Free estimates with no obligation

Audio to text transcriptions

Audio to text transcriptions

What is audio to text transcription?

Audio to text transcriptionsA transcription is a written representation of what can be heard in an audio or video recording. The transcription process therefore consists of converting recorded voices and sounds into text.

This audio to text transcription process is done by a professional transcriber.

What are audio to text transcriptions used for?

There are many reasons why a client might request a transcription.

Everyone has surely heard of audio transcriptions of conversations being presented as evidence in court. These transcriptions aid comprehension of voice recordings, particularly if the recordings are of poor quality. We’ve also all seen transcriptions of audiovisual products (films, TV shows, documentaries etc.) for people who are deaf or hard of hearing.

In addition to these two usage, audio to text transcriptions are also used in public administrations and institutions. For example, parliamentary plenaries and sessions are transcribed, leaving a record of all the contributions made and limiting the storage space used for recordings.

Conferences, speeches, interviews and university lectures are also frequently transcribed so that anyone interested can read or study them afterwards.

At Acantho I&C, we provide audio to text transcriptions for the purpose of translation. A single transcribed document is used to create versions in multiple languages.

How does transcription work?

Audio To Text TrancriptionsAlthough audio to text transcription may seem like a simple task at first glance, the process actually involves many hours of work. The transcriber plays part of the audio, pauses the recording and writes down what they heard, repeating these steps until they have finished transcribing the entire recording. A one-hour recording would take five to six hours to transcribe—and that’s without adding time-stamps for future subtitling.

Almost any recording, in any format, can be converted into text. However, the poorer the quality of the recording is, the longer the transcription will take. It is crucial that the transcribers be able to hear the voices clearly and that there is no background noise or extraneous sounds that could distract them or complicate their work.

Types of audio to text transcription

Natural transcription

In a natural transcription, the transcriber writes down the content of the recording word for word while omitting any irrelevant information such as interjections, repetitions and false starts. No words or meanings are changed, but repeated words and interjections, which are very common in spoken language, are removed. The text is very clear and easy to read and/or study.

The following example illustrates natural transcription:

[00:00:59] [Moderator] Good morning, welcome to the “Artificial Intelligence: function and solutions” conference, organised by the Barcelona Institute of Technology and Artificial Intelligence. Fernando Goikotxeta, the President of the Institute, will now kick off the event.

[00:01:22] [Fernando Goikotxeta] Good morning, everyone. Welcome to the forum, which, for the third year in a row, is being celebrated online from Paseo de Gracia.

Literal transcription

In a literal transcription, the transcriber writes down every sound in the recording without omitting any information. Literal transcriptions include the speakers’ repeated or unfinished words, interjections, false starts and possible grammatical errors.

This is the type of transcription that is presented as evidence in court, where the speakers’ intonation and ways of expressing themselves are valuable information for the investigation.

The following example illustrates literal transcription:

[00:00:59] [Moderator] Testing… Good morning, welcome to the “Artificial Intelligence: function and solutions”, conference organised by the Barcelona Institute of Technology and Artificial Intelligence. Fernando Goikoetxea, uh… Goicotxeta, the President of the Institute, will now kick off the event.

[00:01:22] [Fernando Goikotxeta] [laughs] Um… Good morning everyone. Welcome to the forum, which, for the second… the third year in a row, is being celebrated online from Paseo de Gracia.

Musical transcription

Another category is musical transcription, which involves rendering a recorded melody into sheet music.

Phonetic transcription

This is a conversion of sounds into phonetic symbols using an internationally recognised system.

Why hire a professional translator to convert audio into text?

Audio transcriptionsThere are several automatic programmes and applications that convert audio recordings into text easily and cheaply. A simple Google search will give you a list of the tool that transcribe audio to text. If you’re someone who records your teacher’s lessons at university on your mobile phone, or any other device, so that you don’t lose any information, you could make do with the services offered by these programmes and tools, and study the transcriptions in Word or Google Docs. However, you’ll need to watch out for any grammatical errors that the automatic transcription programme may have made. Sometimes, depending on the subject and focus of the lesson, words may be mispronounced and transcribed incorrectly as a result.

Most people using these apps, tools and programmes do not need professional audio or video transcription services, because the voice recordings are made for later, personal study, and the transcription will not be shared.

On the other hand, if the purpose of an audio to text transcription goes beyond personal use, we recommend getting a professional to transcribe your audio files. This is because audio to text conversion tools are not 100% reliable and good quality is not guaranteed.

Why choose Acantho for your audio to text transcriptions?

At Acantho I&C, we transcribe parliamentary sessions conferences, interviews and more.

A good conference microphone and the right recording system are crucial when it comes converting audio to text. However, recording content under ideal conditions is not always possible. At Acantho, we’ll carefully go through every audio file and recommend the best option for your project.

We work with the latest technology to optimise turnaround times, and we follow a strict correction process prior to delivery in order to provide quality audio and video transcriptions.

Our transcribers are professional, native speakers of the language recorded.

Our transcription services

  • Audio to text transcription
  • Video to text transcription
  • Image transcription
  • Transcription of documentaries
  • Film transcription
  • Conference transcription
  • Court transcription
  • Police interrogation transcription
  • Class transcription
  • Lecture transcription
  • Medical transcription
  • Pharmaceutical transcription
  • Interview transcription
  • Press conference transcription
  • Phone call transcription

Languages we transcribe in

While the most in-demand languages for transcription are Spanish and English, at Acantho I&C we work with more than fifty of the world’s languages. We tailor our services to every client’s specific needs.

If you need audio to text transcriptions of any voice recording in a foreign language, please don’t hesitate to ask us. We’ll give you a personalised quote at no cost and with no obligation.

If you have any questions or need more information about our audio and video to text transcription and/or translation services, please call us on (+34) 976 910 302, or send an email to, and we will be more than happy to assist you.

This post is also available in Español.