Spoken V1 Release Notes – Official Launch, Integrated Pricing & Payments, Multi-Voice Upgrade, and the Brand Sheds Beta!

Spoken V1 marks a truly defining moment — our official public launch and the transition out of beta. This is the version built for everyone, everywhere, with the stability, features, and polish to back it up and arm authors with the absolute best in AI audio narration.

With V1, we’re introducing an integrated pricing system that gives authors complete flexibility: pay per project when you need us, or subscribe for maximum creative output. Our Multi-Voice upgrade delivers the most accurate and natural-sounding AI full-cast narration ever produced, and is getting better each and every day.

This release also brings a sleeker, faster, more powerful platform, a refreshed UI, and the debut of Spoken’s first full brand image rollout — a bold, unified look that reflects who we are and where we’re headed. Spoken V1 is more than a feature update. It’s the start of Spoken as a fully realized product, ready to transform how authors create and publish their work.

Integrated Pricing & Payments

Spoken sets a new industry standard. A seamless way to budget for your audio projects, with two flexible options:

Pay Per Project – $10 per 5,000 words
(Rounded up to the nearest 5,000)

• Includes edit credits equal to 25% of your word count for refining passages, changing voice selections, or correcting AI hiccups.

• Unlimited voices at no extra cost.

• Custom voices generated via Spoken’s prompt analysis or your own prompts, including reusable personal voice clones.

• Full Studio access to control speed, padding, volume, and emotions.

• Free mastered downloads to monetize anywhere.

• Optional free streaming on Spoken for reader discovery.

Monthly Subscription – $50/month

• Includes all Pay Per Project features plus 50% off narration costs.

• Ideal for prolific authors, backlist revival, serialized content, and creative experiments when the words are flowing.

Multi-Voice Upgrade

Formerly known as Multi-Character Multi-Voice, our updated Multi-Voice system delivers pinpoint character analysis and dynamic pacing that naturally adapts to the rhythm of your story. This is our most expressive, most precise full-cast AI narration to date — ready for complex dialogue, subtle tone shifts, and vivid character performances. It has been built to capture the awe of all of your fanbase, and all of your future listeners.

UI & Branding Take a Bold Step Foward

• Redesigned Create page for clearer navigation and workflow.

• Updated banners, visuals, and layout to align with our V1 brand direction.

Platform & Performance Improvements

• Greatly optimized servers for faster parsing, sharper character recognition, and smoother narration generation. This is Spoken with the best engine under the hood. 

• Greater stability and reliability for large manuscripts and complex projects.

• Improved multi-tasking Studio workflow, for narrating individual installments while passages of the work are still being generated.

Spoken Brand Image V1

Spoken V1 doesn’t just perform differently — it presents differently. This release marks the debut of our first fully-realized brand identity: a bold, cohesive visual language that reflects the creativity, sophistication, and impact of the stories our authors tell.

From sleek UI updates to striking banners and promotional materials, every touchpoint with Spoken now feels polished, deliberate, and unmistakably ours. Beyond the platform, our V1 brand campaign is live — showcasing expressive multi-voice narration and positioning Spoken as the definitive home for authors who want their stories to be heard, remembered, and shared.

Spoken Into Existence Speaks Volumes (Literally)

It’s done! The last episode of Spoken Into Existence is now officially “into existence.” Both the trailer and final documentary-style, behind-the-scenes episode are streaming on our YouTube channel, and the novella, "Sackcloth & Blood: Volume 1 – WAR," is published on Spoken! 

Spoken Into Existence is a perfect example of how authors are collaborating and creating through Spoken in this new era of storytelling. This is the first novella in a bold, audio-first series created in real time, with Spoken, by NYT bestselling author Joseph Nassise and acclaimed novelist Tom Leveen. From blank page to fully-voiced story, this project redefines what’s possible for modern authors — giving them complete creative control over their audiobooks using Spoken’s AI-powered narration studio.

It was written specifically for audio, voiced with AI in Spoken Studio, and published as it was completed. Spoken Into Existence captured the whole process, demonstrating how authors are becoming directors of performance — casting characters, shaping tone, and sculpting every beat of their story as an immersive audio experience. No gatekeepers. No barriers. Just pure creative power.

This is the future of storytelling – and this collaboration is the kind of thing we can’t get enough of! Thanks to Joe and Tom for reaching out to us with this idea, and to our in-house filmmaking team, with Joshua David Pivato leading the charge, for bringing it to life through video.

We encourage you to tune in and see the evolution of this groundbreaking project and see how the studio experience is inspiring creative collaboration. Catch all the episodes of Spoken Into Existence here.

Spoken Beta: V0.9.6 Release Notes: API Unleashed, Multi-Cast Upgrade, and the Sound of Spoken

Another Leap Forward in Full-Cast Narrative Cohesion – Spoken Studio API Unleashed with an Easy-Peasy Integration Option – and the Sound of Spoken

Spoken Studio is now open to the world. Our public API lets publishers and platforms generate full-cast audiobooks programmatically. Since our last release, we’ve supercharged MCMV even further. With deeper emotional cues and wickedly smart cadence. Spoken’s performances now sound more alive than ever. And with every first installment, listeners will hear our new audio logo—’Made With Spoken’—paired with our jingle. A signature sound for a new standard in spoken storytelling.

MCMV (Multi-Cast/Full-Cast narration): Another leap forward

We’ve continued refining our MCMV (Multi-Character Multi-Voice) system from our previous release, expanding the engine’s ability to generate expertly accurate emotional cues and natural pacing for complex, cast-driven projects. These enhancements unlock tremendously more immersive, natural, and studio-quality performances for full-cast audiobooks.

Spoken Studio API Integration Framework

This release marks a major milestone: Spoken’s B2B tools are now live and publicly available. Whether you’re a developer, publisher, or platform looking to supercharge your user experience, API.Spoken.press unlocks fast, scalable, and high-quality audio production—programmatically.

The fastest, easiest way to create full-cast audiobooks—now open to all.

Spoken Studio API Easy-Peasy Integration Option

Industry partners can seamlessly connect users to a fully pre-configured Studio environment with a single authentication and project-driven link. Great for distributors of indie-author works!

Pass in your own external Project ID and Client ID to spin up audio projects instantly.

Full Spoken Studio API for full-service partners

Fully integrate project creation, management, and narration of all types of works using Spoken's Studio API.

Scalable Audio Workflows

From demos to full-scale rollouts—Spoken powers millions of listening experiences.

Learn more and explore documentation at API.Spoken.press

New: “Made With Spoken” Audio Logo

Every Spoken story now opens with a cinematic jingle and voiceover tag—“Made With Spoken”—crafted with our in-house HumeAI voice. It’s crisp, distinct, and unmistakably us.

Listen to it HERE

Faster Performance

Expect noticeably faster analysis and parsing across the board. We’ve implemented infrastructure-level speed improvements that make the Studio feel more fluid and responsive.