One of the few service providers in the market offering audio description using synthetic voices

Accessibility through audio description using synthetic voices

There is currently no substitute for human voices. The use of synthetic voices, however, makes sense when it comes to videos clips and short films of up 10 to 15 minutes. Especially for documentaries, where different voices have to be used for passages in different languages. Synthetic voices play a tremendous role here. They are calculated according to the number of minutes and not the number of voices. Nowadays, synthetic voices are barely distinguishable from human voices. Another key point is that audio descriptions can be created very quickly using synthetic voices. The booking of studios, voice artists, audio control rooms, etc., is no longer necessary. Buyouts, which especially drive up the costs of commercial clips, can also be dropped.

The advantages of synthetic voice audio description

At its core, synthetic voice audio description is equivalent to audio description with human voices. The texts are created in specifically designed software by our experienced writers, who supplement the visual elements with appropriate descriptions. This can include details on the mood, the surroundings, and the appearance of certain objects or characters, as well as additional information that is only conveyed visually on screen. The texts are spotted directly in the software and exported as a wav file, either as a pure voice track or an automatic 2.0 mix. Synthetic voices have numerous advantages. They are inexpensive, versatile, and consistent in quality. This is particularly attractive when, for instance, a clip is produced for an instruction manual and perhaps after two years, there is a small change. In such a case, only a small passage needs to be edited. Human voices change. Synthetic voices do not.

Even if no speech synthesizer can measure up to the quality of professional voice artists, the even way of speaking and the consistent pronunciation of terminology eases comprehension, especially in the case of simultaneously existing visual impairments. A variety of voices, both male and female, in a number of different pitches and languages, are available and can be selected to suit the presentation and intended audience. Another advantage is that the drafting of the audio description script and the review of the accompanying effects go hand in hand. Problems, such as text blocks that are too long or timeframes that are too short, are immediately noticeable and can be corrected. This saves time and money, as well as providing planning certainty, as the output of the description is immediately audible. Customer requests and critique at the review stage can be addressed quickly and without incurring further costs as a result of additional studio time.

All in all, with the ever-faster pace of modern productions on a tight budget, synthetic voice audio description is a valuable tool that advances the participation of people with visual impairments, even in smaller productions and events.