BeyondWords Blog

About BeyondWords Blog

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.

Publisher

BeyondWords

Category

business · business · technology · technology

Language

en

Explicit

No

First episode

7 Aug 2019

Latest episode

13 Oct 2026

Latest episodes

93 episodes in the feed.

1. 

   13 Oct 2026

   How El Líbero takes its morning briefing beyond the inbox

   Every weekday morning, El Líbero gives its audience a head start on the news. Selección Nacional, the publication's most-read newsletter, and Lo Mejor de la Prensa, its audio edition, update audiences on the latest news from across Chile. Until recently, this meant an early start for podcast host Magdalena Olea Urrejola. Now, Magdalena sleeps while her voice goes to work. El Líbero worked with BeyondWords to create a professional clone of Magdalena's voice. The team can submit scripts through our API and receive the finished audio in seconds. That gives Lo Mejor de la Prensa the familiar voice listeners already know, with a faster and more predictable production process. Here's a short demo of Magdalena's voice clone: "It's important to understand that recording audio early in the morning is no ordinary task," says Felipe Morales, CTO at El Líbero. "Most people do not wake up with their voice in perfect condition for recording: you need to prepare your throat and diction, avoid nasal congestion, and meet a long list of other conditions. And that is without even mentioning staying up late the night before. "You can forget about all of these issues when it is no longer the journalist who is recording, but simply her voice." El Líbero is transparent about the use of AI narration in Lo Mejor de la Prensa. Every episode concludes with a spoken disclosure, and a written notice appears in the show's Spotify description. Because Magdalena's cloned voice sounds so close to her own, listeners could easily assume she had recorded the episode herself. The disclosures remove that ambiguity, helping the publisher maintain trust with its audience and meet modern ethical standards. They also reassure listeners that AI usage is limited to narration. The reporting, editorial decisions, and script remain the work of El Líbero's human team. Each morning, reporters working several hours ahead of Chile review the latest stories from the national press, allowing them to prepare the morning briefing before most of its audience wakes up. Alongside Selección Nacional, they write a dedicated script for Lo Mejor de la Prensa. The two cover the same news, but are written for different formats. For the podcast, the team leaves out elements designed for reading and browsing, then reshapes the remaining stories into a continuous narrative. The opening is shortened, spoken transitions connect each topic, and the segments are arranged to create a clear progression through the day's news. The audio edition lets people catch up while commuting, getting ready for work, or doing anything else that makes reading less convenient. "You can be just as well informed whether you read the newsletter or listen to the podcast," says Felipe. A pre-recorded intro and outro are automatically stitched together with the narration in BeyondWords, so the El Líbero team receives a complete and polished audio file ready to distribute. From there, Lo Mejor de la Prensa reaches audiences across multiple channels. Every episode is published for free on Spotify, giving users an easy way to make the briefing part of their existing listening routine. El Líbero also embeds each podcast episode on its website homepage. "This helps introduce the podcast to new listeners who may not know about it and who may never have considered that, in just five minutes, they can become fully informed about the most relevant news of the day," Felipe explains. Paying users can also receive the podcast through WhatsApp, the most used messaging app in Chile. Subscribers were already listening to another El Líbero podcast this way, giving the team confidence that the channel could work for Lo Mejor de la Prensa, too. Delivering the briefing through WhatsApp also puts it somewhere subscribers are likely to look early in the day. Rather than having to seek out the latest edition, they find it alongside the messages they are already checking each morning. El Líbero first adopted BeyondWords to narrate ar...

2. 

