While traditional interpreters work with spoken words, a different kind of language professional focuses on a more visual form of communication. Visual industry interpreters work to translate the world as we see it into descriptive language, making visual media, art, and experiences accessible to people with visual impairments. They are the unseen narrators of our visual culture.
The Art of Visual Interpretation: Audio Description
One of the core functions of a visual interpreter is to provide audio description. This involves the careful selection and description of key visual elements in television programs, films, or theater performances. The goal is to evoke vivid mental images and foster empathy in the audience.
This is a complex, intermodal translation where the interpreter transfers content from the visual to the verbal realm. The interpreter is a “sight interpreter” whose task is to describe events, environments, people, characters, their appearance, and their actions. This includes conveying facial expressions, gestures, and body movements.
The ultimate aim is for the listener to not only know what is happening but to also experience the same emotional beats as a sighted viewer—to laugh at the same time, to understand the cause of a sound, and to know who is doing what. To achieve this, professional visual interpreters strive to use a neutral voice and be clear, concise, and descriptive, allowing the target audience to build “internal images” of the scene.
From Live Performance to the Art Gallery
The role of the visual interpreter can extend beyond traditional media to the world of contemporary art. Artists have explored this very profession in moving image works, examining the interpreter’s work in various arenas, from high-stakes diplomatic summits to asylum seeker interviews, placing interpreters at the center of the action rather than as invisible intermediaries.
In a very different artistic context, the visual is translated through human performance. Some contemporary artists create works that exist entirely through the actions of people they call “interpreters.” Instead of a painting or a sculpture, their art is a “constructed situation,” such as a museum guard singing or a couple kissing, which is performed by trained individuals. These “interpreters” are essentially the medium through which the artwork is experienced, translating the artist’s concept into reality through their bodies and voices.
Technology and the New Frontier of Visual Translation
The industry is being transformed by new technologies, particularly in the realm of AI.
One major advancement is in “visual dubbing” or “vubbing.” This AI-powered technology modifies the on-screen lip movements of actors to match translated dialogue, creating a seamless experience for viewers of foreign films. Films have made history as the first feature films to use this technology for their localized versions. In some cases, the original actors even dub themselves in other languages, creating an authentic feel. This represents a new layer in the localization process, where visual content is actively altered to fit a new linguistic context.
Another area of innovation is the AI localization of on-screen text. Generative AI capabilities now automatically detect and translate text within a video—such as slide text, labels, and diagrams—while preserving the original design and layout. This process involves using computer vision to detect text regions, optical character recognition to extract the characters, inpainting to remove the original text, and rendering the translation back into the scene. It is a powerful tool that goes beyond subtitles or dubbing by ensuring that the written information in a video is also accessible to an international audience. The goal is a “fully localized video” where both the spoken narration and the on-screen visuals are understood by the viewer.
Visual industry interpreters are a diverse group, encompassing the artists who craft audio descriptions for the visually impaired, the performers who bring conceptual art to life, and the AI tools that are beginning to reimagine how we translate visual media. Whether through the human voice or artificial intelligence, the goal is the same: to ensure that visual information and experiences can be understood and appreciated by everyone.
