microVAD

Self-contained voice activity detector (VAD) that uses the machine learning architecture from microWakeWord.

Installation

pip install pymicro-vad

Usage

from pymicro_vad import MicroVad

vad = MicroVad()
threshold = 0.5

# Process 10ms chunks of 16-bit mono PCM @16Khz
while audio := get_10ms_of_audio():  # you define this
    assert len(audio) == 160 * 2  # 160 samples
    speech_prob = vad.process_10ms(audio)
    if speech_prob < 0:
        print("Need more audio")
    elif speech_prob > threshold:
        print("Speech")
    else:
        print("Silence")

Building

Ensure you have python3-dev and build-essential installed.

Run script/setup to create a virtual environment, then script/build to build the extension locally.

Release files for pymicro-vad 2.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for pymicro-vad 2.1.0
File	Size	Uploaded
pymicro_vad-2.1.0.tar.gz	137.6 kB	Jun 29, 2026	Details

Built distributions (wheels)

Table of built distributions (wheels) for pymicro-vad 2.1.0
File	Interpreter	ABI	Platform	Reset
pymicro_vad-2.1.0-cp39-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl 96.8 kB Jun 29, 2026	CPython 3.9	abi3	Linux glibc 2.28+ x86-64, Linux glibc 2.27+ x86-64	Details
pymicro_vad-2.1.0-cp39-abi3-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl 93.4 kB Jun 29, 2026	CPython 3.9	abi3	Linux glibc 2.28+ ARM64, Linux glibc 2.27+ ARM64	Details

Total release size: 327.8 kB

Release files / pymicro_vad-2.1.0.tar.gz

Download URL	pymicro_vad-2.1.0.tar.gz
Size	137.6 kB
Tags	Source
SHA-256 checksum How to use checksums	`df954c56227f8696cf0553bd61df4aa583c914ec5c49a14682c9472130ab1a79`
BLAKE2b-256 checksum How to use checksums	`6de3cf037e7b8a42bdc7d231d9cb363789538871fc000c242b0308691216dd23`
Upload date	Jun 29, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.13.12`

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/rhasspy/pymicro-vad
Publishing commit: github.com/rhasspy/pymicro-vad/tree/32bc8dd0dfbeacbb6f777dfc6ead3998a621c24b

Workflow

Publishing configuration: github.com/rhasspy/pymicro-vad/blob/32bc8dd0dfbeacbb6f777dfc6ead3998a621c24b/.github/workflows/publish.yml
Publishing logs: github.com/rhasspy/pymicro-vad/actions/runs/28393345092/attempts/1

Artifact

Subject: pymicro_vad-2.1.0.tar.gz
SHA-256 checksum: df954c56227f8696cf0553bd61df4aa583c914ec5c49a14682c9472130ab1a79 Verifying attestations

Release files / pymicro_vad-2.1.0-cp39-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl

Download URL	pymicro_vad-2.1.0-cp39-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
Size	96.8 kB
Tags	CPython 3.9 Linux glibc 2.27+ x86-64 Linux glibc 2.28+ x86-64 abi3
SHA-256 checksum How to use checksums	`a99894b0eb58e713aceff2503ba371e3816801a30b3c60443bd39d22b8699e64`
BLAKE2b-256 checksum How to use checksums	`0a2acea4a6be9ade4c9ac3cde65a4a8a7d7b5d789267c3ec69b54316323b5e1c`
Upload date	Jun 29, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.13.12`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/rhasspy/pymicro-vad
Publishing commit: github.com/rhasspy/pymicro-vad/tree/32bc8dd0dfbeacbb6f777dfc6ead3998a621c24b

Workflow

Publishing configuration: github.com/rhasspy/pymicro-vad/blob/32bc8dd0dfbeacbb6f777dfc6ead3998a621c24b/.github/workflows/publish.yml
Publishing logs: github.com/rhasspy/pymicro-vad/actions/runs/28393345092/attempts/1

Artifact

Subject: pymicro_vad-2.1.0-cp39-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
SHA-256 checksum: a99894b0eb58e713aceff2503ba371e3816801a30b3c60443bd39d22b8699e64 Verifying attestations

Release files / pymicro_vad-2.1.0-cp39-abi3-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl

Download URL	pymicro_vad-2.1.0-cp39-abi3-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl
Size	93.4 kB
Tags	CPython 3.9 Linux glibc 2.27+ ARM64 Linux glibc 2.28+ ARM64 abi3
SHA-256 checksum How to use checksums	`873ebdf97de6fed7ed30ec815b00b21e4b15a72e64b70fbe9c133571646d0e0c`
BLAKE2b-256 checksum How to use checksums	`b4720b5e5e1b664ce0a20594a796bb8175227661412b853d8f8a57cd4d7f627f`
Upload date	Jun 29, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.13.12`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/rhasspy/pymicro-vad
Publishing commit: github.com/rhasspy/pymicro-vad/tree/32bc8dd0dfbeacbb6f777dfc6ead3998a621c24b

Workflow

Publishing configuration: github.com/rhasspy/pymicro-vad/blob/32bc8dd0dfbeacbb6f777dfc6ead3998a621c24b/.github/workflows/publish.yml
Publishing logs: github.com/rhasspy/pymicro-vad/actions/runs/28393345092/attempts/1

Artifact

Subject: pymicro_vad-2.1.0-cp39-abi3-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl
SHA-256 checksum: 873ebdf97de6fed7ed30ec815b00b21e4b15a72e64b70fbe9c133571646d0e0c Verifying attestations