Transcription software

[Walter Soyka]

[Trevor Ward] “Perhaps the Speech to Text feature in Premiere is more geared for actors who are going off of a script, then being able to match the text to the audio then finding your place in the film. Not sure how that is too useful for anyone.”

I’ve used the speech analysis in conjunction with human-prepared transcriptions. This is immensely helpful for working with a producer’s paper cut or finding specific words or phrases in interviews.

Walter Soyka
Principal & Designer at Keen Live
Motion Graphics, Widescreen Events, Presentation Design, and Consulting
RenderBreak Blog – What I’m thinking when my workstation’s thinking
Creative Cow Forum Host: Live & Stage Events

[Trevor Ward]

Just to provide some closure on this thread…

I tried a couple of software solutions including the thing in Premiere and the results came back pretty terrible.

I finally found a company called Flatworld that does transcription for $0.66 per minute of audio. Or, $40 for a one hour interview with one speaker. I gave them a 5 minute portion as a test. Came back about 99% accurate. I’m positive it’s an Indian company. For my purposes, the 99% is plenty accurate enough. I have thus sent in over 15 hours of interviews to be transcribed. Took them about a week to complete the job (over Christmas week). I haven’t had time to sample the results, but will let you know if I’ve regretted my decision.

Trevor F. Ward
Memories of Guantanamo

[Megan Oldfield]

Can you tell me how the results were when you got to check the material you had transcribed over Xmas week?

[Silvia Crown]

Hello,

I just want to recommend owltranscription.com service if you want to convert yours interview to text it is cheap as 0.64$ per minute.

Let me know if you have questions.

[Ernest As]

Given how painful transcribing audio is, people repeatedly ask us why there is still no software that can automatically take an audio and spit out its transcribed text with good accuracy. Now, it’s not entirely true that there is no such software – there are many, but they don’t help in transcribing real-world audio which typically involves handling multiple voices and all kinds of background noises.

Everybody has got their own style of speaking

Training a machine to recognize human voice has proven to be very difficult due to the variations in how people speak a particular language. Despite being the most widely spoken language, English itself sounds considerably different in various parts of the world.

Even if everyone spoke a language the exact same way, there is still the added difficulty of training the system for different voices – from young to old to male to female to hoarse to soft to – you get the drift. Even the same person tends to speak differently in different situations, for example, during a moment of excitement or a bout of cold. Let’s not also forget that some people speak faster, while others speak slower, with lots of ums, ers and uhs, which aren’t even part of any spoken language! Arriving at a speech model that can handle all these variations (like humans do) is really tricky.

So, are we stuck?

Based upon what I’ve read, and my experience, it takes a minimum of 4-5 hours to transcribe 1 hour of digitally recorded interviews. Now the real question is, what’s your time worth?

Transcription process takes precision and accuracy, commitment and dedication, focus and patience..

My suggestion is to use one of transcription services like https://gotranscript.com

They are used by Harward, Stanford.. The fact that such top universities trust with their transcripts proves quality credentials.

[Trevor Ward]

Actually, for a moderately fast typer, you should be able to transcribe an interview in about twice the length of the interview. Or you can use a transcription service, or hire an intern or entry level person to do that work. 4-5 hours seems excessive.

-Trevor F. Ward
Red Eye Film Co.
http://www.redeyefilmco.com
http://www.MemoriesofGuantanamo.com

[Igor Jovcevski]

I wouldn;t want to show off, but I do work on an app that does exactly that ?
It mac only for now and has two versions for both Avid And Premiere.
It adds markers to source clips ( using Google Speech API)
Still looking for testers so you can sign up as beta tester if you’d like to have a go.
to download it just google ‘ edit8 transcribe ‘

[Ritzel Tampos]

Hi everyone!

I come across this post regarding transcription software and I may of help for those looking for a very reliable transcription software.

I’ve been working in non-fiction production for a few years and my team and I got tired of how slow, frustrating and expensive transcription is. So we ran some tests by applying speech recognition to audio and video files and it worked great. It’s amazing when you can get back transcription immediately with pretty good accuracy!

We’ve now built Simon Says (https://simonsays.ai), a website for automated transcription and we are looking for users to test the site and give us feedback.

I am looking for 10 users to try the beta site. If you have transcription needs, let me know.

Thanks
Ritz

[Jim Tierney]

Kind of an old thread, but figured it’d be worth posting…

If you’re using Premiere Pro, Digital Anarchy just released a panel for Premiere (Transcriptive) that uses A.I. to transcribe video. Since it’s fully integrated into Premiere, the entire transcript lives within Premiere, meaning you can edit it, click on words to move the playhead to that point in your sequence, save to markers, or export to a caption/subtitle file. Here’s the link if you want to grab the trial version:

https://digitalanarchy.com/transcribe-video/transcriptive.html

cheers,
Jim Tierney

[Robert Maier]

I’m looking for a video transcription service that can stamp SMPTE time code along with text for about 5 hours of interviews that already has been cut on a low-budget documentary. Any Ideas?