Skip to content

Remove silences from source audio #99

Closed

Description

@thestumonkey

We are storing the raw audio for playing, but there's lots of silence in it. Using VAD, we can remove a lot of the silences and reduce load on the main transcrption and recongition services

Activity

  1. linear commented on Sep 16, 2025

    @linear
  2. AnkushMalaker commented on Feb 24, 2026

    @AnkushMalaker
    Collaborator

    This was the default behaviour earlier, but now I don't see that much use. Feel free to open with some more info
    Default storage is opus, and models handle silence innately now a days

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions