Looking for recommendations - Best Speech (mp3, mp4 .wav) to Text (.SRT, .VTT, .SBV, or .SUB) Tool that works with Storyline 360.

Apr 15, 2020

Hi - I am looking for recommendations for a Speech to Text tool (to import captions) that works with both audio and video (.mp3/.mp4.wav) and outputs to Storyline 360 supported files (.SRT, .VTT, .SBV, or .SUB) with an accurate cue point for each caption.

This has been my experience so far:

Used Dragon Naturally Speaking Premium V13.00.000.200. but because it does not work with .mp4 files, had to use another tool to format the audio to .mp3 so Dragon could transcribe it. Cleaned that text up (because it was inaccurate and jumbled and had no timeline cues) and pasted that (.TXT) into another free converter tool(ToolSlick) to get a caption file in a SL360 supported format (.SRT). That file imported to SL360 fine but the timeline cues assigned by ToolSlick were totally wrong (video was 2m.16s and the ToolSlick output was 5 min) so only some of it imported and even that was in the wrong place. I just want one accurate tool! :)

Thank you in advance for any help.

4 Replies
Scott Wilson

Hi Christina,

I was just searching for answers as well. If you're still about, let me share my experiences of things you could try. There are quite a lot:

  • Premiere Pro CC 2022 has a fantastic Speech to Text tool. It will generate a transcript and captions with extremely good accuracy plus the ability to easily edit it. Simply create a new sequence, import audio onto your timeline away transcribe. It uses Adobe Cloud so it uploads to their servers but does it very quickly
  • Techsmith has a new tool called "Audiate". It's very quick to get a transcription, not as accurate as Adobe but very easy to edit. It also doubles as a Digital Audio Workstation (not as good as something like Adobe Audition)
  • I tried Amazon Web Services, it has a fantastic speech to text tool which will output to transcription file and SRT captions.
  • Probably the most powerful and most accurate is Google Cloud Speech to text. It's a bit tricky to set up and to export to SRT but worth checking out.
  • A great free alternative is to convert your audio file into a video, upload to YouTube and wait for the auto transcription. That will then let you download the captions. I find that the captions you download from YouTube have weird timings, so I import the captions into Camtasia and reexport and it corrects it.

Hopefully one of these helps you or anyone else out there looking for answers.


Christina Thurston

Thanks Scott! I appreciate you taking the time to share that information. My company actually went with Otter.ai and we love it. It met all my above requirements and much more. Many departments are using it - not just design. There is a free account but we got the team account with all the functions.