Skip to main content

Correction: Browser Agent SDK has no client-side VAD

By Steven Van ·

Deepgram says client-side Silero VAD was documented but never shipped in the Browser Agent SDK; barge-in runs server-side instead.

Deepgram has corrected its Browser Agent SDK documentation: the client-side Silero voice activity detection it described was never actually shipped in any released package.

None of the following ever existed:

  • The vad option on MicrophoneOptions in @deepgram/agents
  • The speechThreshold and silenceThreshold VAD options
  • The speech-start and speech-end events on AgentMicrophone
  • The vad field in WidgetConfig and the widget's VAD configuration section
  • The @ricky0123/vad-web and onnxruntime-web peer dependencies (uninstall them if you added them for VAD)

MicrophoneOptions actually accepts sampleRate, echoCancellation, noiseSuppression, and autoGainControl, and the microphone streams continuously while unmuted. Barge-in still works, but it's driven server-side: the Voice Agent API emits a user-started-speaking event, which apps pair with player.interrupt() to stop playback. Deepgram

Deepgram
Deepgram
Power enterprise voice solutions with Deepgram’s Speech-to-Text, Text-to-Speech, and Voice Agent APIs. Real-time, accurate, and built for scale.
View Deepgram →

Read the original announcement →

Read Correction: Browser Agent SDK has no client-side VAD on Creators Toolbox