pymicro-vad

library2.0.1pypypi✓ verified 82d ago

Self-contained voice activity detector (VAD) for Python. Lightweight, no external dependencies, uses WebRTC VAD engine. Current version: 2.0.1, release cadence: irregular.

ai-ml devops

pip install pymicro-vad

github ↗homepage ↗

INSTALL

IMPORT

SIG · PYMICRO-VAD

pymicro-vad

ai-mlpythonv2.0.1

harness data pending

Install & Compatibility

Where this runs

No compatibility data collected yet for this library.

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

MicroVad

✓ from pymicro_vad import MicroVad

✗ from pymicro_vad import VAD

create_vad

✓ from pymicro_vad import create_vad

process_10ms

✓ from pymicro_vad import process_10ms

Creates a VAD instance and checks if a 10ms audio frame contains speech.

from pymicro_vad import VAD vad = VAD(sample_rate=16000) # Example: detect voice activity in a 16-bit PCM frame frame = b'\x00\x00' * 160 # 10ms at 16000 Hz is_voice = vad.is_speech(frame) print(is_voice)

Debug

Known issues

gotchaThe VAD expects raw PCM audio (16-bit little-endian) as bytes. Do not pass numpy arrays or floats without conversion.

fix

Convert audio to bytes using (array * 32767).astype('int16').tobytes() if using floats.

affects: all

gotchaFrame size must match the expected number of samples for the sample rate. For 16kHz, 10ms frames are 160 samples (320 bytes). Misaligned sizes cause silent false negatives.

fix

Ensure frame length in samples = sample_rate * 0.01 (e.g., 160 for 16kHz).

affects: all

Upgrade

Version history

2.0.1latest on PyPI · released Dec 16, 2025

Audit

Dependencies

No dependency data recorded yet.

Agent activity

16 hits · last 30 days

node

OpenAI (training)

Resources

githubhttps://github.com/rhasspy/pymicro-vad ↗

homepagehttps://github.com/rhasspy/pymicro-vad ↗