Introduction
Many organizations today face a familiar challenge: they've already created large libraries of video content, but much of it is not fully accessible.
As ADA Title II enforcement ramps up, and as accessibility expectations rise across sectors, retrofitting existing videos with audio description (AD) has become a priority.
The good news? Adding audio description no longer has to be an expensive, slow, or complex process. Thanks to AI-powered tools like ViddyScribe, it's now faster and more affordable to make your existing video content accessible.
In this guide, we'll show you how.
What Is Audio Description?
Audio description is a spoken narration that describes important visual information in a video, such as actions, on-screen text, scene changes, and facial expressions, for viewers who are blind or have low vision.
It plays during natural pauses in the audio, supplementing dialogue and sound effects.
Example:
"A banner reading 'City Budget Meeting, April 3rd' appears on screen."
"The instructor writes 'E=mc²' on the whiteboard."
Without audio description, blind and low-vision users miss critical information that captions and dialogue alone don't convey.
Why Audio Description Is Required
Under ADA Title II, state and local government entities (and public schools and universities) must ensure that their digital content is accessible to people with disabilities.
The U.S. Department of Justice points to WCAG 2.1 Level AA as the applicable standard.
- WCAG 2.1 Success Criterion 1.2.5 states that“audio description is provided for all prerecorded video content in synchronized media”so that essential visual information is available to users who cannot see the screen.
- WCAG 2.1 Success Criterion 1.2.2 requires that“captions are provided for all prerecorded audio content in synchronized media, except when the media is a media alternative for text and is clearly labeled as such.”This ensures that people who are deaf or hard of hearing can access the audio information in your videos.
- WCAG 2.1 builds on Success Criterion 1.4.3 andSuccess Criterion 1.4.11, which require sufficient contrast for text, images of text, and user interface components so that on-screen labels, controls, and other essential graphics in and around the video player are perceivable.
- Under WCAG 2.1 Success Criterion 2.3.1, pages must not contain anything that flashes more than three times in any one second period, or any flashing must stay below the general flash and red flash thresholds. This includes animated intros, transitions, and other visual effects in or around video content.
- WCAG 2.1 Level AA also expects that video players are operable via keyboard, work with assistive technologies, and allow users to turn captions and audio description on or off as needed.
If your videos are embedded on a website, LMS, or public platform and lack audio description, your organization may be out of compliance.
Need the legal context first? Review our breakdown of ADA Title II requirements for video content, then come back here for the implementation workflow.
The Traditional Way to Add Audio Description (Manual Production)
Historically, adding audio description meant:
- Hiring a writer to script the descriptions.
- Recording a professional voiceover.
- Re-editing the video to integrate the narration or creating a separate descriptive audio track.
- Testing and QA to ensure compliance.
This process is:
- Expensive (often $15–$35 per minute of video)
- Time-consuming (weeks per video)
- Difficult to scale (impractical for large video libraries)
That's why many organizations have struggled to retrofit existing content, until now.
Faster, Scalable Audio Description
ViddyScribe uses advanced AI to analyze your video and generate audio description without the need for manual scripting or voice recording.
Benefits:
- Cost savings: a fraction of the cost of traditional production.
- Speed: process videos in minutes, not weeks.
- Scalability: handle entire libraries of videos efficiently.
- Superior quality: best-in-class output with the simplest user experience.
- Flexible output: export VTT files or descriptive audio tracks ready for your website or video player.
For individuals and organizations facing large backlogs of inaccessible video content, ViddyScribe offers a practical path to accessibility.
Add Audio Description With ViddyScribe
Step 1: Upload Your Video
- Log in to ViddyScribe.
- Upload your existing video file (most common formats supported).
Step 2: Let ViddyScribe Process Your Video
- The AI analyzes the video and generates best-in-class audio description text and timing fairly quickly.
Step 3: Review and Edit (Optional)
- You can review and edit the generated descriptions to match your organization's style or preferences.
- This step is optional; many users find the default output ready to use.
Step 4: Export the Audio Description
- Export as a VTT file (for use with accessible video players), a mixed audio track or an open format video with baked-in audio description depending on where you need to use it.
- No need to re-edit or re-upload your original video.
Step 5: Publish and Comply
- Upload the VTT file alongside your video on your website or LMS.
- If your platform supports descriptive audio tracks, you can provide those as well.
That's it! Your video is now accessible and compliant.
Conclusion
Retrofitting existing video content for ADA Title II and WCAG 2.1 compliance used to be a massive barrier, especially when it came to adding audio description.
ViddyScribe makes it easy.
- No re-editing required
- Works with your existing video platforms
- Best-in-class output with the simplest user experience
- Affordable and fast
- Scales to large video libraries
- Plus, get closed captions in 53 languages for complete accessibility
If your organization is ready to tackle its backlog of inaccessible videos or ensure that new content meets accessibility standards, ViddyScribe is ready to support that workflow.
Review pricing or try ViddyScribe today.
FAQ
Can I add audio description to an existing online video without re-editing it?
What files can I download, and which output should I use?
The available downloads depend on your description type and which processing steps you’ve completed:
- Finished video: Your video with audio description incorporated. Use this when publishing a complete described version, including Extended AD.
- Mixed audio track (Standard AD): The original soundtrack combined with audio description. Use this as an additional audio track on a compatible video platform.
- Isolated AD audio (Standard AD): Only the generated description narration. Use this when mixing the narration yourself in an editing application.
- Audio description script: The written descriptions and their timing, available in WebVTT format for review or further editing.
- Closed captions: Caption files supplied separately from the video; they are not burned into the picture.
- Descriptive transcript: A text version combining spoken content with visual descriptions, useful for readers who prefer to review the content at their own pace.
Text Only generation creates the script first. To download finished audio or video, complete the final generation step, then download your outputs from the Library.
Who needs audio description, and when is it required under ADA Title II?
How long does it take to add audio description with ViddyScribe?
Will ViddyScribe work with my current CMS, LMS, or video player?
Make Your Videos Accessible in Seconds
53 languages · Standard & Extended AD · VTT, audio, and video

