BeyondWords Blog

BeyondWords
  • 0.0 (0)
  • TECHNOLOGY

Stories, insights, and announcements from the BeyondWords blog—read aloud by AI. Learn how publishers are using audio and video to shape the future of digital storytelling.

  1. MAR 30

    How immersion reading can drive deeper news engagement

    Immersion reading (or immersive reading) is the act of following along with text while listening to audio narration. In other words, synchronized reading and listening. (You can try it out for yourself by playing this article.) Google Trends shows interest in immersion reading has surged in recent months: Interest peaked in February 2026 when Audible launched its Read & Listen feature, which highlights the corresponding ebook text as the audiobook plays. Kindle has offered a similar feature for years, but this new launch pushes immersion reading further into the mainstream and makes it more accessible. It also reflects a broader shift in how people consume content: Audiences don't always want to choose between reading and listening—they expect both to work seamlessly together. Why enable immersion reading on articles? Enabling immersion reading on articles means tapping into a behavior that's gaining momentum and has potential to drive meaningful value for your business. Audible says customers who read and listen simultaneously are among their most engaged users. That's not surprising. Combining visual and auditory input helps people stay focused, absorb more, and move through content with less effort. Nine in ten Audible customers agree: immersion reading improves content retention and comprehension. So, immersion readers are likely to spend longer with your journalism and get more from your stories. Adoption is likely to emerge across several audiences, such as: Book lovers bringing read-and-listen habits with them Younger audiences accustomed to watching subtitled content News subscribers keen to stay more focused in a world of distractions Second-language readers who benefit from seeing and hearing content together Readers who need more accessible ways to absorb the news Listeners engaging with longer or more complex stories By offering audio, text, and a read-along feature, you cater to a wide range of needs and preferences. Whether your audience is multitasking or taking time to focus, you're giving them a way to engage that fits. And delivering a read-listen experience is easier than you think. How to enable immersion reading on articles BeyondWords makes it simple for publishers to enable immersion reading on their websites and apps. Our platform automatically turns articles into audio, embeds a player alongside the text, and highlights each word as it's spoken—so users can read along as they listen. Setup takes minutes. Create a project, embed the player script, and you're ready to go. You can tailor the immersion reading experience to match your publication's style, with customizable word and paragraph highlight colors for light and dark modes, as well as flexible player styling. BeyondWords also makes it easy for readers to control playback. Click-to-play lets users start listening from any paragraph, while a sticky player keeps controls accessible as they scroll down the page. Audio narration is powered by hyper-realistic ElevenLabs voices or voice clones, so every article sounds natural, engaging, and on-brand. Together, these features turn every article into a seamless read-and-listen experience that keeps audiences engaged from start to finish. Want to enable immersion reading on your website or app? Book a demo with our team.

    3 min

  2. MAR 23

    How AI audio is reshaping modern news apps

    Apps are where news publishers build their most valuable audience relationships, and AI audio is playing a growing role in their success. Leading publishers like The Washington Post, The Guardian, and Business Insider are using AI audio to deepen in-app engagement in a way that's scalable and cost-effective. And they're deploying it in increasingly creative ways. Expanding usable moments Listening is already entrenched in mobile behavior. Music, podcasts, and audiobooks fill commutes, workouts, and quiet moments throughout the day. AI audio helps your app compete for those same moments within daily routines. Publishers including The Guardian and the Wall Street Journal let users listen to almost any story inside their apps. They can switch between listening and reading without friction, easily choosing the format that best suits their needs and preferences. This means audiences can more easily fit news into their day. So, they're more likely to subscribe—and stay subscribed. Or drive ad impressions. Making individual articles playable is the foundation to building audio engagement. But the real magic happens when listening extends beyond a single story. Turning single plays into long listening sessions Many publishers use playlists and audio queueing to encourage exploration and longer listening sessions. On The Washington Post and Bulletin apps, starting one article automatically generates a queue of related stories. When one audio finishes, the next one begins, pulling listeners into deeper sessions than they originally planned. These apps also let users start editor-curated playlists and build custom audio queues, so they can intentionally engage in longer listening sessions. For example, listeners can queue up articles to play on their commute home. Or start a themed playlist before heading out for a run. By giving readers the option to step away from the screen while staying connected with your app, you unlock new patterns of news consumption. Patterns that are key to building long-term loyalty. And if your app integrates with the user's device, driving sustained engagement becomes even easier. Making audio mobile-native Native device integration allows your audio to function as part of a smartphone's built-in playback system, so listening works the way users expect from any established audio app. For example: Playback continues when the screen locks or the app is minimized Stories appear in lock-screen controls and system control panels Playback can be controlled using familiar on-screen controls Readers can pause and resume with headphones Audio works seamlessly in vehicles through CarPlay and Android Auto Incoming calls automatically pause playback and resume afterwards When audio works this way, users can move between tasks without breaking playback. This continuity reduces friction, supports longer sessions, and makes your audio journalism feel like a first-class mobile experience—not an add-on feature. It also keeps your brand present beyond the app itself, increasing the likelihood that users return and press play again. Tapping into audio stickiness For many publishers, in-app audio isn't just embedded in articles or tucked away in menus—it's a prominent destination in its own right. Apps like The Washington Post and Bulletin feature "Listen" tabs, bringing audio to the centre of the news experience rather than treating it as a secondary format. That prominence matters. According to the Pugpig Media App Report 2025, users who engage with audio in publisher apps spend nearly twice as much time as those who don't. That means more advertising revenue, more subscription conversions, and stronger subscription loyalty. Some publishers accelerate in-app audio discovery and adoption even further by: Providing personalized audio recommendations based on user data Sending push notifications at key audio engagement moments Introducing audio during the app onboarding process Creating an audio-native experience also me...

