Accessibility that includes everyone
SDH captions that go beyond dialogue — capturing sound effects, music cues, and speaker identities for a fully inclusive viewing experience.
How it works
Submit video content
Provide your video file or URL. Ollang transcribes speech and detects non-speech audio events.
SDH enrichment
Sound effects, speaker identifiers, and music cues are added as caption events alongside dialogue.
Accessible output
Receive subtitle files or burned-in captions that meet WCAG and broadcast accessibility standards.
%20--%3e%3cstyle%20type='text/css'%3e.cls-0%20{fill:%23F8F9FA;}%20.cls-1%20{fill:%23E2E2E2;}%20.cls-2%20{fill:%23773CF3;}%20.cls-3%20{fill:%23FFFFFF;}%20.cls-4%20{fill:none;stroke:%23773CF3;stroke-width:1.1;stroke-linecap:round;stroke-miterlimit:10;}%20.cls-5%20{fill:none;stroke:%23C6B2FF;stroke-linecap:round;stroke-linejoin:round;stroke-miterlimit:10;}%20.cls-6%20{fill:none;stroke:%23773CF3;stroke-linecap:round;stroke-linejoin:round;stroke-miterlimit:10;}%20.cls-7%20{fill:none;stroke:%23C6B2FF;stroke-linecap:round;stroke-miterlimit:10;}%3c/style%3e%3cpath%20class='cls-1'%20d='m42.6%2043c-0.5-14.6%2010.7-28.7%2026.8-29.3%2015.1-0.2%2027.5%2011.7%2027.6%2027.3%200.1%205.5-1.6%2012.7-5%2018.1-2.4%203.7-5.6%206.9-8.3%2010.2-1.8%202.4-2.7%204.7-3.3%207.7-0.9%204.3-3%208.1-7.1%2011-7.1%204.4-21.3%204-23.7-11-0.5-2.8%205.8-4.2%206.2-0.4%201.4%207.8%2010.4%2010.6%2016.1%205.2%201.6-1.6%202-3.1%202.6-5.1%201.6-8.2%206.5-11.3%2010.9-17.7%203.3-4.4%205.3-9.7%205.3-16%200-11.8-9-22.8-21-22.8-10.6%200-19.6%208.8-20.5%2019.3l-0.1%204c-0.1%201.9-6.1%202.6-6.5-0.5z'/%3e%3cpath%20class='cls-2'%20d='m82.7%2050.7h-26.7c-0.6%200-1%200.3-1%201s0.4%201%201%201h26.6c0.8%200%201-0.3%201-1s-0.3-1-0.9-1z'/%3e%3cpath%20class='cls-2'%20d='m55.9%2057c-0.5%200-0.9%200.4-0.9%201s0.3%200.8%200.9%200.8h21.7c0.7%200%201-0.2%201-0.9s-0.4-1-0.9-0.9h-21.8z'/%3e%3cpath%20class='cls-2'%20d='m55.9%2063c-0.5%200-0.9%200.4-0.9%201.1s0.4%200.9%201%200.9l16.6-0.1c0.5%200.1%201-0.2%201-0.9s-0.3-1-0.9-1h-16.8z'/%3e%3cpath%20class='cls-2'%20d='m69.8%2030.5c-3.9%200-7.7%203.4-7.7%207.6-0.2%204.1%203.5%208.4%208.2%208.3%204.1-0.1%207.1-3.5%207.1-7.7%200-4.1-3.2-8.1-7.6-8.2z'/%3e%3cpath%20class='cls-3'%20d='m73.3%2036h-7.2c-0.3%200-0.6%200.3-0.6%200.6%200%200.4%200.3%200.6%200.6%200.6h2.3v6.7c0%200.3%200.3%200.6%200.7%200.6%200.3%200%200.6-0.2%200.6-0.6v-3.6h0.3v3.6c0%200.3%200.4%200.6%200.6%200.6%200.4%200%200.6-0.2%200.6-0.6v-6.7h2.1c0.4%200.1%200.7-0.2%200.7-0.6%200-0.3-0.3-0.6-0.7-0.6z'/%3e%3cpath%20class='cls-3'%20d='m69.7%2035.3c0.6%200%201.2-0.5%201.2-1.2%200-0.5-0.5-1.2-1.2-1.1-0.6%200-1.1%200.5-1.1%201.1s0.5%201.2%201.1%201.2z'/%3e%3cpath%20class='cls-4'%20d='m28.3%208.9c-9.8%209.8-17.7%2024-17.7%2042.3%200%2015.5%206.3%2030.8%2017.5%2042.5'/%3e%3cpath%20class='cls-4'%20d='m34.6%2015.7c-7.2%207.3-14.6%2018.4-15%2034.8-0.1%2013.6%205.2%2026.1%2014.9%2036.6'/%3e%3cpath%20class='cls-4'%20d='m40.6%2022.2c-6.4%206.8-11.9%2015.9-11.9%2029.2%200%209.5%203.8%2019.7%2011.2%2028.7'/%3e%3cpath%20class='cls-6'%20d='m111.4%209.1c7.1%207.3%2017.8%2020.5%2017.8%2042.1%200%2013.4-4.8%2027.7-17.8%2042.6'/%3e%3cpath%20class='cls-6'%20d='m105.4%2015.9c6.2%206.3%2014.9%2017.6%2014.9%2035.2%200%2010.8-3.4%2023-14.9%2036'/%3e%3cpath%20class='cls-6'%20d='m99.2%2022.2c5.7%205.9%2011.6%2015%2011.7%2028.7%200%2010-4.3%2020.7-10.8%2029.2'/%3e%3cpath%20class='cls-5'%20d='m22%202.4c-9.1%209.1-19.8%2025-19.6%2049.2%200%2014.3%205.1%2031%2019.5%2048.9'/%3e%3cpath%20class='cls-5'%20d='m117.7%202.4c9.8%209.5%2019.9%2025.3%2020.2%2048.2%200.2%2015-5%2033-20.2%2049.9'/%3e%3cpath%20class='cls-5'%20d='m40%2073.1'/%3e%3cpath%20class='cls-5'%20d='m39.4%2041.4c-0.8%203-1.5%205.3-1.5%2010%200%207.1%202.6%2015.3%208.7%2022'/%3e%3cpath%20class='cls-5'%20d='m100.5%2041.4c0.9%203.1%201.4%206.2%201.4%209.7%200%206.6-2.3%2015.1-8.8%2022.3'/%3e%3cpath%20class='cls-7'%20d='m100.5%2041.4'/%3e%3c/svg%3e)
Features
Sound effect labels
Automatically annotate non-speech audio like [applause], [music], and [door knock].
Speaker identification
Label each line with who is speaking for clarity in multi-speaker content.
WCAG compliance
Output meets accessibility standards including WCAG 2.1 and FCC guidelines.
Broadcast formats
Export TTML, EBU-TT, and SRT files ready for submission to broadcasters.
Music & tone cues
Capture background music and emotional tones to give full context to deaf viewers.
Multilingual SDH
Deliver SDH captions in 50+ languages without sacrificing accessibility annotations.
Use cases
Public broadcasters
Meet regulatory SDH requirements for all programming.
Streaming services
Ensure content is accessible to deaf and hard-of-hearing viewers.
Film & documentary
Add SDH to festival entries and theatrical releases.
Education
Make lecture recordings and course videos fully inclusive.
Make your content truly accessible
SDH captions that meet broadcast standards and give every viewer a complete experience.
Book a Demo