[Updated Nov. 18, 2019, with more services, based on reader comments.]
Suddenly, it seems like automated speech-to-text applications are everywhere. What was mostly in the realm of fantasy a few years ago is now commonplace: Using either a stand-alone application, workflow extension or web site, we can drop a media file in and, a very short time later, we get text back.
Pretty amazing!
BACKGROUND
In the past, transcripts were exclusively created by people listening to audio and typing what they heard. In most cases, the transcripts were high-quality, especially regarding jargon and acronyms. But, they also took time to create and were somewhat expensive.
NOTE: Costs are always relative. You could do transcripts yourself for free, depending upon how you valued your time versus the amount of material that needed transcription.
A few years ago, both Google and Amazon began offering web-based, general purpose transcription. These were very fast and very cheap, but their accuracy was poor, especially for nouns, jargon and acronyms.
Still, like all of technology, both speed and accuracy improved.
TODAY
Today, we have a plethora of applications and web services that fall into three general categories:
LARRY’S LIST
What I’ve done is create a list of automated transcription services, with the following omissions:
What remained, after these exclusions, were two categories of services: media-specific and general.
Media-Specific services include:
General Transcription services include:
Here is a spreadsheet with more details. Almost all services provide free trials and variable pricing. Where tiers were offered, I picked the middle tier.
Also, all services have more features than were listed here. I picked the highlights from the descriptions on their websites.
BIG NOTE!
I tried to make the media-centric section of this list complete. If I omitted your favorite, please let me know and I’ll update this article and spreadsheet.
9 Responses to Survey: Speech-to-Text Applications for Media [u]
Larry,
thanks for all of this. It’s going to be very useful. I believe CoreMelt produce another called something like Scribeomatic. Never used it but I like their other apps.
Kelvin:
Thanks. I’ll look into it.
Larry
Thanks Larry. These are huge time savers.
There’s also Descript which like Lumberjack can export an xml to produce a rough cut and one click remove ums and ahhs.
Ken:
Thanks, I’ll update my list tonight.
Larry
Mjoll has a comprehensive solution as well… “Mimir”
https://mjoll.no/mimir/
They also have a Premiere panel!
Isaac:
Thanks, I’ll update my list tonight.
Larry
You may want to include http://www.Rev.com
I used them for our closed captions and it seemed good to me.
Jeff:
Thanks for the heads-up. I added them to my update.
Larry
Hey Larry, https://ebby.co are the only ones I’ve found providing pay-as-you-go plans – worth mentioning