Spoken v2.1.2 — Spoken Multi-Cast™ - A Major Change in Workflow

Better Preparation Tools, More Accurate Narration

This release introduces new pre-production tools for Magic Mode, giving you greater control over reviewing passages and speaker assignments before generating audio. It's a powerful new preparation step that helps streamline your workflow. We've also included general improvements and bug fixes across Text-to-Speech, Speak-Its, and overall platform performance.

---

Pre-Production & Magic Prep Features

Creating accurate narration starts with accurate preparation. Version 2.1.2 introduces a dedicated pre-production workflow for Magic Mode, making it easier to review and refine your content before generating a base narration layer.

What's New

• A new Manage Passages experience allows you to review and edit passages before narration begins.

• Verify and update character attribution, speaker assignments, speaker cues, passage text, accents, and emotion cues in one centralized workflow.

• Generate narration for a single chapter or your entire work, providing greater flexibility when creating or updating audio.

• Review passage changes and regenerate only the content that needs updating, without reprocessing your entire project.

• Enhanced passage editing tools make it easier to fine-tune speaker details and ensure your narration is prepared exactly as intended.

Why It Matters
These new preparation tools help ensure your base narration is as accurate as possible from the very first generation, reducing the need for post-production corrections while preserving the simplicity and speed of one-click narration.

---

Bracketed Cues Support in Text-to-Speech

Text-to-speech now supports bracketed cues within passage text when editing a passage. Use cues such as [British accent], [whispers], or [excited] to influence the delivery of a specific word or phrase.

For the best results, think of narration control in three levels:

• Speaker Cues apply to every passage spoken by that character.

• Emotion Cues apply to the entire current passage.

• Bracketed Cues apply only to the specific words or phrase enclosed in brackets.

Because these controls can influence one another, avoid using them to accomplish the same effect at multiple levels. For example, if you're using a bracketed cue to create a specific emotional moment within a sentence, it's often best to remove the passage-wide Emotion Cue so the two instructions don't compete.

Bracketed cues are intended as a precision tool for isolated moments—not as a replacement for Speaker or Emotion Cues.

(Note: Bracketed cues are supported on Magic Mode + 11L Voices only; they are not supported for Hume models.)

---

Improvements & Fixes

• General improvements to Text-to-Speech inputs and processing.

• Performance and reliability enhancements for Speak-Its.

• Improved stability across narration and content generation workflows.

• Various bug fixes and behind-the-scenes optimizations for a smoother overall experience.

Spoken Studio v2.1.1 Release Notes: Foundation & Performance

Faster Workflows. Smarter Voice Systems. Stronger Reliability.

Following the rollout of Magic Mode and the continuity enhancements introduced in v2.1, Spoken Studio v2.1.1 focuses on strengthening the systems that power audiobook creation behind the scenes.

This release delivers meaningful improvements across voice management, project workflows, editor behavior, system responsiveness, and production reliability.

In short:

Spoken Studio should feel faster, smarter, and more predictable throughout the creation process.

---

Workflow & Editor Refinements

We've continued refining the authoring experience throughout Studio.

This release includes improvements to editor behavior, project management workflows, voice preview handling, narration preparation tools, and character management—helping reduce friction and keep production moving smoothly.

Notable improvements include:

• More accurate character analysis for voice assignments, prompts, and accent detection.

• Improved character merging and deduplication to reduce duplicate entries across projects.

• Enhanced voice preview behavior with improved end-of-preview timing for a more natural listening experience.

• Longer preview endings. Based on author demand—particularly those distributing through Author’s Republic—voice previews now include additional trailing silence, making it easier to meet retail submission requirements.

Collectively, these updates create a significantly smoother production workflow.

---

Performance & Reliability Improvements

• Voice retrieval performance for faster voice loading and assignment.

• Project processing workflows.

• System reliability.

• Audio preparation pipelines.

• Internal quality control systems.

• Magic Mode precision, reducing audible artifacts at the beginning and end of generated clips.

• Improved accent preservation during spoken generation when narrator and character voice settings are correctly configured.

These updates help ensure Studio remains responsive and dependable as projects become larger and more ambitious.

Improved Accent Consistency:

When character voice settings are configured correctly, Spoken Studio now does a significantly better job preserving accents throughout the narration process, resulting in more consistent performances across chapters and scenes.

Best practice: Before clicking Make Spoken, verify that each character's Speaker Cue and Accent are correctly assigned—particularly when a character's accent differs from the chapter narrator. If no accent is displayed, simply click the character's colored voice bar to open the voice settings and add the appropriate Speaker Cue and Accent before generating audio.

