Skip to content

Latest commit

 

History

124 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Simpaudio logo — free offline text-to-speech voice studio for Windows

Simpaudio

The Private, Offline Voice Studio.
No Subscriptions. No Cloud. No Compromise.

⬇️ Download Free ⭐ Star Us

Simpaudio is a free, open-source, offline text-to-speech (TTS) voice studio for Windows. It turns text into natural, studio-quality speech in 8 languages with 40+ realistic voices — powered entirely by Piper TTS and Kokoro TTS running locally on your PC. No cloud, no accounts, no subscriptions: it is the private ElevenLabs alternative that keeps your audio on your machine.

Beyond plain text-to-speech, Simpaudio includes voice blending (create a unique voice by mixing two others), audiobook generation from PDF/EPUB/TXT files, Whisper speech-to-text, a visual SSML editor, and SRT subtitle export — all free forever under the MIT license.


📑 Table of Contents


🚀 Why Simpaudio Wins

💰 $0/month

Free Forever
No hidden tiers. No "free trial" trap.

🔒 100% Offline

Your Data, Your Control
Air-gapped voice synthesis.

🎤 40+ Voices

8 Languages
Realistic, natural-sounding synthesis.

🔬 Open Source

MIT Licensed
Audit, fork, and extend.


Powerful Features. Zero Friction.

🗣️ Professional Text-to-Speech

Convert text into studio-quality audio with 40+ realistic voices spanning 8 languages. Export as WAV, MP3, or SRT subtitles—perfect for YouTube, podcasts, and audiobooks.

🧬 Voice Blending DNA

Mix two voice models to create entirely unique personas. No two creators will have the same voice. It's your vocal fingerprint.

📚 Audiobook Studio

Import manuscripts (TXT, MD, EPUB, PDF) and auto-generate full audiobooks with chapter-specific voices and perfectly timed subtitles. One click. Done.

🎧 Whisper Transcription

Convert speech to text offline using OpenAI's Whisper engine. No APIs. No rate limits. No transcription bills.

🎨 Visual SSML Editor

Design complex speech patterns with a point-and-click SSML designer. Pauses, emphasis, pitch control—all without touching code.


📊 The Numbers Say It All

Cloud TTS Service          Simpaudio
─────────────────────      ─────────────────
💳 $22/month               ✅ Free Forever
☁️ Data in the cloud       ✅ 100% Offline
🔑 Account required        ✅ No login needed
⏱️ API rate limits         ✅ Unlimited synthesis
🚫 Voice cloning locked    ✅ Free voice blending
📶 Internet dependent      ✅ Works anywhere

🎯 Built for Creators

✍️ Writers & Authors

Turn chapters into audiobooks. Assign unique voices. Export with timing metadata. Your story, your voice.

🎬 Content Creators

YouTube voiceovers. TikTok audio. Podcast intros. Generate unlimited content voices without vendor lock-in.

💻 Developers

Python-based. Fully extensible. Self-host or integrate into your stack. MIT license means zero restrictions.

🏢 Enterprises

No per-seat licensing. No cloud bills. Deploy on-premise. Perfect for sensitive or compliance-critical audio.


🌍 The Open Source Difference

Simpaudio isn't just free—it's built on trust.

  • Transparent — Every line auditable. No hidden telemetry.
  • Future-Proof — You own the code. Your investment never expires.
  • Community-Driven — Contribute features. Report bugs. Shape the roadmap.
  • Commercially Viable — MIT license means you can use it in production without restrictions.

Backed by battle-tested open-source engines:

  • Piper — Fast, efficient TTS synthesis
  • Kokoro — State-of-the-art voice generation
  • Whisper — Industry-leading speech recognition

🚀 Getting Started in 60 Seconds

System Requirements

✅ Windows 10/11 (64-bit)
✅ 4 GB RAM (8 GB recommended)
✅ 2 GB free disk space
✅ Internet (first-time model download only)

Installation

Option 1: Installer (Recommended)

📥 Download simpaudio-installer.exe
🖱️ Run and follow the setup wizard
✅ Done. App is in your Start Menu.

Option 2: Portable (USB/Custom)

📦 Download simpaudio-portable.zip
📂 Unzip anywhere (USB, custom folder, etc.)
▶️ Run simpaudio.exe directly

Option 3: Developer Mode

git clone https://github.com/alimaandev/simpaudio.git
cd simpaudio
python -m venv venv
venv\Scripts\pip install -r requirements.txt
python app.py

First Run

Models download on-demand and cache locally. After first use, Simpaudio runs completely offline.