    5 min

  3. MAR 10

    How we curated ElevenLabs voices for news publishing

    This post is narrated by Caroline Piercy's Instant voice clone, powered by ElevenLabs through BeyondWords. ElevenLabs offers more than 10,000 AI voices across a range of styles, tones, and personalities. If you're looking for pre-made voices to narrate your articles, the abundance of choice quickly becomes friction. After all, not every voice lives up to newsroom standards. That's why, when adding ElevenLabs voices into BeyondWords, we didn't just add the full library—we handpicked the very best options for news narration. Key criteria for news narration First, we excluded ElevenLabs voices that use "Live Moderation". News publishers regularly cover sensitive or controversial topics, and automated moderation systems aren't always calibrated for journalism. By removing moderated voices from our selection, we help ensure legitimate reporting isn't inadvertently flagged or restricted. Secondly, we filtered out voices with short notice periods to give publishers greater stability once a voice is selected. The final filter we applied was for "High-Quality" voices. These voices have been reviewed by the ElevenLabs team to meet professional standards for clarity, stability, and tone—all essential to doing publishers' journalism justice. Once we'd applied our initial filters, it was time to start listening. Curation through careful listening Our team listened to hundreds of remaining ElevenLabs voices to assess their suitability for article narration, testing them with long-form news content. We evaluated voices against the qualities publishers consistently tell us matter most: naturalness, clarity, and authority. This meant removing: character voices, like those made for cartoons; novelty voices, like those created for ASMR content; voices that didn't meet our studio-level quality standards; and voices with overly emotional or flat delivery. Where we didn't have in-house language expertise, we brought in native speakers to share their opinions on the voices. We also gathered feedback from some of our publishers. The result is a selection of over 200 news-ready voices across dozens of languages and accents*. All available for immediate use through the BeyondWords platform. Many of these voices are multilingual, which means they're capable of delivering natural narration across various languages. This is particularly useful for publishers who want to maintain consistency across markets. Multilingual voices can carry traces of their native accent, but they're often indistinguishable from native voices. It's worth exploring the full range before narrowing your selection. Tools for faster voice selection To make voice selection even easier, we added voice previews built around real news-style openings. These give you a realistic sense of how each voice will perform in context. We also set new default voices to give you a convenient starting point across our most-used languages. You can preview some of our favorite ElevenLabs voices below: If you'd like to get tailored voice advice from our team, we're happy to help. Finding the right voices for every publisher We have vast experience working with publishers to find the right voices for their brands. Just recently, we helped a fashion title adopt a female, regionally accented voice that feels authentic to its readership and aligns seamlessly with its style. Whether you have a detailed brief or prefer to rely on instinct, we'll guide you toward voices that align with your editorial identity. And collaborate to find the right fit for every use case. If there's a specific ElevenLabs voice you'd like to use that isn't part of our curated selection, we'll add it for you. You can also create ElevenLabs voice clones. Ready to find your publication's voice? Book a demo with our team.

