Make the most of your audio and video content by transcribing it to text. We apply voice recognition and professional native transcriptionists.

Transcription is the representation of spoken language in written form where speech, audio and video files are converted into text format. Transcribed content forms part of your SEO strategy as online searchers can find transcribed content easier.

Benefits of Transcription

  • Enables video and audio content to be indexed by search engines and found.
  • Makes the video accessible to deaf and hard-of-hearing viewers.
  • It can be easily translated and added as subtitles to your videos.
  • Supports audio and video content by delivering an added script.

Transcription in Steps

A project manager checks your file for language and audio subject field and quality. Localised Web uses third-party AI driven voice recognition providers to make an initial draft of the transcription.

The draft is then edited by a professional native transcriptionist (or transcriber) who is knowledgeable in the subject field of the audio file and familiar with the dialects or accents of the speakers in the recording. We time stamp your transcription text file to make it easier for listeners to locate the transcribed audio.

Audio and Language Quality Check

Although voice recognition technology has advanced notably, it is important to consider that low quality audio recordings or audio files with background noise, speech impediments, overlapping conversations, slang, colloquialisms, accents or dialects can defer the transcribed output from an AI service. This is why we also get the files reviewed by professional transcriptionists.

Videos are one of the most common content types that require transcription. Transcription is often followed by subtitle template creation and translation into more languages.

4 Different Transcription Types

Verbatim Transcription

This transcription type includes the most audio details. This is why it is also called true verbatim or strict verbatim transcription. All non-verbal utterances, conversational affirmations, interruptions, overlapping speak and pauses are transcribed.

All audio or video is literally transcribed, and verbatim transcription is often used in research or investigative campaigns. It is also applied in the legal system and for job interviews.

Edited Transcription

The most common transcription type is edited transcription or clean verbatim transcription. As opposed to verbatim transcription all non-verbal communication such as coughing, filler words or stammering is left out of the transcription.

Edited transcription is the standard format for publishable content that is to be translated at a later stage.

Intelligent Transcription

This is further polished audio or video content as the transcribed output conveys the meaning of the speech in a readable and natural way.

This transcription type is also called intelligent verbatim transcription, but it goes a bit further than verbatim transcription by removing repeated utterances and the grammatical structure might be enhanced for better readability.

Intelligent transcription is often applied in the medical industry and within business communications.

Phonetic Transcription

This is a highly specialized transcription method that captures the way speakers pronounce words and utter sounds. Sometimes the speaker’s rising and falling tone is also annotated together with the sounds overlapping the audio. Phonetic transcription applies a specialized notation system.

Most Common Content Types for Transcription

  • Videos
  • Webinars
  • Radio Programs
  • Podcasts
  • Lectures and Courses
  • Meetings and Phone Calls
  • Interviews