Releases: CodeBySonu95/VoxSherpa-TTS
Release list
VoxSherpa TTS — v4.0 (Multi speaker)
🎙️ VoxSherpa TTS — v4.0 · Dialogue Engine Update
APK attached below. For the latest version, Google Play is always recommended — Play Store updates arrive before GitHub releases.
Version Code: 22
Version Name: 4.0
⚠️ Version codes 13–21 have been skipped due to internal technical restructuring. No functionality was lost.
📲 Download
Note: The APK attached to this release may not be the latest version. Play Store always has the most recent update.
ℹ️ The Play Store version is slightly more advanced but includes ads. For more details, check the documentation.
What's New in v4.0
- 🗣️ Multi-speaker dialogue synthesis with Piper
- 🏷️ New
[speaker]tag system - 🎭 Voice style & tone controls
- ⏱️ Adjustable sentence gap / silence timing
- 🐛 Piper crash fix, better MMS support & stability improvements
🗣️ Multi-Speaker Dialogue Support
Piper now supports multiple speakers within a single script, enabling natural back-and-forth dialogue synthesis in one pass.
🏷️ New [speaker] Tag System
A dedicated tag system lets you assign lines to different speakers directly in your script, making dialogue-based TTS generation simple and structured.
[speaker1] Hello, how are you?
[speaker2] I'm good, thanks! How about you?
🛠️ Fixes & Improvements
- Piper Crash Fix — Resolved a crash issue affecting Piper synthesis
- Better MMS Model Support — Improved compatibility and stability with MMS models
- General Bug Fixes — Various minor fixes for improved stability
Requirements
- Android 11 (API 30) or higher
- ARM64 device
- ~500 MB free storage recommended (for models)
Feedback
Found a bug or have a suggestion? Open an Issue on GitHub.
VoxSherpa TTS V3.0 (MMS Models)
v3.0: The Massive Multilingual Update (1138+ MMS Models)
🌟 What's New
This is a major milestone release that massively expands language accessibility, enabling users worldwide to utilize text-to-speech capabilities in their native languages and regional dialects.
🚀 Key Features & Improvements
- 1300+ MMS Models Integrated: Added full support for Massively Multilingual Speech (MMS) models, bringing thousands of new languages and localized dialects to the application.
- Enhanced Global Coverage: Significantly expanded language resources to ensure better accessibility for underrepresented languages globally.
- Performance Optimization: Optimized the UI and underlying architecture to efficiently handle, filter, and load the massive list of models smoothly.
🤝 Credits & Acknowledgments
A huge thank you to @willwade for contributing and integrating these 1138+ MMS models into the project.
🛠️ Installation & Upgrade Guide
- Download the latest APK from the Assets section below.
- If you encounter any delay during the initial loading of the model list, please restart the application once to refresh the setup.
VoxSherpa TTS v2.9.1
• Fixed Kokoro crash on Chinese text input
• Added additional language support files for improved character handling
• Improved multilingual text processing stability
• Minor internal fixes and optimizations
VoxSherpa TTS v2.9 · System TTS & Bug Fixes
🎙️ VoxSherpa TTS — v2.9 · Bug Fixes
APK attached below. For the latest version, Google Play is always recommended — Play Store updates arrive before GitHub releases.
📲 Download
[
](https://play.google.com/store/apps/details?id=com.CodeBySonu.VoxSherpa)
Note: The APK attached to this release may not be the latest version. Play Store always has the most recent update.
What's New in v2.9
- 🔊 All downloaded models now visible to System TTS
- 🐛 Bug fixes and stability improvements
Changelog since v2.6
V2.7 — Filter & Share
- Filter voice models by language/type
- Share any text directly to VoxSherpa TTS
V2.8 — Sample Voice
- System TTS upgrade
- Sample voice preview for all models
V2.9 — Bug Fixes (This release)
- All downloaded models now revealed to System TTS
- Bug fixes and stability improvements
Requirements
- Android 11 (API 30) or higher
- ARM64 device
- ~500 MB free storage recommended (for models)
Feedback
Found a bug or have a suggestion? Open an Issue on GitHub.
VoxSherpa TTS v2.6 — Media Notification
🎙️ VoxSherpa TTS — v2.6 · Media Notification
APK attached below. For the latest version, Google Play is always recommended — Play Store updates arrive before GitHub releases.
📲 Download
[
](https://play.google.com/store/apps/details?id=com.CodeBySonu.VoxSherpa)
Note: The APK attached to this release may not be the latest version. Play Store always has the most recent update.
What's New in v2.6
- 🔔 MediaStyle Notification — playback controls directly from the notification shade
- 🎚️ Pitch control in System TTS
- ⚡ Speed control in System TTS
- Performance improvements and stability fixes
- Bug fixes and minor UI improvements
Full Changelog
Due to some issues, previous releases weren't published on GitHub — but here's everything added since the beginning:
V1.0 — Foundation
- Text to Audio · Save audio (.wav) · Favorites · Speed control
- Kokoro (high-quality) + Piper (fast) dual engine
- Chunk-based playback · Smart punctuation pauses
- Models download · Import Custom Model
- System TTS integration · PDF to Audio · TXT to Audio
V2.2 — Core Improvements
- Pitch control · Improved emotion tags & smart punctuation
- Regenerate audio on voice change · Send feedback · UI improvements
V2.3 — Playback Upgrade
- Interactive audio seeking · New mini player
- Smoother UI · Fixed cancel generation delay
V2.4 — Bug Fixes
- Better System TTS language detection
- Large screen compatibility · UI enhancements
V2.5 — Stability
- Bug fixes and performance improvements
V2.6 — Media Notification (This release)
- MediaStyle notification with playback controls
- Pitch & speed control in System TTS
- Performance improvements · Bug fixes · Minor UI tweaks
Requirements
- Android 11 (API 30) or higher
- ARM64 device
- ~500 MB free storage recommended (for models)
Feedback
Found a bug or have a suggestion? Open an Issue on GitHub.
VoxSherpa TTS v1.0-beta
🎙️ VoxSherpa TTS — v1.0-beta
First public pre-release. Core features are stable and ready for testing.
What's New
This is the first public release of VoxSherpa TTS — a fully offline neural text-to-speech app for Android.
Engines
- Kokoro-82M — studio-quality multilingual TTS (Hindi, English, 50+ languages)
- Piper / VITS — fast, lightweight neural TTS for everyday use
Features
- Download and manage voice models directly from the app
- Import local
.onnxmodels from device storage - Real-time waveform visualization
- Save generated audio as WAV files
- Speech history library with favorites
- Adjustable speed and pitch
- Smart Punctuation & Emotion Tags support
- 100% offline — no internet required after model download
Known Limitations
- Kokoro generation is slow on budget/mid-range devices (2–3 min per minute of audio) — this is a hardware limitation, not a bug
- Firebase-based online model list requires internet for first-time model discovery (local import works fully offline)
Requirements
- Android 11 (API 30) or higher
- ~500 MB free storage recommended (for models)
Installation
- Download
VoxSherpa-TTS-v1.0-beta.apkbelow - Enable Install from unknown sources in Android settings
- Install and open the app
- Go to Models tab → Download a voice model → Start generating
Feedback
Found a bug or have a suggestion? Open an Issue on GitHub.
⚠️ This is a pre-release. Expect rough edges. Production release coming soon on Play Store