---

Bugs & Fixes

As part of v2.1.1, we've addressed a variety of bugs and edge cases throughout the platform, including:

• Text processing improvements

• Character handling refinements

• Editor behavior fixes

• Quality-of-life improvements throughout Studio

• General stability and performance enhancements

---

Looking Ahead

This release makes every author, publisher and producer’s workflow better.

v2.1.1 represents an important investment in the systems underneath Spoken Studio — strengthening the platform as we continue expanding what's possible for AI audiobook narration.

Spoken v2.1 Release Notes — Continuity and Creative Control

Magic Mode Character Accent Control, Chapter-Specific Narrator Accent Changes, and Cross-Project Lexicon Carry-Over

Fresh off the launch of Spoken Studio V2 and Magic Mode, v2.1 delivers the first major expansion to Spoken Studio with an emphasis on personalization and continuity systems.

This release introduces Character-Level Accent Control for Magic Mode and Cross-Project Lexicon Carry-Over— two powerful additions designed to give authors, producers, and publishers greater influence over performance while dramatically reducing repetitive production work.

Whether you're producing a single title, a long-running series, an author's backlist, or an entire publishing catalog, v2.1 helps ensure your creative decisions remain consistent from project to project.

---

Magic Mode Default Narrator Accent Changing by Chapter

As Spoken builds up the rudimentary and cadence layers to create perfect cohesion, dominant narrator accent by chapter is deep-seated and very important. However, before now, you could not alternate or change that dominant accent by chapter. Being able to define different narrator accents by chapter is essential if you alternate your narrators or have duel / duet narrators, and those alternating narrators have different accents. 

We've fixed this by enabling you to define chapter-specific pacing and accent overrides by chapter. This is for your dominant narrator only, as speaking characters will carry through their speaker cues and voice timbre for great delivery.

As you scan down through your chapters, we've also detected who the likely narrator is, to make it easier for you to remember which chapter narrators might require a different pacing or accent from your book's default.

---

Magic Mode Character Accent Control

Magic Mode has always analyzed your manuscript for character and narration cues, including likely accents, speech patterns, and delivery styles.

However, if a character's accent wasn't clearly established within the text itself, there was previously no reliable way to ensure that character would consistently perform with a different accent than the chapter's primary narration voice.

With v2.1, that's now possible.

After completing Lexicon review and before narration begins, you'll now find a new editable Accent & Tone Cue field within the Voices tab.

Whether Spoken has automatically assigned your voices or you've cast them yourself, you can now provide direct performance guidance for individual characters — specifying accents and tone characteristics that may not be explicitly stated in the manuscript.

Once selected, these cues become part of the Magic Mode narration process and are carried throughout the character's performance.

Many stories contain characters whose voices are clearly envisioned by the author, but whose accents or delivery styles may never be directly described on the page.

Now, Speaker Cues can help bridge that gap.

---

Cross-Project Lexicon Carry-Over

Your pronunciation work now follows you.

When a new project is analyzed, Spoken can identify words and phrases you've previously corrected in other projects and automatically make those pronunciation replacements available for reuse.

Character names.

Fantasy worlds.

Invented languages.

Specialized terminology.

If you've already taught Spoken how something should be pronounced, you shouldn't have to do it again.

With a single click of the Apply button, matching Lexicon replacements can be brought into the current project.

You can also choose to save newly created pronunciation replacements into your growing personal Lexicon library, allowing future projects to benefit from the work you've already completed.

The result is stronger continuity across series, catalogs, and publishing programs — with significantly less setup work along the way.

---

Consistency Across Every Title

As more authors, producers, and publishers build larger libraries inside Spoken, consistency becomes increasingly important.

v2.1 helps ensure that character names, locations, terminology, and creative decisions remain aligned across projects, while giving creators even greater influence over the performances that bring those stories to life.

A truly meaningful release for anyone building more than a single audiobook.

---

Bugs, Fixes & Quality Improvements

We've also included a variety of improvements throughout Studio, including:

• Improved ePUB upload handling and processing

• Clearer in-Studio guidance and instructional messaging for Magic Mode workflows and editing controls

• Faster project preparation workflows

• Increased precision 

• General stability improvements and bug fixes

---

Looking Ahead

Spoken Studio V2 introduced a new way to produce audiobooks.

v2.1 builds on that foundation by making Magic Mode more customizable, more consistent, and more responsive to the creative choices that make every story unique.

The more you create with Spoken, the more Spoken works the way you do.