Audio description is a technique for making films, videos and TV programmes, but also theater performances, museum visits or events, accessible to people who are blind or visually impaired. Viewers with a cognitive disability, brain injury or autism can also benefit from audio description. In the case of audiovisual productions, a voice-over describes all the visual elements in the pauses between the dialogues and important sounds. This voice provides information about people or characters, locations, events and times. Actions, facial expressions and body language are also recorded in an audio description. This way, people with a visual and/or cognitive impairment can still know what is shown on the screen.
Scribit.Pro specializes in audio description for online video. Our experienced professionals provide video content with a professional audio description. But our foolproof software also makes it possible to easily and quickly add audio description to videos yourself. You don't have to be or hire a voice actor, because the Scribit.Pro editor instantly converts the video's image description into a synthetic (or artificial) voiceover.
How does it work?
Scribit.Pro uses ReadSpeaker computer voices to add audio description to videos. As a global text-to-speech specialist, ReadSpeaker develops synthetic voices and products that use those voices. Thanks to the use of leading technology, these synthetic voices are among the most natural voices on the market. Despite the fact that it is a computer voice, it still sounds lifelike.
ReadSpeaker developed a so-called pronunciation dictionary, which contains several hundred thousand combinations of spelling and pronunciation. The software extracts information about the pronunciation from this. But these dictionaries are also used to train the software; the software learns the most common patterns of spelling and pronunciation. After some training, the software can predict the pronunciation of words that are not in the dictionary, such as names or words from other languages.
It always remains an artificial voice. This may cause the intonation to differ from the desired pronunciation. This can be remedied by simply writing the word differently, for example phonetically. In this way it is often possible to get the pronunciation of the synthetic voice correct.
Why doesn't Scribit.Pro use a voice actor?
By using ReadSpeaker synthetic voices, Scribit.Pro software remains accessible and affordable to everyone. Studios, voice actors and even microphones are unnecessary. The image description only needs to be typed into the editor at the right moments in the video. This text is then automatically pronounced by the software. The user can turn on the audio description for the video at the touch of a button.
Would you rather use a voice actor?
That's no problem either. Simply download the 'script-by-timecode file' via Scribit.Pro or manually create a script with timing. Scribit.Pro can of course also do this for you. These texts can then be recorded by a professional voice actor, or in a studio. Scribit.Pro can arrange that for you. There are several other professionals or organizations that can record audio description voiceovers, such as Ferry Molenaar, Letterval of Voicebooking.