English language support has been added to Voicedocs Transcriber Service. You can now convert your audio files to text or add subtitles to your videos in English. Just choose English from the language drop-down menu when you upload a file.

Voicedocs Software company which does R&D in the AI field, develops its own speech recognition engine without using third-party services.


Voicedocs Transcriber's Speech Recognition Engine for the Turkish Language has been Updated

The new version transcribes 9% more accurate than the previous one. Thus, you will get 9% more accurate transcription and do less editing when you transcribe an audio file.

Also, the transcriber for the English language will be released very soon. Please, stay tuned.


What is Speech Recognition?

Speech Recognition (or Automatic Speech Recognition) is the process of converting live or pre-recorded speech to text using computer technologies. Fig. 1 shows some of the Speech Recognition applications.

Fig. 1. Some application of Speech Recognition


One of the most promising, socially necessary areas of speech recognition and the software on its base is to help people with disabilities. Scientific research and development of automatic speech recognition software and technical tools can be used to improve the lives of certain categories of people with disabilities.
In this blog post, we explain how speech recognition and its resulting products – The Dictation Software and Transcription software can be used by the disabled people.

Speech technologies against occupational diseases
How do computer occupational diseases occur?

In this article we analyze how the use of modern speech technologies, in particular, dictation and automatic transcription software help to avoid the computer occupational diseases.
The increase of the role of computers in everyday human life and work activities, in addition to great benefits, brings some professional diseases, which creep unnoticed, and one day the serious dangers appear for the quality of human life and activities.


Many people today have to conduct interviews for different purposes. Sometimes, interviews are needed for the purpose of research, sometimes for media releases, and for many other purposes like these. There are different methods of gathering the data you get from interviews. Mostly used methods are to either write down the interviews or record them.

Why Should You Record Interviews?


Transcription of the interview

The transcription of the interview, like the transcription of any other audio file is tedious and time-consuming process.
What is the difference between transcription of an interview and transcription of other types of audio files? A journalist, researcher, lawyer or someone else records an interview, or just a conversation with someone, or dictates an interesting situation to his/her recording device or smartphone.

Quick turnaround time – on of main requirements


Transcription is a process of converting (transcribing) previously recorded speech to text. Most often, such work is needed to transcribe interviews, seminars, meetings, conferences, roundtables, to create subtitles for video, etc. It may seem that transcribing of audio files is a simple process, but it requires speed, knowledge of grammar, patience, and also quickly typing skills. The process of transcription of audio files is a very tedious and time-consuming process.