Spoken Beta: V0.9.4 Release Notes: Natural Cadence, Emotional Precision, and Massive MCMV Level Up

Spoken just got sharper, smoother, and more emotionally tuned. This release introduces a significant upgrade to our parsing and narration engine—fine-tuning padding mechanics and emotional cueing to deliver professional-grade pacing and performance across all narration formats.

Smarter Parsing, Natural Performance

Our parsing mechanic now operates at a more granular level, adjusting rhythm and spacing to reflect the natural cadence of your story. Padding logic has been reworked to better mirror the expectations of professional audiobooks—introducing well-timed pauses at punctuation, line breaks, speaker transitions, and more. The result is narration that flows with intention, clarity, and a distinctly human rhythm.

Emotional Cueing—Leveled Up

We’ve enhanced our emotional detection and instruction engine, enabling deeper, more expressive performances from every voice. We now generate more specific, fine-grained emotional instructions for each passage and line of dialogue, resulting in noticeably richer and more nuanced performances. It’s a major step forward in capturing the emotional heartbeat of every story.

A Milestone in Multi-Character, Multi-Voice (MCMV) Narration

This release pushes our MCMV narration to a new level. As more creators adopt multi-character formats, Spoken is becoming the definitive platform for layered, cast-driven storytelling at scale. This upgrade lays critical groundwork for even more transformative leaps coming soon in multicast preparation.

Terms of Service Update

We’ve updated our Terms of Service to clarify how Service-Narrated Content may be accessed and distributed. Please review the latest version in your account settings for full details.

https://ihave.spoken.press/tos

Spoken Beta v0.9.2 Release Notes: Publishing Integration, Voice Prompt Clarity, and a Multicast Transformation on the Horizon

We’re excited to announce our first publishing integration partnership and several improvements to voice creation, narration clarity, and interface behavior. With major updates to multicast passage preparation just around the corner, this release lays the foundation for faster, smarter audiobook production tools.

Our First B2B Publishing Integration

Our first B2B publishing integration marks a major milestone in connecting external author platforms directly to the Spoken Studio. (Yep—we’re taking the show on the road!)

Through this new integration, authors can now seamlessly transfer their manuscripts into Spoken from partnered platforms to then proceed through the automated narration process, whether using single, dual, or multi character multi voice. 

This is a key step toward our mission to empower authors with world-class audio tools, making professional, multi-voice narration accessible from the platforms where they already produce and distribute their written work.

More integrations are on the way—this is just the beginning.

Voice Prompt Clarity (Custom Voice Creation)

When creating a custom voice, users will now get clearer input feedback when entering prompts:

• A live character count now displays: “X characters (100min – 300max)”

• The input field now enforces a 300-character limit to avoid silent errors

• The Generate button clearly disables when the prompt falls outside the allowed range

This helps eliminate confusion and improves usability during voice creation.

Stability Improvements for Narration Flow

To protect your projects during heavy processing, we’ve introduced automatic locking of editing tools while narration is in progress. During generation, casting, or narration:

• Controls for voice changes, passage edits, or deletion are temporarily disabled

• Users can cancel the process manually at any time, which unlocks all options again

This change prevents workflow conflicts and ensures a smoother narration experience.

Additional Fixes & Improvements

We’ve added automatic cleanup for empty passages, resolved inconsistencies in channel tag display, and ensured updated voice prompts appear immediately in the interface. Character order in the Voices tab now remains consistent across installments.

Multicast Upgrades Are Coming

We're on the verge of a transformative upgrade to our multicast passage preparation, making it faster, smarter, more automated, and more scalable. This will be a significant leap forward in how multi-voice projects are built and perfected.

Stay tuned—this one’s big.

Spoken Beta v0.9.0 Release Notes: Automated Narration with Magic Button, and Self-Service Downloads

Spoken gets even more powerful with the v0.9.0 release. We’re continuing our mission to make audiobook creation as seamless—and magical—as possible. This release introduces full manuscript automation via the new “Feeling Lucky?” toggle, letting users generate a fully narrated, fully cast project in one click. We’re also rolling out automated delivery of downloadable project files, removing friction for authors who want to take their audiobook with them.

Automated Audiobook Creation (The “Magic” Button)

We’ve always said Spoken should feel like magic—and now it does.
With the new “Feeling Lucky?” toggle, authors can choose to let Spoken take the reins completely.

After you’ve selected Auto-Generate a Custom Voice for every character, this incredible new feature becomes available. When you enable it, the familiar Make Spoken button becomes Make Spoken Magic, triggering a fully automated process that:

• Generates custom character voices across your manuscript using either Hume AI or ElevenLabs

• Automatically narrates every passage using those voices

• Delivers a complete, polished audiobook with zero manual effort

No casting. No narration setup. Just one click, and your story comes to life—ready for intros, mastering, and publishing.

Self-Service “Take It With You” (TIWU)

With our new Self-Service Take It With You system, authors receive their fully mastered, industry-standard audiobook files instantly via email—dispatched directly into your inbox the moment you hit download. The entire process is fully automated, with files packaged and delivered into your hands.

Here’s how it works:

• Click Download on any published project, then click on “Take It With You (TIWU)”

• Spoken will email you the full TIWU package, with MP3 files for every installment

Instant access to your files, whenever you need them.