    4 min

  4. FEB 19

    Outside Interactive uses BeyondWords to scale ElevenLabs voices across multiple titles

    Outside Interactive now uses BeyondWords to deliver ElevenLabs narration across multiple editorial titles, including Outside Online, Velo, and Backpacker. Once an article is published, an audio version can be generated and embedded with BeyondWords, so subscribers can listen on the move or read and listen simultaneously. Quality voices for quality journalism. After reviewing a range of AI voice providers, Outside gravitated toward ElevenLabs voices for their quality and realism. For a brand built on immersive, human-led storytelling, anything less wouldn't cut it. Rachel Risko, Lead Product Manager at Outside, explains: "Our long-form features are crafted pieces of journalism—they deserve narration that sounds natural and engaging, not robotic. ElevenLabs produces voices that can carry the emotional weight of a 5,000-word adventure narrative without listener fatigue. "When someone's on a long trail run listening to one of our stories, the voice needs to feel like a companion, not a machine." You can listen to an extract of one of Outside's audio articles below: "It's the kind of immersive, character-driven narrative that works beautifully in audio," says Risko. Adopting ElevenLabs, without the complexity. ElevenLabs set the benchmark for voice quality, but Outside knew building the surrounding infrastructure—from CMS integration to the audio player—would be complex and time-consuming. That's when they discovered BeyondWords. BeyondWords allows Outside to use ElevenLabs voices as part of an automated publishing workflow. After a simple, one-time setup of the WordPress plugin and a dedicated project for each title, audio versions are created and embedded into articles. There are no extra steps for editors, and minimal engineering overhead. So, Outside can scale ElevenLabs audio without disrupting existing workflows. Using audio to drive subscriptions. Audio plays a direct role in Outside's subscription strategy, offered as one of the many exclusive benefits to Outside+ subscribers. For non-subscribers, the BeyondWords Player displays a "Subscribe to listen" prompt. Clicking play takes readers to the sign-up page, where audio is positioned as a premium benefit. For subscribers, the audio player displays a "Listen and enjoy this subscriber-only benefit" message that reinforces exclusivity. By giving subscribers flexibility in how they consume content, Outside can foster engagement habits that increase satisfaction and reduce churn. Outside also uses audio to support its brand identity. With a mission to help people get outdoors, the company believes that time outside is transformational and essential to human health, happiness, and connection—for everyone. By turning its editorial content into a premium listening experience, this allows their audience to enjoy the stories that inspire them while on the go. "Our readers are active people—they're out hiking, running, driving to trailheads, or commuting to their next adventure. Audio lets them engage with our long-form storytelling during moments when reading isn't practical," explains Risko. "It's about meeting our audience where they are: in motion, outdoors, living the lifestyle we celebrate." Add ElevenLabs narration to your publication. Want to offer high-quality AI narration without building and maintaining an audio stack? BeyondWords lets you deploy ElevenLabs voices through a fully automated, publisher-ready workflow—across websites, apps, and feeds. Book a demo to see it in action.

    3 min

  5. FEB 12

    Audio article best practices: 11 ways to boost listener engagement

    Audio articles get more engagement when they're presented and promoted thoughtfully. In this post, we'll share audio article best practices informed by our close partnerships with leading publishers. So you can get more readers to click play—and keep listening. Here are 11 ways to boost listener engagement: 1. Choose the right voice Choosing the right voice for your audio articles reduces friction, strengthens trust, and makes the listening experience more enjoyable. So people listen for longer and come back for more. Many publishers choose AI voices because they're easy to scale and deliver a consistent listening experience across large volumes of content. These are key factors to consider when choosing an AI voice: Naturalness and clarity: The voice should sound lifelike, with smooth pacing, natural emphasis, and accurate pronunciation, so it never distracts from the story. Brand alignment: The voice should feel true to your publication's character. Consider whether the accent reflects the communities you serve and whether the voice's personality fits your newsroom. Tone and editorial fit: The delivery should suit the content. For example, a steady tone helps serious reporting feel more credible. You may want to use different voices across different categories. At BeyondWords, we curate AI voices from ElevenLabs and Azure to give you the best possible balance of quality and variety. And we can help you find the best options for your publication. That said, we recommend voice cloning above anything else. Clone your journalists' voices Cloning your journalists' voices is one of the most effective ways to make your AI audio feel authentic, distinctive, and closely aligned with your newsroom's identity. It can deepen audience connection, encouraging listeners to stay engaged for longer and return more often. If your newsroom already has recognizable voices (such as podcast hosts) cloning lets you extend the value of their voices without adding to their workload. Publishers like News Corp Australia, SPH Media, Schibsted, and La Nación have worked with BeyondWords to create Professional voice clones for their publications. 2. Customize the audio player Customizing the player is one of the simplest ways to make audio feel more integrated with your website or app and increase playback rates. If you're using the BeyondWords Player, you can choose from Small, Standard, or Large player designs. Each offers a different balance between visibility and functionality. Whatever player size you choose, update the background, icon, and text colors so they fit naturally with your light and dark mode designs. Aim for strong contrast to ensure accessibility and make the play button easy to spot. If you prefer full control over the design and behavior of your player, you can build custom interfaces using our JavaScript, iOS, and Android SDKs. 3. Position the player (and widget) strategically We recommend positioning the audio player directly above the featured image or first paragraph of your article, so it's easy for prospective listeners to discover. Also enable the BeyondWords Player widget, so users can access the player as they scroll down the page. Alternatively, build a custom solution for your website or app. 4. Enable playback-by-paragraph JFM boosted audio engagement rates tenfold after enabling BeyondWords' playback-by-paragraph feature, which lets readers click anywhere in an article to start (or stop) listening. The feature lowers the barrier to audio by making it easy to try out, while also giving readers more control over how they consume a story. Together, these benefits can increase dwell time and improve reader satisfaction. 5. Use paragraph highlighting With paragraph highlighting, the section of text being read aloud is highlighted in a color of your choice. This reduces the friction of switching between reading and listening, improves comprehension, and makes long-form articles easier to follow. Combined with playback-...

