Link to home
Start Free TrialLog in
Avatar of Software Programmer
Software Programmer

asked on

Audio (Mp3/M4a/Wma) or Video (Mp4, Mpeg) to Text Format

Assume we have 5,000 audio files of a particular person lecture and assume that that person got died years ago.

Now how to translate the audio files to text.

1. Assume need to upload a audio and correct the transcription based on the pronounciation and fix the transcription errors
2. Repeat the process for couple of files to achieve 100% accuracy
3. Convert the remaining audio files to text

Which application - open source or commercial which has this capability and can achieve more than 90 or 100% of accuracy.

Please kindly suggest with opinions and comments.
Avatar of David Johnson, CD
David Johnson, CD
Flag of Canada image

the defacto standard is Dragon Naturally Speaking use the trial and see if it works for you
Avatar of Software Programmer
Software Programmer

ASKER

Does the Dragon Naturally Speaking has these features?
See here  https://shop.nuance.com/store?Action=Custom&Locale=en_NZ&SiteID=scsoftAP&cvokeywordid=432%7C122887&cvosrc=&gclid=EAIaIQobChMIhoXDq7rl2gIVCSu9Ch1NtA8wEAAYASAAEgJn-_D_BwE&pbpage=resp-dragon-home&utm_campaign=&utm_medium=&utm_source=google&utm_term=dragon+naturally+speaking  for their products.  They claim 99% recognition but that will depend a lot on the quality of your material.

Now if you want it automated, I'm not sure that Dragon does that.

Note that Dragon is considered to be the Number 1 for voice transcription.  And as David Johnson says you can always trial it to see if that is what you want.
I tried Dragon and Google Voice and saw Google voice has a better transcription than Dragon. The only problem is Google Voice doesn't come as a product to buy so that cost will be one time.

can u help me with the following questions?

1. Does anyone Knows any standalone product which has built with Google speech recognition api to buy to work without internet?
2. Does Google has any product which has speech recogniztion to text instead of in cloud ? (cloud api for reference: https://cloud.google.com/speech-to-text/)
3. Google support nearly 120 languages (https://cloud.google.com/speech-to-text/) but Dragon doesn't

We need to go for one time payment but don't see it in Google.

Please help me with your comments.
This question needs an answer!
Become an EE member today
7 DAY FREE TRIAL
Members can start a 7-Day Free trial then enjoy unlimited access to the platform.
View membership options
or
Learn why we charge membership fees
We get it - no one likes a content blocker. Take one extra minute and find out why we block content.