Audio description and smarter AI Captions: What’s new in Brightcove Accessibility

Accessibility has become a real part of how teams plan, publish, and manage video—especially as new regulations like the EAA and updated ADA requirements take effect and introduce clearer compliance obligations.

To make meeting those requirements more manageable, we’ve introduced audio descriptions and enhanced our AI captions with speaker attribution and audio cues.

These updates are designed to fit into your existing workflow and help you meet accessibility requirements without adding unnecessary production or overhead.

Let’s walk through what’s new.

Audio descriptions — Now inside Brightcove

For many teams, audio description has long been part of accessibility planning — but executing it meant relying on external vendors and manual production workflows.

Now, you can automatically generate audio descriptions directly within Brightcove.

Brightcove supports Standard Audio Description, identifying key visual elements and inserting descriptions into the natural pauses of the original audio.

Descriptions may cover:

• On-screen text
• Charts and data visualizations
• Scene changes
• Physical actions or gestures

For viewers who are blind or have low vision, these details are essential to fully understanding the content, while organizations gain a scalable way to meet regulatory requirements and expand the reach and inclusivity of their video.

Where available, the audio description track can (when available) be toggled on or off in the player, making it easily available to those who need it without changing the experience for others.

Why this matters right now

Accessibility requirements have moved from guidance to enforceable regulation:

• The European Accessibility Act (EAA) has been enforced since June 2025.
• ADA Title II in the U.S. now requires public entities to meet WCAG 2.1 AA standards.
• WCAG 2.1 AA includes Success Criterion 1.2.5, which requires audio description for prerecorded video content with meaningful visuals.

Producing audio descriptions has traditionally required an expensive manual process involving multiple steps—scripting, voice recording, editing, and working with external vendors—making it difficult to apply changes across large video libraries.

Now, you can generate audio descriptions directly within Brightcove using Brightcove’s AI Suite.

That means faster compliance for your team and a richer, more accessible viewing experience for every audience.

👉🏻 Learn how audio descriptions works

Enhanced AI Captions: Two important improvements

Auto captions have quickly moved from a nice-to-have feature to a baseline expectation. As more teams rely on them to reach broader audiences, the standard for quality has risen just as quickly.

That’s why we’ve introduced two meaningful upgrades designed to make captions clearer, more natural, and more accessible for everyone.

Speaker attribution

When multiple people are speaking, captions without speaker labels can quickly become confusing.

With Speaker Attribution, AI-generated captions now automatically identify who is speaking, making interviews, panels, and multi-presenter videos easier to understand.

You can choose how speakers appear on screen, depending on the style of your content:

• Hyphens: A simple hyphen signals a change in speaker without naming them. This keeps captions visually clean while still helping viewers follow the conversation.
• Generic labels: Speakers are labeled as [Speaker 1], [Speaker 2], and so on, providing clear structure without relying on specific names.
• AI-detected names: When context allows, AI identifies and displays speaker names automatically. If a name can’t be confidently determined, the system defaults to a generic label, so captions remain accurate and consistent.

The result is captions that are clearer, and easier to follow, without requiring your team to manually edit speaker names before publishing.

Audio cues

Captions often need to capture distinct sounds, not just speech.

With audio cues, AI captions now include relevant non-speech sounds such as:

• [applause]
• [music playing]
• [laughter]
• [phone ringing]

These cues provide important context for viewers who are deaf or hard of hearing. They’re also helpful for anyone watching without sound, a common way audiences consume video today.

Audio Cues are turned on by default, since including relevant sound is part of what makes closed captions complete, but you can turn them off if a simpler visual style better fits your content.

👉🏻 Learn more about the enhanced AI captions

Accessibility that fits your workflow

The thinking behind these updates it that meeting your accessibility requirements can’t be something that slows you down.

With audio description is now easier to generate and captions are more complete and clearer by default, the path toward you meeting the WCAG 2.1 AA standards compliance becomes more manageable.

If accessibility has felt complex or resource-heavy in the past, we hope this feels different.