Using Subtitle Edit to create amazing audio to text SRT transcripts

Published by

on

Subtitle Edit is a free and open source tool that does a WHOLE lot of things, but the key piece it is doing for me in my workflow is transcribing audio to text so that I can get SRT transcripts with very little editing required. The accuracy on this has been amazing in the edits I have done so far. 100% accuracy, no edits required by me after the tool runs on my edited video.

My transcription steps (version 4.0.15)

Here are the steps I use in Subtitle Edit 4.0 that have worked well for me.

  1. Generate an MP4 file of my edited video, fully finished and ready for transcription.
  2. Launch Subtitle Edit.
  3. From the menu, select Video > Open video file
  4. Find and select my MP4 file
  5. From the menu, select Video > Audio to text (Whisper)
    • There is also a Vosk/Kaldi option that I haven’t tried, but Whisper has been so good I’m not changing!
  6. My audio to text configuration:
    • Engine: Purfview’s Faster-Whisper-XXL
    • Language: English
    • Model: medium.en (1.5 GB)
    • Auto adjust timings: True
    • Use post-processing: True
      • Click the Settings link to set post-processing settings. I have “Merge short lines”, “Break/split long lines”, and “Fix short duration” enabled.

The interface won’t win any awards, but it works great. There is a lot of functionality built into this tool that I’m not even using and it makes the interface a little busy so it took some digging for me to find the right buttons to click. For the most part, I left things on the default settings and everything worked out really well.

The installation doesn’t come with all the tools, though. For example, as you make choices on your engine and model the tool begins asking you to download dependent packages. I actually liked this because it meant that the installation wasn’t a huge bloated thing at the beginning, but slowly adds in only the pieces you actually need.

In terms of activity, you can watch the GitHub repo for new releases.

All in all, great tool, you should add it into your flow!

Updated steps for 5.0.0 Beta release

It’s been a long time since I’ve checked in with Subtitle Edit, but at a reader’s request I took a look at the latest Beta release available on 2026-05-16 (-beta27) and figured out the sequence that matches with the previous steps.

  1. Generate an MP4 file of my edited video, fully finished and ready for transcription.
  2. Launch Subtitle Edit.
  3. From the menu, select Video > Open video
  4. Find and select my MP4 file
  5. From the menu, select Video > Speech to text
  6. My speech to text configuration:
    • Engine: Purfview Faster Whisper XXL (~1.4 GB)
    • Language: English
    • Model: medium.en (1.5 GB)
    • Post processing: Checked ✅
    • Click the settings icon (⚙️) to set post-processing settings. I have “Adjust timings”, “Merge short lines”, “Break/split long lines”, and “Fix short duration” enabled.

7 responses to “Using Subtitle Edit to create amazing audio to text SRT transcripts”

  1. […] default (or a preset like “–standard”) is fine. Your dialog should look similar to this: (Using Subtitle Edit to create amazing audio to text SRT transcripts – St-Cyr Thoughts) The Whisper audio-to-text dialog in Subtitle Edit. Here, Engine is set to Faster-Whisper, language […]

  2. zojal Avatar
    zojal

    Very helpful sir, especially since there are no articles and videos that discuss this for Linux, only you. Thank you very much sir

    1. Jason St-Cyr Avatar

      I’m glad it helped! You should note that I am using this on Windows, but hopefully it works for you on Linux as well!

  3. Michael Damian Klinkenberg Avatar
    Michael Damian Klinkenberg

    Please give the version number you are talking about resp.

    taken screenshots from as above. Rather prefer an an old version.

    The new version 5 beta 27 does not have this straight

    forward Video > Audio to text (Whisper… anymore.

    It is now somewhere in a confusing subdir speech to text

    with loads of unexplained models to download.

    Need to get srt from a french video.

    Regards

    1. Jason St-Cyr Avatar

      Hey Michael, I wrote this two years ago so I went through the releases and it looks like the version at that time was probably the 4.0.x series? It’s REALLY a lot of releases ago, though. I don’t know if having a slightly different UX is going to be worth everything you’ll lose by going back two years of features and fixes.

  4. Michael Damian Klinkenberg Avatar
    Michael Damian Klinkenberg

    Correct, Jason.

    Even so, your guide ist not working on my 4.01 version, I never had the

    neccesity to update so far.

    Tried to find your quote “…latest release in December 2023” on github,

    but there is only one from November 2023 followed by January 2024.

    Hence the question.

    Maybe you find time to update this guide so it applies to the recent

    nikse-version i.e. the link you provide here either?

    Whether or not, thanx for your effort and take care.

    Damian

    1. Jason St-Cyr Avatar

      Hey Damian, I downloaded the latest 4.0.x version (4.0.15) and updated the instructions slightly. Almost everything was exactly the same, just a slight movement of one of the elements in the picture and the engine is now called Purfview’s Faster-Whisper-XXL.

      I’ll download the latest 5.0 beta and see what it’s like and I’ll post another update once I’ve seen the latest!

Leave a comment