webrtcvad
Python interface to the Google WebRTC Voice Activity Detector (VAD)
Decision gist · record as of 2026-08-14
Yes, with conditions. The underlying WebRTC VAD algorithm is mature and well-regarded. However, high install friction (compiled extension), dormancy since 2017-01-07, and uncertainty about modern Python compatibility mean you should verify it builds on your target platform and consider whether a more recently maintained alternative better suits your needs before committing.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires 16-bit mono PCM audio at 8000, 16000, or 32000 Hz; frame duration must be 10, 20, or 30 ms.
- Compilation of C extension may require build tools and development headers.
- High install friction due to compiled C extension dependency (webrtcvad-2.0.10.tar.gz).
License · maintenance · safety
MIT (permissive) — MIT license (permissive) imposes no significant restrictions on use, modification, or distribution in commercial or private projects.
last release 2017-01-07 (3506 days) · last repo commit 2024-07-04 · 2,497 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 480,417 downloads/mo, #6,430 on PyPI
Alternatives
Verify before relying
pip install webrtcvad
import webrtcvad
vad = webrtcvad.Vad(1)
sample_rate = 16000
frame = b'\x00\x00' * (sample_rate * 10 // 1000)
result = vad.is_speech(frame, sample_rate)- Whether the package builds successfully on modern Python versions despite classifiers only listing up to 3.5.
- Whether pre-built wheels are available to avoid compilation friction on common platforms.
- Current real-world accuracy and performance compared to more recently maintained VAD alternatives.
What it is and what it does
webrtcvad is a Python binding to Google's WebRTC Voice Activity Detector, a classifier that determines whether short audio frames contain speech or silence. It accepts 16-bit mono PCM audio at fixed sample rates (8000, 16000, or 32000 Hz) in frames of 10, 20, or 30 milliseconds, and returns a boolean indicating whether speech is present. The detector supports aggressiveness levels (0–3) to tune sensitivity.
The package is used in speech recognition pipelines, telephony systems, and audio preprocessing workflows where you need to filter out silence or identify speech segments before further processing. It wraps a mature, well-regarded algorithm from the WebRTC project, but the Python wrapper itself has not been updated since 2017-01-07, creating uncertainty about compatibility with modern Python toolchains and whether better-maintained alternatives now exist.
Use it for
- Preprocessing audio streams for automatic speech recognition by filtering out silence before sending to a speech-to-text service.
- Segmenting recorded phone calls or voice messages to extract only the voiced portions for analysis or transcription.
- Real-time voice activity detection in VoIP or conferencing applications to trigger recording or transmission only when speech is detected.
- Training or evaluating speech detection models by labeling audio data as voiced or unvoiced at the frame level.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, with conditions.
The underlying WebRTC VAD algorithm is mature and well-regarded. However, high install friction (compiled extension), dormancy since 2017-01-07, and uncertainty about modern Python compatibility mean you should verify it builds on your target platform and consider whether a more recently maintained alternative better suits your needs before committing.
Install
webrtcvad on PyPI
Before you install
High install friction due to compiled C extension dependency (webrtcvad-2.0.10.tar.gz). The package is dormant—last release was 2017-01-07, over 3506 days ago—with no recent maintenance activity, though the repository remains active with 2497 stars.
Requires 16-bit mono PCM audio at 8000, 16000, or 32000 Hz; frame duration must be 10, 20, or 30 ms. Compilation of C extension may require build tools and development headers.
License in practice
MIT license (permissive) imposes no significant restrictions on use, modification, or distribution in commercial or private projects.
Quickstart
pip install webrtcvad
import webrtcvad
vad = webrtcvad.Vad(1)
sample_rate = 16000
frame = b'\x00\x00' * (sample_rate * 10 // 1000)
result = vad.is_speech(frame, sample_rate)Verify before relying
- Whether the package builds successfully on modern Python versions despite classifiers only listing up to 3.5.
- Whether pre-built wheels are available to avoid compilation friction on common platforms.
- Current real-world accuracy and performance compared to more recently maintained VAD alternatives.
Package facts
| License | MIT permissive |
| Python support | Not specified |
| Install friction | High. Source build required |
| Runtime dependencies | None |
| Maintenance | Dormant 3,506 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 480,417 / month, #6,430 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaIntended Audience :: DevelopersLicense :: OSI Approved :: MIT LicenseProgramming Language :: Python :: 2Programming Language :: Python :: 2.7Programming Language :: Python :: 3Programming Language :: Python :: 3.2Programming Language :: Python :: 3.3Programming Language :: Python :: 3.4Programming Language :: Python :: 3.5Topic :: Scientific/Engineering :: Artificial IntelligenceTopic :: Scientific/Engineering :: Human Machine InterfacesTopic :: Scientific/Engineering :: Information Analysis |
Evidence: webrtcvad-2.0.10.tar.gz
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “speech detection python”
- webrtcvadProvides a Python interface to Google's WebRTC Voice Activity…
- silero-vadSilero VAD detects speech activity in audio files and streams,…
- pymicro-vadA self-contained voice activity detector that processes 10ms chunks…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also pymicro-vad · silero-vad · webrtcvad-wheels · python_speech_features · realtimestt · aic-sdk · streamlit-webrtc · pyrnnoise · pytgcalls · voip-utils