Spoken Integrates Hume AI to Help Storytellers Tell Stories With More Emotion

Spoken has integrated Hume AI’s Text-to-Speech as the team here strives to offer intuitive, engaging audio performances for its authors. "Spoken's integration of Hume AI is empowering authors to create more emotionally resonant, performance-driven audiobooks. The voices are studio grade, emotive, and, with Hume, we’re now able to cast voices for teen and children characters. That’s something our fiction authors in particular have been asking for,” said Spoken CEO and Founder Phil Marshall. 

Hume AI Chief Operating Officer Janet Ho elaborated on how Spoken is utilizing Hume’s voices. “Phil and his team have designed an intuitive technology that’s evolving at a fast pace. We’ve witnessed their progress in beta and are excited to see their product in full production. When they came to us in search of a voice partner, our focus on highly empathetic voices was a perfect fit. Now, as we listen to the stories that are streaming on Spoken with Hume AI voices, we can hear for ourselves what a great collaboration this is.”

As Spoken nears the end of its beta phase, we’re positioned to be a go-to resource for authors and their publishing and distribution partners. Breakthrough and bestselling authors alike are using Spoken’s studio and Hume’s voices to create audio projects that never would have been heard before, whether single narrator, dual narrator or multi-cast, and across every genre.

Spoken author Jessica Wheeler shared her recent experience in using the platform’s automated option for voice generation, “I absolutely love the generator. I feel like the quality is even better.” She also elaborated on the addition of Hume voices to Spoken’s library. “I”m very excited about the different ages for voice selections. The Hume voices are really good! Getting a child's voice is huge and I know other authors on Spoken are requesting that quite a bit.” 

Marshall is utilizing the Spoken studio to narrate and promote his own debut science fiction novel, Taming the Perilous Skies, which is scheduled to release in September. “We founded Spoken to give indie authors like myself an accessible and affordable path to success with producing high-quality audio. We’re thrilled to partner with Hume AI to help us achieve that goal.” 

Some of the most sought–after creator features in AI narration are found within the Spoken studio experience, including:

• Automated analysis of story for summary, comparable works, smart topic tags, and safety ratings

• Automated analysis of narrative style and every character for automated custom voice narration

•  Emotive voices across all languages and demographics 

•  Fine-tuning control over pitch, emotion, volume, speed and delivery of every passage, with audiobook quality mastering to ensure a great end result

• Options for single, multi-cast and dual narration (we heard ya, romance writers)

• Personal voice cloning and real-life voice recording for personalized introductions

• Custom pronunciation lexicon to ensure unique words sound perfect (yep, we heard you too, sci-fi crowd)

• Marketing assets to use on social channels, websites and newsletters

• Chapter excerpts to use as lead magnets teasers for multi-chapter audiobooks, sample projects, short works, etc.

To listen to or create a narrated audio project on Spoken, visit www.spoken.press and follow @spoken.press on social. 

Spoken Into Existence Ep 4: Inside The Studio

In Episode 4 of Spoken Into Existence, listeners are invited behind the curtain—into a digital writer’s workshop where story meets sound, and authors transform into audio directors in real time. (Thanks to two bestselling authors, Joseph Nassise and Tom Leveen, for letting us hang out with them.)

This episode is about craft. Specifically, the craft of performance—how every line in a story becomes a sonic event, sculpted with precision inside the Spoken Studio.

We’re no longer simply writing books. We’re building experiences.

Welcome to the Spoken Studio: Creative Control Redefined in the Studio of the Future

This is the future of audiobook creation—interactive, iterative, immediate.

Inside the Spoken Studio, authors like Joseph and Tom aren’t just uploading manuscripts. They’re entering a dynamic production environment where every element of their story—narrator tone, character timbre, emotional pacing—can be dialed in, down to the sentence.

