**: Silero v6 unified, 256ms (8 chunks of 32ms per inference)
- **Sample rate**: 16 kHz
- **Input shape**: `(1, 4160)` — 64 sample context + 4096 audio samples
- **Output**: speech probability (1,1,1) + new hidden_state + new cell_state
- **Compute**: `ALL` (ANE preferred, GPU/CPU fallback)
- **Size**: ~1 MB

## Performance (M-series Apple Silicon)

On 44 min English audio @ 16 kHz:
- Total VAD time: ~2.6 s (1017× real-time)
- Per-block latency: ~250 µs
- Detected 2304 s of speech, 358 s silence

## Source

Converted from [snakers4/silero-vad](https://github.com/snakers4/silero-vad)
(MIT) via the conversion tooling in
[beshkenadze/AudioEnhanceKit](https://github.com/beshkenadze/AudioEnhanceKit).
This is the same `silero_vad_v6_256ms_ios16.mlpackage` shipped in AEKit's
`scripts/coreml_output/`.

## Usage in mlx-audio

```python
from mlx_audio.stt import load
model = load("CohereLabs/cohere-transcribe-03-2026")
out = model.generate("call.wav", language="en", vad=True)  # uses this VAD
```

The model is loaded transparently by `cohere_asr.generate(vad=True)`. No manual
download or path is needed; mlx-audio falls back here when the bundled copy
isn't available, or when `MLX_AUDIO_SILERO_COREML` env var points elsewhere.

## License

The original Silero VAD model is released under the
[MIT License](https://github.com/snakers4/silero-vad/blob/master/LICENSE).
This conversion is published under the same MIT license.