    8 min

  6. FEB 2

    Script templates: Adapt stories for video & audio—automatically

    The most engaging videos and audios start with stories tailored to the format. That's why we're introducing script templates. BeyondWords script templates automatically transform your articles into specialized video and audio scripts, adapting the length, structure, and style to match how people watch and listen. These scripts then continue through your custom workflow to generate on-brand video and audio. It's the easy, effective way to repurpose written journalism for modern audiences. Use our pre-made storytelling templates. We've pre-built a set of script templates you can use straight away. For instance: Summary converts articles into short-form scripts ideal for engaging users who want quick updates on the move. Hook and Payoff generates high-impact videos that are great for video feeds and social platforms, where grabbing attention is the first challenge. Presenter Voiceover works particularly well when paired with cloned newsroom voices, as it enables warmer, more personable narration across your video output. All templates are designed to preserve the tone and meaning of the original article, so resulting videos and audios reflect your journalism accurately. You can find the full selection of pre-made script templates—or create your own—in your BeyondWords dashboard. Create custom script templates. With custom script templates, you can define your own instructions for how articles should transform into audio and video scripts. This allows you to align with an existing video content strategy, cater to specific video use cases, and experiment with new storytelling approaches. Want to use a different template based on brand, section, or platform? Organize your content into projects and create a template for each. If needed, you can override the default on a per-article basis. Start extracting more value from every story. BeyondWords turns articles into format-native video and audio stories at scale. So you can improve engagement, reach new audiences, and boost advertising revenue—without adding work for your team. Here's a quick overview of how audio and video automation works: 1. Integrate BeyondWords with your website and app. 2. Choose or create a script template to control how articles are transformed into scripts. 3. Choose or create a style template to define the visual look of your videos. 4. Select a voice or create a voice clone for consistent, on-brand narration. 5. Configure background music, distribution, monetization, and more. 6. Publish as normal and let audio and video versions appear automatically. Prefer to keep humans in the loop? You can create, review, edit, and manage content through your BeyondWords dashboard. To see the full workflow in action, book a demo with our team.