Here, you can:

• Generate voices with surgical precision using structured vocal prompts

• Adjust performance at the passage level—modifying speed, tone, even emotion

• Preview dialog in-scene, evaluating how voices interact in dramatic sequence

Edit narration like you would dialogue in a play, removing unnecessary attributions and letting the voice do the storytelling

And it happens in minutes, not months.

What You See. What You Hear. What You Control.

Watch the manuscript light up with color-coded voice tags. Click into a line. Update the voice, the emotion, the pacing. Need a whisper? Select it. Want a shout? It’s two clicks away. Don’t like how the line lands? Rewrite it—instantly—and generate the new read in seconds.

In the traditional process, these changes would cost time, coordination, and thousands in studio fees. Here, they cost a few keystrokes.

Even complex moments—like summoning the voice of a supernatural antagonist—become part of the toolkit. A blend of AI modeling and manual finesse makes it possible to test, reject, revise, and relaunch a vocal performance until it resonates with narrative intent.

One character (Moxie) might be the testing ground, but the episode reveals something bigger: the blueprint of a new kind of authorship.

This Isn’t Audio Production. It’s Story Architecture.

What we’re witnessing is a tectonic shift in how stories are made.

The Spoken Studio is more than a tool. It’s a co-creative space where authors no longer hand off control—they own it, wield it, and remix it on demand. Just as screenwriters evolved into showrunners, authors now step into the role of sound architects.

It’s not about replacing the page—it’s about building the performance layer. So the question becomes … “When storytelling becomes a form of sound engineering, how does your role as an author evolve?” Discover the answer to that question by entering the studio at Spoken.

Learn more about Joseph Nassise.

Learn more about Tom Leveen.

Watch More Episodes

Experience all the episodes of Spoken Into Existence on YouTube.

Learn more about Spoken.

Spoken Beta V0.8.8: Hume AI, Automated Custom Voices, and Marketing Kits

This release brings major upgrades to how your Spoken projects are cast, customized, and shared. With v0.8.8, we’re introducing a new voice service into both the voice library and custom voice generator, groundbreaking one-click custom voice automation for every character in your story, and marketing kits to equip authors with high-value Spoken assets built for promotion.

Hume AI

We've now integrated Hume AI, featuring their emotionally intelligent voice generation, into both our voice library and custom voice tools. Hume-powered voices support a broad range of character types, accents, and emotional performances.

Automated Custom Voices

Automated Custom Voices allows authors to choose between 11Labs or Hume voices and, with one click, have Spoken analyze their story, identify every character, and generate a unique custom voice for each one. No manual voice selection—just an instant, ready-to-edit cast waiting for you in Passage Editing. Available to use across any of our narration formats.

Child  and Teen Character Voices

We’ve added dedicated Child and Teen voices to the Spoken voice roster—ideal for middle grade fiction, YA, or flashback scenes. These new voices are available via Hume.

You’ll find these voices:

• Auto-selected when characters are detected as children or teens.

• Available in the voice picker listed as “Child”.

Want your young adventurer to sound exactly right? Now they can.

Marketing Kit

You can now promote your Spoken story with professionally packaged assets that come ready to share.

Every published project automatically generates a Marketing Kit with branded cover art formatted for social media. Find your kit on your Project Page after publishing.

Note. The project must be set as public, and have mastering enabled.

Formats available: 

• Square Image (Instagram)

• 1080x1920 Vertical Format

• 1600x900 Horizontal Format

Global Speed and Volume changes

Instead of adjusting speed and volume one passage at a time, you can now set global speed and volume for each character directly from the Voices tab. Just select the voice you want, make your changes, and click Continue—your adjustments will apply across your entire project.

Other Fixes and Changes

We’ve removed the “Basic,” “Enhanced,” and “Advanced” voice tiers. All voices are now categorized simply as Premium or Voice Actor for a cleaner, more consistent experience and higher quality voice choices.

We’ve also removed the Performance Insights button from user profile pages due to its inaccuracy. Users should rely on the play and like counts on project pages. 

Lastly, we removed estimated costs of narration because we're still evaluating the options for how best to have our users pay for narration.