Skip to content

AsrTools

A desktop GUI that turns audio into SRT or TXT subtitles

Visit official site

What AsrTools is

The repository describes AsrTools as a speech-to-text tool that works by calling ASR interfaces from large vendors rather than running a local model, which is why it says no GPU or complex environment is needed. The interface is built with PyQt5 and qfluentwidgets. The stated advantages are vendor-side stability, a simple setup, and flexible output formats.

What you can do with it

  • Turn recorded audio into subtitles for a video
  • Transcribe an interview for editing
  • Add subtitles to teaching videos

Who it is for

  • Speech-to-text needs in video production, audio editing and subtitling, per the source

What to watch out for

  • The source notes a current free mode using vendor ASR services
  • Direct video-file extraction is planned for a future version

Pros & cons

✓ What we like

  • No GPU or complex local model setup is described as necessary
  • Batch processing and two subtitle formats are listed
  • The GUI workflow is documented step by step

! What to watch out for

  • Dependence on third-party ASR interfaces is outside the project's control
  • Direct video-file processing is described as future work
  • Data handling for uploaded audio is not described

FAQ

Does it need a GPU?

The repository says vendor ASR interfaces avoid the need for a GPU and complex local setup.

Which outputs are supported?

SRT and TXT subtitle files are listed.

Can it process video files directly?

The feature list describes that as planned for a future version.

Last reviewed: 2026-11-15

More AI audio tools tools

View all →

How we review