Changelog

March 31, 2026

Sound Effects

Drop your listeners straight into the scene. The waveform editor now includes four one-click sound effects: Static for that old-radio crackle, Phone for tinny telephone calls, Radio for authentic AM/FM tuning with sweeping static and squeals, and Echo for cavernous reverb. Effects are stackable — layer phone on top of static, or echo on top of radio — and the result saves with your snippet.

Background Audio Tracks

Set the mood with ambient sound layers. Upload any audio file to your project's sound library (rain, crowd noise, restaurant ambience — whatever fits your story), then assign it to a range of segments with a visual timeline gutter. Background tracks loop automatically, fade in and out smoothly, and play behind the narration during chapter playback. When you export, background audio is baked into the final MP3 — no post-production needed.

Volume Normalization & Analysis

No more jarring volume jumps between chapters. A new Normalize volume option in the export dialog brings every chapter to a consistent −20 dB RMS with peak limiting — the same standard used by ACX. Before exporting, click Analyze to see each chapter's current volume level at a glance, color-coded to highlight inconsistencies.

March 14, 2026

Built-In Waveform Audio Editor

This is a big one. Every generated snippet now has an Edit generated sound button that opens a full waveform editor right inside the project — no external tools, no re-uploading, no context switching. Select a region on the waveform and delete unwanted artifacts, insert silence for pacing, or adjust gain to level out volume — all with instant visual feedback. Hit Save and your edited audio replaces the original in place, ready for export. The editor loads on demand so it never slows down your workflow until you need it. Your TTS output is now truly yours to shape, one waveform at a time.

March 12, 2026

Email Notifications & Password Reset

Audiobook Studio now sends email notifications to keep you in the loop. Get notified when your account is approved, paused, or reactivated — and admins receive an email whenever a new user registers. Forgot your password? Use the new Forgot password? link on the sign-in page to receive a secure reset link via email, complete with location and device details so you know the request is yours.

March 12, 2026

Analysis Modes: Character & Flow

You can now choose how your manuscript is analyzed when you upload it. Character Analysis uses AI to detect characters, dialogue, and narration — ideal for fiction with multiple speakers. Flow Analysis splits text by paragraph for single-narrator books or manual control — no AI or API key required. Pick a mode right after upload, or switch any time in project settings.

Better ElevenLabs Error Reporting

When your ElevenLabs API key is missing permissions (e.g. the “user_read” scope needed to display usage), the settings panel now shows a clear explanation instead of failing silently. Other API errors are surfaced with their full message so you can diagnose issues faster.

New Landing Page

Visitors now see a dedicated landing page that introduces Audiobook Studio — covering features, pricing transparency (BYOK — bring your own API keys, no hidden costs), and cross-device support. Sign in and docs links are always accessible from a sticky navigation bar.

March 10, 2026

Mobile-Friendly Interface

Audiobook Studio now works on phones and tablets. The navigation collapses into a hamburger menu, the voice/generate sidebar opens as a slide-over panel, and all editor controls, dialogs, and tables adapt to smaller screens.

March 9, 2026

DAISY Audiobook Export

Export your audiobook as a DAISY 2.02 Digital Talking Book — the standard format used by screen readers and accessible audiobook players. Once your chapters are exported, click DAISY in the Export dialog to package everything into a single downloadable ZIP with full chapter navigation.

March 8, 2026

Buy a Plan with Stripe

You can now upgrade any project to the paid plan directly from the app. Click Export → Buy a Plan and complete a secure one-time payment of $19.99 via Stripe. Your project is upgraded instantly once payment is confirmed — no coupon needed.

March 8, 2026

Smarter Character Detection

Character detection is now significantly more accurate. Indirect speech like "telling him she had big bones" is correctly identified as narration instead of dialogue. The system no longer invents characters that don't exist in your text, and chapter titles are no longer duplicated in the detected segments.

March 8, 2026

Sign in with Google

You can now sign in or register using your Google account — no password needed. Just click Continue with Google on the login or registration page. If you already have an account with the same email, it links automatically.

March 8, 2026

Multiple TTS Providers

You can now choose between ElevenLabs, OpenAI TTS, and Google Cloud TTS for voice generation. Set your preferred provider in Settings, and each new project will use it automatically. Switch providers anytime for future projects.

Word Document Import

Upload .docx files directly — no need to convert to Markdown first. Headings, bold, italic, and lists are all preserved. Chapter splitting works just like it does with Markdown and PDF files.

Join Segments

Merge adjacent segments into one with a single click. Useful when character detection splits dialogue that should stay together.

Right-to-Left Text Support

The editor now properly handles right-to-left text (Hebrew, Arabic, etc.) with correct alignment and direction throughout the interface.

TTS Provider Setup Guide

A new TTS Provider Setup documentation page walks you through creating and configuring API keys for each provider, step by step.

Other Improvements

• Smarter Google Gemini integration — content safety filters no longer block fiction with mature themes.
• Friendlier error messages when TTS provider API keys are misconfigured or missing permissions.
• Voice list now refreshes automatically when switching between projects that use different TTS providers.