    3 min

  7. JAN 19

    Rethinking content extraction for audio and video automation

    Article-to-audio and video automation only works if you extract the right content first. For publishers, this step is a constant source of friction. Modern news pages are dynamic, JavaScript-heavy, and packed with non-editorial elements, but most content extraction methods still rely on fixed HTML rules tied to page structure. This can result in navigational elements, ads, and other unwanted elements appearing in audio and video assets. Or your team having to spend time specifying content manually. That's why we built a more reliable content extraction method. Introducing automatic extraction BeyondWords now offers automatic extraction, which is powered by AI. Our model interprets the context of a page and accurately identifies which text and images actually belong to the article, even when layouts vary or content is rendered dynamically. The extracted content then flows through the rest of the BeyondWords workflow to generate audio and video, based on your settings. Automatic extraction delivers practical benefits for publishers: Cleaner, more faithful audio and video versions of your articles; Reduced need for per-site configuration and manual tuning; Better adaptability across layouts, frameworks, and CMSs; and More reliable scaling across diverse publisher environments. Solving the content extraction problem took a lot of engineering effort. We evaluated several tools, compared benchmarks, and iterated several times to finally arrive at a solution that yields high-quality results. Optional filters and metadata controls are available for publishers who want to refine what content is extracted, but most sites won't need them. We also added controls that allow publishers to limit which domains the workflow is allowed to run and to set HTTP headers to bypass paywalls, so our servers always have access to the necessary content. Automatic extraction in action To give you an example, we ran a media-rich news article through BeyondWords using the automatic extraction setting. The screenshot below highlights which parts of the article were used to generate the audio and/or video versions—and which parts were automatically excluded. BeyondWords accurately identified the editorial text and images for inclusion in the audio and video versions. Unwanted elements—such as the navigation menu, advertising banner, author byline, key points, call-to-action button, image caption, content sidebar, and footer—were rightfully excluded. And this was all done automatically. The next step: Developing a change detection algorithm Improving initial extraction only solves part of the problem. For audio and video automation to meet newsroom needs, article updates must be detected and reflected accurately. A potential solution is to repeatedly fetch the page and rerun the entire extraction and AI pipeline, but this method is inefficient and could be unstable. It can also introduce unnecessary costs—especially when changes are minor or purely superficial. To avoid this, we developed a change detection algorithm. This compares newly fetched HTML with the content extracted previously to determine what has changed. So, audio and video stay in sync with article edits, without manual intervention or excessive processing. Built to fit your publishing stack Automatic content extraction is built directly into our Magic Embed integration, making it easy to enable audio and video across your publication. Add a small script to your website, then let BeyondWords handle the rest—including content extraction, audio and video generation, distribution, monetization, and analytics. You can manage settings and content centrally through your BeyondWords dashboard. Want to see how it works in practice? Book a demo today.

    4 min

  8. JAN 7

    Vertical video is the next big news format—is your newsroom ready?

    Vertical video is moving from social platforms into the heart of news products. Over the past year, publishers like The New York Times, The Economist, and CNN have introduced vertical-video feeds across their homepages and apps. These new "Watch" tabs signal a clear shift: social-style video is becoming a core output for modern newsrooms. The opportunity. Social platforms like Instagram and TikTok have made short-form vertical video a daily habit for millions. 73% of U.S. consumers watch short-form video multiple times per day, according to Media.net. And 90% of consumers are open to seeing these formats on publisher sites. This presents a clear opportunity for newsrooms to bring a popular format into their own ecosystems, where engagement can be owned and monetized. INMA's Advertising Initiative Lead, Gabriel Dorosz, says short-form vertical video is "the biggest ad opportunity for news." Advertisers are expected to redirect US$146 billion from display advertising into short-form video advertising by 2028. Publishers are also using vertical video to drive subscription revenue. The Economist's paid subscribers have doubled their vertical video consumption over the past year, according to Nieman Lab, helping the publisher to tackle the "unread guilt factor" that so often drives subscription cancellations. The challenge. To deliver a TikTok-style experience inside your news app, you need a constant supply of timely vertical video. Traditional production workflows simply can't keep pace. Each clip demands scripting, recording, editing, approvals, and coordination—an intensive chain of tasks that makes high-volume output hard to sustain. And by the time a video is ready, the story's moment may have already passed. Costs add up quickly, too. Relying on traditional video production makes it tough to generate a return on investment. Newsrooms need a fast, scalable way to turn articles into vertical video. That's where BeyondWords comes in. The solution. BeyondWords automatically converts your articles into vertical videos and delivers them directly into your websites, apps, and feeds. So you can publish videos as quickly and consistently as you publish stories. It's the simple, commercially smart way to satisfy modern media habits. Videos can be fully customized to fit your brand and audience. You can: turn full articles into video or generate video-specific scripts using AI; choose an ElevenLabs or Azure voice, or clone your own voices for narration; auto-insert relevant images and videos from Getty or your own DAM system; and customize the visual style of your videos, including captions and branding. Our platform can also generate horizontal videos and audio versions from the same article, allowing you to repurpose stories across multiple formats and channels without additional work. Just integrate, configure, then let BeyondWords do the rest. Want to know more? Book a demo with our team.

    3 min
See All (50)

About

Stories, insights, and announcements from the BeyondWords blog—read aloud by AI. Learn how publishers are using audio and video to shape the future of digital storytelling.

Information

  • Creator
    BeyondWords
  • Years Active
    2025 - 2026
  • Episodes
    50
  • Rating
    Clean
  • Copyright
    © BeyondWords
  • Show Website
    BeyondWords Blog