   6 Oct 2026

   Eleven v4: Voice cloning this fast should not sound this good

   Eleven v4, the latest voice model from ElevenLabs, is available now in BeyondWords. As someone who spends a lot of time working with AI voices, I can tell you it represents a striking leap in quality. In my testing, v4 voices read out articles much like a professional narrator would. Prosody is natural with emphases placed to give the correct meaning to each sentence. Delivery is context aware, so the article content has real feeling, and longer pieces maintain their flow and character much more consistently from one section to the next. This ElevenLabs model also supports IPA transcriptions for finer control over custom pronunciations, along with a wider range of languages and accents. But instant voice cloning is where things really get interesting. I've found that Eleven v4 produces significantly more accurate instant voice clones than previous models. With as little as 10 seconds of recorded speech, it can capture far more of a speaker's accent, delivery, and individual style. You can listen to my own v4 instant voice clone narrating this article. For publishers, this level of fidelity changes what instant voice cloning can realistically be used for. It becomes much easier to create audio around the individual voices, accents, and styles that already exist within a newsroom. Instant voice cloning only requires a short, approved audio sample and is included for free in every BeyondWords subscription. Once generated, v4 clones can be applied to the articles you choose. So, every story can be automatically narrated by the person who wrote it, in a voice that sounds more realistic than ever. For podcast hosts, broadcasters, and other journalists already known by voice, this adds instant familiarity and personality to audio content. Regional publishers can preserve local accents that make listening experiences feel much more authentic to the communities they serve. Better voice cloning also gives publishers another way to build a distinctive audio identity and create richer experiences that feel recognizably their own. Voice is increasingly becoming part of a publisher's identity, not just a way of narrating an article. As audiences spend more time with audio, headphones, speakers, and voice interfaces, the voices they associate with a publisher will matter more. Publishers like La Nación are already proving the concept with our highest-quality professional voice clones. With v4 in BeyondWords, bringing this kind of experience to more newsrooms becomes much easier. Already a BeyondWords publisher? You can create an instant voice clone and start testing it with v4 in just a couple of minutes. Go to Custom voices in your organization dashboard, click + Voice, and follow the steps. Once your clone is ready, select the v4 model and head to the Editor to start testing. You can also try v4 with premade and generated voices, or talk to our team about creating an even higher-quality v4 professional voice clone. Not yet a BeyondWords publisher? Book a demo to see how you can keep up with ElevenLabs' latest voice models through a platform built for publishers.

3. 

   25 Aug 2026

   Introducing the BeyondWords MCP How it works What you can do Get started

   With the BeyondWords MCP, you can configure and manage your BeyondWords account, projects, and content directly from your AI assistants. For example, you can: Ask Claude to set a new pronunciation rule Ask ChatGPT how many listens your publication got last month Ask Cursor to update the BeyondWords player colors to match the styles in your codebase Work with BeyondWords through conversation, in the AI assistants you already use. MCP, or Model Context Protocol, is an open standard that allows AI assistants to connect to external tools and data sources. The BeyondWords MCP creates a secure, private connection between a compatible AI assistant and your BeyondWords account. The BeyondWords MCP works with Claude, Claude Code, ChatGPT, VS Code, Cursor, and other AI apps supporting remote MCP servers using Streamable HTTP. Depending on the app, this may be referred to as a custom connector, plugin, or server. There's no server to run or API keys to manage. You sign in securely through OAuth and choose whether to give your assistant read-only or write access to your BeyondWords account. And the connection is totally private to you: other users won't be able to access your BeyondWords data. The BeyondWords MCP currently allows you to: Create and update projects Create, update, regenerate, and manage content Explore analytics and performance Create and manage pronunciation rules Manage and configure voices View and update player settings You can combine information and actions from BeyondWords with each assistant's own capabilities and other connected tools. For example, you can ask ChatGPT to pull listening data from your BeyondWords projects, analyze the results, and use them to create a report in Google Docs. This is just the beginning for the BeyondWords MCP. We'll be adding more capabilities over time, and we'd love to hear what you'd like to do with it next. To connect your BeyondWords account to an AI assistant: 1. Log into your BeyondWords dashboard 2. Click your profile picture, then select Profile 3. Go to Connected apps and click Connect 4. Choose the AI app you'd like to connect, then follow the instructions provided We'd love to hear how you're using the BeyondWords MCP and what you'd like to do with it next. If you have any questions, feedback, or suggestions for new capabilities, get in touch.

Contact BeyondWords Blog

Guest appearances

Books guests

Based on episode analysis; this does not confirm that the show is currently accepting guests.