Please confirm that you would like to cancel your order and delete files.


File type not recognised. Please upload an Audio or Video file.

Subscribe to our Newsletter

Stay up to date on our latest promotions and deals.

Download your quote

Fill out your details below and we will generate a quote for you.

speech to text nibity

Speech To Text Transcription


Speech to text transcription, commonly known just as transcription, is the process of writing out an audio or video recording. Recordings can be in many formats from a digital recording, YouTube video clip, cassette tape, video, podcasts, webinar, CD or DVD.

Speech to text transcription has a rich and evolving history

Where this used to be done predominantly by “secretaries” sitting near the desk of the boss, taking his Dictaphone, putting on the headphones and letting the fingers fly, slowly but surely these on-site secretaries have been overtaken by virtual typing and secretarial service as audio files could be emailed or uploaded, and the ‘text’ emailed back.

The speech to text transcription businesses emerged – transcription service providers, like Nibity and Way With Words, who began to dominate the landscape. These little ‘businesses’ generally consisted of four or five people, receiving audio files and typing them quickly into text.

But from here, the speech to text ‘industry’ arose, with pioneering companies expanding to all corners of the world – both in terms of clients and transcribers.  There is no longer a need for typists to sit together in a room to change speech to text; transcribers can download audio and upload Word documents from pretty much anywhere in the world. As services grew that offered audio to text transcription the era of machine transcription and Deep Neural Networks have started to appear.

Developers have been working on speech to text software that will automate speech to text transcription but are challenged by thousands of accents and dialects spoken in English alone worldwide. There are an uncountable number of differences in the way people speak. Take the speed of speech, enunciation, pronunciation, slurring of speech, swallowing of vowels – all these and more challenge the accuracy level of any transcription software or current technology. Purely automated transcription using technologies is still presently far behind the abilities of trained and experienced human transcribers. The question is: Does machine transcription really top human ability? Especially trained transcribers with an excellent command of language, sharp hearing, and knowledge of subject matter.

Why Speech To Text?

There are a number of reasons that individuals and organizations around the world have their speech recordings transcribed online. While speech to text transcription is most commonly associated with doctors and lawyers (hence, the focus of many transcription providers on medical and legal transcribing), here are some more general speech to text or transcribing benefits, suggesting why more and more people are turning their speech to text.

First of all, it’s a great way to disseminate information. While people certainly do enjoy watching and listening to videos, accessing such files can be more complicated and people can be hindered by not always having the right technology or being in a situation to watch and listen. Having transcripts, though, allows for both reading them in .doc or PDF formats, as well as reading them in a printed version.

Suppose you’re holding a meeting or a conference, but some people aren’t able to attend. That means that they will miss out on all the content of the discussion unless they manage to get hold of the notes. This is why transcripts are useful: the only thing you have to do is to get a transcript of the recording and then just send it to whoever missed the event.

Or perhaps attendees at your meeting or event spend their time scribbling notes, trying to take down as much information as possible. If instead, you record and then have the audio recording transcribed, you can furnish everyone who was there, and even those who weren’t, with the fullest amount of information possible – the whole thing!

When writing a dissertation or doing a research, for example, it might get quite difficult to track the information down from an audio file, listening through hours and hours of recordings to find a pertinent comment. Choosing speech to text transcription is not only a good way to store the data, it also allows to search the document for required keywords and copy and paste selections from the transcript right into another document.


  • Easy: Simply upload, get collection date and pay.
  • Quick: Get your transcript back in 24 hours, or next in queue.
  • Accessible: Easily access your account to check status and collect transcripts.
  • Affordable: Select one of our discount packages for even cheaper options.