Changelog
Follow up on the latest improvements andΒ updates.
RSS
new
improved
π Nepvox V2 Dashboard
We've been rebuilding the Nepvox dashboard from the ground up β faster, cleaner, and packed with AI tools to help you go from idea to finished audio in seconds.
π New
- All-new dashboard β a completely redesigned, modern dark-themed workspace with a reorganized Home page, quick-action shortcuts (AI Auto Generate, Text to Speech, Batch Convert, Voice Editor, Usage Analytics, Plans, Refer & Earn, and more), and a cleaner navigation sidebar.
- AI Auto Generate β describe what you want in a prompt and get a ready-to-narrate script and a matching voice suggestion automatically.
- "Write with AI" script generator β generate a script directly inside the editor for podcasts, ads, audiobooks, social clips, and more, in short/medium/long lengths.
- AI conversation generator β describe a topic and get a full multi-speaker dialogue script, with each speaker automatically assigned a distinct, language-matched voice.
- Batch Convert (multi-voice) β build a script out of multiple blocks, assign a different voice to each one, reorder them by drag-and-drop, and generate everything as a single combined audio file. Includes ready-made quick-start templates and sample script downloads for new users.
- Help Chat AI Assistant β an in-app AI chat that answers product questions without leaving the dashboard.
- Smarter waveform audio player β after generating speech, you now get a real animated waveform with live playback progress, click-to-seek, skip Β±10s, and a footer summary β replacing the old plain progress bar.
- Grammar check & translate β review AI-suggested grammar/spelling fixes inline, or translate your script into another language with one click, with automatic voice-language matching.
- Smart auto-naming β generations without a custom name now get a readable, content-based title instead of a generic "Voice - timestamp" label.
- Google One Tap sign-in for faster login/signup.
π§ Improved
- Text-to-Speech history β new table-based history view with duplicate, delete, remove-from-folder, and download actions.
- Folder suggestions β AI can now suggest (or create) the right folder for a script based on its content.
- Session & authentication flow hardening across sign-in and checkout.
You can now go beyond a single generation. The new Voice Editor lets you combine your generated voice clips into one polished, downloadable track β right inside NepVox.
What you can do
- Merge multiple voicesβ Combine several generated clips into one seamless voiceover without leaving NepVox.
- Edit on a timelineβ Drag to reorder clips, preview any segment, and adjust each clip's volume before exporting.
- Add background musicβ Browse a built-in library of royalty-free tracks by mood and genre, preview them, and blend them under your narration at your chosen volume.
- Render & downloadβ Export everything as one finished audio file, ready to use.
Getting there
- New sidebar shortcutβ Open the Voice Editor directly from the left navigation, no need to go through Speech History first.
- Project switcherβ Jump between projects right from inside the editor.
- "All Projects" viewβ Browse and edit every voice clip across your entire account in one place, not just one project at a time.
Polish & performance
- Refreshed designβ A new time ruler, cleaner voice/music tracks, a redesigned playhead, and a waveform that visually fills in as your audio plays.
- Drag-to-seek timelineβ Click or drag anywhere on the timeline or ruler to jump playback to that exact spot.
- Live volume controlβ Adjusting a clip's or background track's volume now applies instantly, even mid-playback.
- Faster background musicβ Tracks are cached after first use instead of being re-fetched every render, so adding music is noticeably quicker.
- Custom render playbackβ Your finished mix plays back in an on-brand player with instant Download and Speech History actions, instead of a plain browser audio widget.
- Tooltips throughoutβ Every icon-only button now shows a clear label on hover.
We refreshed NepVox with Microsoft Azureβs latest voice catalog
New in this update
*
89 new premium voices
added*
12 existing voices
updated with corrected Azure metadataNew voice families
*
Dragon HD Omni Latest
β expressive voices with unique character styles*
Dragon HD Latest
β high-definition neural voices across multiple languages*
Dragon HD Flash Latest
β faster Dragon HD variants*
MAI Voice 2
β next-generation multilingual AI voices (20+ languages)*
DragonHD Preview
β early-access preview voicesHighlights
*
English (US):
Ethan, Grant, Harper, Iris, Jasper, Olivia, Evelyn, Juno, Tessa*
English (India):
Diya, Neerja*
English (Australia):
Isla, Cyanspark, Siennatopaz*
Hindi:
Arjun, Dhruv, Kavya, Priya*
Chinese:
Bo, Lan, Mei, Wei, Ivoryserenade, Xiaoshuang, Lingqing*
Europe & Southeast Asia:
Expanded coverage across German, French, Spanish, Italian, Filipino, Indonesian, and Malay.Improvements
Updated metadata across 12 existing voices:
* Status corrections
* Gender metadata fixes
* Style list updates
β¨ All newly added voices are available across both Free and Paid plans β enjoy exploring the expanded voice library.
We've completely rebuilt the NepVox dashboard frontend using Vue 3 and Inertia.js, replacing the previous server-rendered Blade views.
What changed:
- Pages now load as a single-page app (SPA) β navigation is instant with no full page reloads
- All dashboard views (TTS Studio, Speech History, Voice Library, Projects, Profile, Subscriptions, Support) are now Vue components
- Sidebar state, accordion menus, and transitions are smoother
- Build output is leaner β assets are bundled with Vite
What stays the same:
- All existing features work exactly as before
- No changes to your data, voice generations, or account settings
This is a foundation change β it lets us ship new features faster going forward.