Now Live on Google Play · V2.6 
 ___      ___  ________     ___    ___ ________  ___  ___  _______   ________  ________  ________     
|\  \    /  /||\   __  \   |\  \  /  /|\   ____\|\  \|\  \|\  ___ \ |\   __  \|\   __  \|\   __  \    
\ \  \  /  / /\ \  \|\  \  \ \  \/  / | \  \___|\ \  \\\  \ \   __/|\ \  \|\  \ \  \|\  \ \  \|\  \   
 \ \  \/  / /  \ \  \\\  \  \ \    / / \ \_____  \ \   __  \ \  \_|/_\ \   _  _\ \   ____\ \   __  \  
  \ \    / /    \ \  \\\  \  /     \/   \|____|\  \ \  \ \  \ \  \_|\ \ \  \\  \\ \  \___|\ \  \ \  \ 
   \ \__/ /      \ \_______\/  /\   \     ____\_\  \ \__\ \__\ \_______\ \__\\ _\\ \__\    \ \__\ \__\
    \|__|/        \|_______/__/ /\ __\   |\_________\|__|\|__|\|_______|\|__|\|__|\|__|     \|__|\|__|
                           |__|/ \|__|   \|_________|

Offline Neural TTS · Android · No Cloud · No Limits

↓ Get it on Google Play ★ GitHub GPL v3.0 Android 11+ ARM64

VoxSherpa TTS runs studio-quality neural text-to-speech entirely on your Android device.

Powered by Sherpa-ONNX — supports Kokoro-82M, Piper, and VITS engines.
Hindi, English, Japanese, Chinese and 50+ languages — zero internet required after model download.

SCROLL
01 // SCREENSHOTS

See it in action

Generate
Generate
Models
Models
Library
Library
Settings
Settings
02 // WHY VOXSHERPA

ElevenLabs quality.
No internet required. No subscription.

Others
Cloud · Sends your text to servers · Charges per character
VoxSherpa
On-device · All processing happens on your device — no cloud required · use offline models
🔒
Offline & Private
All inference on your device. No internet after model download. No account, no telemetry, no data collection. Ever.
🌐
50+ Languages
Hindi, English, British, Japanese, Chinese, French, Spanish and more. Serious Hindi support — offline, no compromise.
📄
Document to Audio
PDF to Audio and TXT to Audio built-in. Listen to any document hands-free. No cloud processing involved.
🔔
System-Wide TTS
V2.6
Set VoxSherpa as your Android TTS engine. Use it in Chrome, WhatsApp, any app — with pitch and speed controls.
🎵
Media Notification
V2.6
Full MediaStyle playback controls from the notification shade and lock screen. Pause, resume, seek — without opening the app.
🎧
Pro Audio Controls
Real-time waveform visualization, interactive seeking, chunk-based playback, adjustable speed & pitch. Export as WAV.
📦
Flexible Model Import
Download models inside the app or import your own .onnx files from local storage. Multiple models installed simultaneously.
📚
Speech Library
Every generation saved locally. Favorites, timestamps, voice attribution per recording. Regenerate on voice change.
⚙️
Emotion Tags
Smart Punctuation for natural pauses. Express mood inline: [whisper] [angry] [happy]. 100+ Kokoro voices.
03 // ENGINES

Two engines.
One app.

⭐ Studio Quality

Kokoro-82M

82 million parameter neural model. Same architecture powering top commercial TTS services — running fully offline on your phone.

Rivals ElevenLabs quality
100+ speaker voices
Best for audiobooks & voiceovers
82M params · FP32 · Sherpa-ONNX
⚡ Fast

Piper / VITS

Lightweight and fast. Generates natural speech in seconds on any Android device — perfect for daily use.

Fast on budget hardware
Natural, clear output
Best for quick synthesis
Low memory footprint
04 // LANGUAGES

Speak every language
offline.

🇮🇳 Hindi 🇺🇸 English 🇬🇧 British English 🇯🇵 Japanese 🇨🇳 Chinese 🇫🇷 French 🇪🇸 Spanish 🇩🇪 German 🇵🇹 Portuguese 🇮🇹 Italian 🇰🇷 Korean 🇷🇺 Russian 🇵🇱 Polish + 37 more
05 // TECH STACK

What's inside the build?

tech-stack.json
[$] cat tech-stack.json
 
{
  "language" → "Java"
  "platform" → "Android 11+ · ARM64"
  "built_with" → "Sketchware Pro"
  "inference" → "Sherpa-ONNX · ONNX Runtime"
  "tts_engines" → ["Kokoro-82M", "Piper", "VITS"]
  "audio_api" → "Android AudioTrack (PCM)"
  "distribution" → "Google Play Store"
  "version" → "2.6 · Media Notification"
  "license" → "GNU GPL v3.0"
}
 
[$]
06 // PERFORMANCE

Honest numbers.
Real hardware.

Device Tier Kokoro-82M Piper / VITS
● Flagship (SD 8 Gen 3) ~20–40 sec / min audio ~5 sec / min audio
● Mid-range (8-core) ~60–90 sec / min audio ~10 sec / min audio
● Budget (6-core) ~2–3 min / min audio ~20 sec / min audio

Kokoro prioritizes quality over speed by design — the same 82M parameter architecture that powers premium commercial TTS, running entirely on a mobile CPU. Chunk-based playback means audio starts playing before full generation completes.

Ready to go fully offline?

Free to install. No account. No subscription.
Your voice stays on your device — always.

▶ Download on Google Play
Android 11+ · ARM64 · ~500 MB storage recommended for models
07 // CONTRIBUTE

Open Source —
contributions welcome

1. Fork the repo
2. git checkout -b feature/YourFeature
3. git commit -m "Add YourFeature"
4. git push origin feature/YourFeature
5. Open a Pull Request

Found a bug? → Open an Issue

08 // LICENSE

GNU GPL v3.0

VoxSherpa TTS — Copyright (C) 2025 CodeBySonu95

This program is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.

This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.

See the full LICENSE file for details.