“Any audio description is valuable to me as it enables me to understand the programme or event I’m following.” – Seema Flower
Audio description (AD) plays a crucial role in making visual content accessible to blind and partially sighted individuals by providing spoken commentary that conveys essential visual details. A recent study by RNIB delved into the use of synthetic speech for AD, evaluating its quality, suitability, and impact on viewer experiences.
Key Findings from the RNIB Study
The study, which involved UK broadcasters and content from major channels, assessed synthetic voices across various genres, including drama, sports, and factual content. Participants, unaware that they were listening to synthetic voices, provided feedback through an online survey and focus groups.
1. Suitability of Synthetic Voices
The study found that in most cases, participants did not immediately recognise synthetic voices as artificial. However, synthetic speech lacked emotional impact, particularly in genres such as drama and sports, where emotional resonance is crucial. In contrast, for factual content, participants viewed synthetic voices as a viable option, where emotional engagement is less critical.
2. Preferences for Audio Description
The findings highlighted that participants highly valued the “human aspects” of AD, such as when the describer laughed or conveyed excitement. Matching the describer’s voice to the content in terms of accents, tone, and emotional engagement emerged as a key factor in enhancing the viewing experience.
3. Challenges with Emotional Engagement
A significant drawback of synthetic voices is their inability to fully convey human emotion and spontaneity. Participants noted that synthetic AD felt detached and lacked the warmth that a human voice can provide, especially in entertainment content.
The Future of Synthetic Speech in Audio Description
Despite the challenges, synthetic speech presents potential benefits such as scalability, cost-effectiveness, and greater availability of AD services. However, to be widely accepted, synthetic voices must achieve minimum quality standards that ensure clarity, naturalness, and emotional appropriateness across various content types.
RNIB’s report offers recommendations to enhance synthetic speech, including:
- Improving emotional adaptability to match different genres.
- Ensuring culturally appropriate accents and tones.
- Maintaining consistency across episodes or content series.
- Enhancing sound mixing for better clarity and integration with programme audio.
Make Your Services More Accessible with Blind Ambition
At Blind Ambition, we specialise in helping businesses and organisations make their goods and services accessible to blind and partially sighted individuals. From ensuring compliance with accessibility standards to implementing effective solutions like audio description, we provide expert consultation and training to help you create a more inclusive environment.
Call us today for a free consultation and discover how you can unlock new opportunities by making accessibility a priority.


