Vision, described
AI-generated audio description that narrates scenes, actions, and text for blind and low-vision viewers — delivered at broadcast quality.
How it works
Analyze your video
Ollang's vision AI identifies visual scenes, on-screen actions, and gaps in the existing audio track.
Generate descriptions
Natural-language scene descriptions are scripted to fit precisely within the available audio gaps.
Voice and deliver
Descriptions are voiced using natural TTS and mixed into the final audio track ready for distribution.
%20--%3e%3cstyle%20type='text/css'%3e.cls-0%20{fill:%23F5F5F5;}%20.cls-1%20{fill:none;stroke:%235217E5;stroke-width:1.5829;stroke-linecap:round;stroke-linejoin:round;stroke-miterlimit:10;}%3c/style%3e%3cpolygon%20class='cls-0'%20points='142.1%2072.3%20142.1%20143.9%2071.8%20143.9%2071.8%2072.2'/%3e%3cpolygon%20class='cls-0'%20points='23.3%2072.2%2023.3%20143.9%201.8%20143.9%201.8%2072.2'/%3e%3cpath%20class='cls-1'%20d='m72.1%202.6c-37.9%200-69.6%2030.9-69.6%2069.5%200%2037.5%2028.8%2069.5%2069.6%2069.5%2038.8%200%2069.5-29.9%2069.5-69.6-0.1-34.3-29.6-69.4-69.5-69.4z'/%3e%3cpath%20class='cls-1'%20d='m71.8%2012.3c-31.4%200-60%2025.4-60%2059.7%200%2029.7%2022.3%2059.5%2060.3%2059.5%2032.4%200%2060-25.1%2060.1-59.5%200.1-28.6-24.7-59.7-60.4-59.7z'/%3e%3cpath%20class='cls-1'%20d='m71.9%2022.3c-5.6%200-11.3%200.8-18.2%203.4-11.5%204.5-26.1%2016.5-30.6%2033.3-6.1%2023.3%206%2050.6%2030.6%2058.6%2012.1%204.1%2024.8%204.4%2036.3%200%2013.3-4.8%2028.8-17.4%2032.7-38.5%203.9-23.1-11-43.3-28-51-6.7-3.1-14.4-5.8-22.8-5.8z'/%3e%3cpath%20class='cls-1'%20d='m45.9%2056.8-14.7%2015.1%2015.2%2015.7c6.5%208.6%2014.9%2013.8%2025.6%2013.8%2017.6%200%2038.7-14.2%2040.2-31.5%200-19.5-17.9-37.5-40-37.6-14.9%200-29.7%207.4-37.3%2023.2-2.2%204.7-3.6%2010.9-3.6%2016.4%200.9%2018.8%2014.5%2039.7%2038.6%2039.7%2020.4%200.7%2042-12.9%2042.3-39.7%200.1-19.6-16.7-39.3-40-39.6-20.5%200-40.2%2015.3-41%2039.4'/%3e%3cpath%20class='cls-1'%20d='m71.9%2041.8c-8.8%200-17.9%203.9-23.5%2011.3l-2.2%203.1'/%3e%3cpath%20class='cls-1'%20d='m50.5%2071.9c0%209.5%206.8%2021%2021.4%2021%2012.6%200%2021.9-9%2021.7-21.6-0.2-10.1-8.8-20.9-21.8-20.9-11.3%200-21.3%209.3-21.3%2021.5z'/%3e%3cpath%20class='cls-1'%20d='m57.6%2071.9c0%206.2%204.5%2014%2014.4%2014%207.9%200.2%2014.3-6%2014.3-14%200-6.8-5.5-14.2-14.5-14.2-7.6%200-14.2%206-14.2%2014.2z'/%3e%3cpath%20class='cls-1'%20d='m63.8%2071.9c0%204.1%203.3%207.8%208%207.8%204.1%200.1%207.9-3.1%207.9-7.8%200-4-3.3-8-8-8.1-3.9%200-7.9%203.1-7.9%208.1z'/%3e%3c/svg%3e)
Features
Scene gap detection
AI identifies silent gaps in dialogue where descriptions can fit without disrupting speech.
Natural narration
High-quality neural voices narrate scene descriptions in a clear, consistent style.
Extended AD
Alternate version with paused audio allows longer descriptions for complex visual scenes.
50+ language support
Deliver audio description in any language your audience needs.
Regulatory compliance
Output meets FCC, Ofcom, and EBU standards for broadcast audio description.
API delivery
Integrate audio description into your publishing pipeline via REST API.
Use cases
Public broadcasting
Meet regulatory AD requirements for all programming hours.
Streaming services
Provide AD tracks for blind and low-vision subscribers.
Cinema
Deliver AD audio for theatrical and home release.
Corporate video
Make presentations and training videos accessible to all employees.
Open your content to every viewer
Broadcast-quality audio description that meets accessibility standards worldwide.
Book a Demo