---
title: "What is voice activity detection (VAD) in speech-to-text?"
description: "Voice activity detection finds which parts of audio contain speech. How VAD works in 10 to 30 ms frames, how it trims silence before transcription and what it saves."
url: https://broadrouter.com/glossary/vad/
lang: en
updated: 2026-11-14
publisher: BroadRouter (a BroadNet site); API by BroadNet Inference, https://inference.broadnet.ai
---

# Voice activity detection (VAD)

Updated 2026-11-14

Voice activity detection (VAD) is a signal-processing step that classifies short frames of audio as speech or non-speech. Speech systems use it to skip silence, split long recordings at pauses, detect when a speaker has finished, and avoid transcribing background noise.

Also called: voice activity detection, speech activity detection, speech detection, silence detection

VAD answers one question many times per second: is someone talking in this slice of audio?

## How it works

Audio is cut into short frames and each frame gets a speech or non-speech label. The two most used open detectors show the typical parameters:

|  | WebRTC VAD | Silero VAD |
| --- | --- | --- |
| Type | classic detector from Google’s WebRTC project | pre-trained neural model, MIT licence |
| Sample rates | 8, 16, 32 or 48 kHz | 8 or 16 kHz |
| Frame or chunk | 10, 20 or 30 ms | 30+ ms |
| Audio format | 16-bit mono PCM only | as documented in the repo |
| Tuning | aggressiveness 0 (least filtering) to 3 (most) | see repo examples |
| Speed | small C code | under 1 ms per chunk on one CPU thread; about 2 MB model |

Frame size and [sample rate](https://broadrouter.com/glossary/sample-rate/) are linked. At 16,000 samples per second, a 30 ms frame is 16,000 x 0.030 = 480 samples, or 960 bytes of 16-bit audio. Raw frame labels flicker, so tools smooth them: require a few hundred milliseconds of speech before opening a segment, and some silence before closing it.

Hosted APIs use the same idea. OpenAI’s speech-to-text guide lets you set `chunking_strategy` to `auto` or a VAD configuration on audio longer than 30 seconds for its diarization model, which the guide lists as deprecated.

## Why it matters

-   **Cost.** Speech-to-text APIs usually bill per audio minute. Cutting long silences before upload cuts billed minutes.
-   **Latency.** Less audio uploaded means a smaller request and less to process.
-   **File limits.** Splitting at pauses, rather than at fixed times, avoids chopping a word in half when a file is too big for one request.
-   **Voice bots.** Detecting the end of a turn decides how fast a bot replies.

VAD is also the first stage of [speaker diarization](https://broadrouter.com/glossary/diarization/).

## On BroadNet Inference

BroadNet’s docs do not document VAD settings or a silence-trimming option for `/v1/audio/transcriptions`. You upload WAV or MP3 up to 26,214,400 bytes and get back `{"text": ...}`. If your audio has long gaps, as voice notes and call recordings often do, run WebRTC VAD or Silero VAD locally, keep the speech regions, and send those. The [WhatsApp voice notes guide](https://broadrouter.com/guides/transcribe-whatsapp-voice-notes/) covers the ffmpeg conversion to 16 kHz mono that both detectors accept. Transcription is priced per minute, $0.0042 on [BroadNet Transcribe Arabic](https://broadrouter.com/models/cohere-transcribe-arabic/); the [speech-to-text cost calculator](https://broadrouter.com/tools/speech-to-text-cost-calculator/) shows what trimmed minutes save.

## Questions

### What is a good open-source VAD?

Two common choices are WebRTC VAD, a small classic detector with aggressiveness modes 0 to 3, and Silero VAD, an MIT-licensed neural model of about 2 MB that processes a 30+ ms chunk in under 1 ms on one CPU thread.

### Does BroadNet apply VAD to my audio?

BroadNet's docs do not document VAD settings. Trim silence or split at pauses on your side before upload if you need control over it.

### How does VAD cut speech-to-text cost?

Per-minute APIs bill the audio you send. If a recording is 40% silence and you send only the speech regions, you pay for about 60% of the minutes. Keep short pauses so words are not clipped.

## See also

-   [Speech-to-text](https://broadrouter.com/glossary/speech-to-text/) (term)
-   [Speaker diarization](https://broadrouter.com/glossary/diarization/) (term)
-   [Sample rate](https://broadrouter.com/glossary/sample-rate/) (term)
-   [Timestamps (speech-to-text)](https://broadrouter.com/glossary/timestamps-asr/) (term)
-   [Transcribe WhatsApp voice notes to text with an API](https://broadrouter.com/guides/transcribe-whatsapp-voice-notes/) (guide)
-   [Voice notes to text for business: WhatsApp and Telegram to tickets](https://broadrouter.com/blog/voice-notes-to-text-for-business/) (article)
-   [How to transcribe call center recordings: an Arabic-ready pipeline](https://broadrouter.com/blog/transcribe-call-center-recordings/) (article)

Try it on your real workload. New accounts start with $5 of credit for Gemma and transcription. DeepSeek, GLM and Qwen3.8 need a top-up.

[Get started](https://inference.broadnet.ai/account/?utm_source=broadrouter&utm_medium=referral&utm_campaign=glossary-vad&utm_content=page-cta) ·

**Sources**

-   [Silero VAD, official GitHub repository](https://github.com/snakers4/silero-vad)
-   [py-webrtcvad, Python interface to the WebRTC VAD](https://github.com/wiseman/py-webrtcvad)
-   [OpenAI, speech to text guide (chunking\_strategy with VAD)](https://developers.openai.com/api/docs/guides/speech-to-text)
-   [BroadNet Inference API reference, transcription](https://inference.broadnet.ai/docs?utm_source=broadrouter&utm_medium=referral&utm_campaign=glossary-vad&utm_content=sources)