Model Size First Use
Piper Voices (all 40+) ~60 MB each When you select a voice
Kokoro Neural Engine ~340 MB When using high-quality mode
Whisper STT ~150 MB When transcribing audio

💡 Real-World Examples

📖 Audiobook Author

"I published 3 books last year. Simpaudio saved me $2,400 in narration costs and gave me complete creative control."

  • Import PDF manuscript
  • Assign different voices to characters
  • Export final audiobook with synchronized SRT subtitles
  • Result: Professional audiobook in hours, not weeks

🎬 YouTube Creator

"50 videos. Zero voiceover artist fees. Infinite voice variety."

  • Blend voices to create unique channel persona
  • Generate voiceovers while offline
  • Batch-process entire video scripts
  • Result: Consistent, professional audio at scale

🔐 Corporate Compliance

"We handle NDA-protected content. Cloud services weren't an option."

  • Runs on-premise or air-gapped machines
  • No data leaves your infrastructure
  • MIT licensed for commercial use
  • Result: Enterprise-grade privacy, startup-level pricing

🛠️ Made by Developers, For Developers

# Real example: synthesize speech with the built-in Piper engine
from engines import create_engine

tts = create_engine("Piper TTS")
tts.generate(
    text="Welcome to Simpaudio",
    voice="en_US-libritts-high",
    speed=1.0,
    pitch=1.0,
    output_path="audio.wav",
    status_callback=print,
)

Why developers love it:

  • 🐍 Native Python API
  • 📦 Self-contained dependencies
  • 🔧 Customizable synthesis pipeline
  • 📊 Batch processing support
  • 🚀 Runs on CPU (no GPU required)

🤝 Community & Support

Have ideas? Found a bug? We're all ears.


FAQ

Is Simpaudio really free?

Yes. Simpaudio is 100% free forever with no paid tiers, no trial periods, and no hidden limits. It is open source under the MIT license.

Does Simpaudio work offline?

Yes. After a one-time model download on first use, Simpaudio runs completely offline. All text-to-speech, voice blending and speech-to-text happen on your PC.

Is my audio or text uploaded anywhere?

No. Simpaudio has no cloud component. Your text, your voice models and your generated audio never leave your computer. This is the key difference from cloud TTS services like ElevenLabs.

Can I use Simpaudio commercially?

Yes. The MIT license allows personal, commercial and enterprise use, including in products you sell — you only need to keep the copyright notice.

What is voice blending?

Voice blending mixes two voice models (for example af_heart,af_bella) into one unique synthetic voice. It is built in and free, unlike cloud services that charge extra for custom voices.

Which languages are supported?

Simpaudio supports 8 languages: English, Spanish, French, Hindi, Italian, Japanese, Portuguese and Mandarin Chinese, across 40+ Piper voices plus the Kokoro neural voices.

What can I export?

You can export audio as WAV or MP3, and subtitles as SRT with real word timestamps — ideal for YouTube captions, podcasts and audiobooks.

How much disk space do I need?

About 2 GB free is recommended. Models download on demand and are cached locally; Piper voices are roughly 60 MB each.

Does Simpaudio work on Mac or Linux?

Currently Simpaudio targets Windows 10/11 (64-bit). The underlying engines are cross-platform, so a Linux/macOS port is a welcome contribution.

How do I report a bug or suggest a feature?

Use the bug report form or the feature request form. Include your version and Windows version to help us fix it faster.


📜 License & Legal

MIT License — Use freely in personal, commercial, or enterprise projects.

Your voice. Your data. Your rules. No compromises, no asterisks.


✨ Simpaudio
Professional voice synthesis that lives on your PC, not in someone else's cloud.
Free. Open. Powerful.

GitHub Stars MIT License Python 3.10+ Windows

If Simpaudio saved you time or money, consider leaving a ⭐ — it's the fuel that keeps us building.


Project docs: Changelog · Contributing · Code of Conduct · Security · License

About

Simpaudio — free offline text-to-speech (TTS) voice studio for Windows. 40+ realistic voices in 8 languages via Piper & Kokoro TTS. Voice blending, audiobook generation, Whisper speech-to-text, SRT subtitle export & visual SSML editor. The private ElevenLabs alternative — no cloud, no accounts, MIT licensed.

Topics

Resources

Code of conduct

Contributing

Security policy

Stars

4 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages