-
Notifications
You must be signed in to change notification settings - Fork 57
Home
Welcome to the home of TTS-Story! This project is designed for creators, bibliophiles, and tech enthusiasts who want to bridge the gap between the written word and the spoken voice using local hardware.
Whether you're looking to turn a 500-page classic from Project Gutenberg into a narrated masterpiece or just want a local, private way to handle text-to-speech (TTS), you’re in the right place.
Most TTS tools are built for short snippets—a tweet here, a paragraph there. TTS-Story is built for the "long haul."
It is a web-based interface powered by a Python backend that runs entirely on your local machine. No subscription fees, no "character limits" from cloud providers, and no privacy concerns.
- Local Processing: Everything stays on your hardware.
- Massive Text Support: Designed specifically to handle entire books and long-form content.
- Multi-Speaker Orchestration: Assign different voices to different characters or stick to a single, consistent narrator.
- Advanced Extraction: Drop a raw text file in, and the tool helps you clean and process it for the best audio results.
- Model Variety: Access a range of state-of-the-art TTS models to find the perfect "voice" for your story.
We’ve made the setup process as "one-click" as possible for Windows users. Our installer handles the heavy lifting, including checking for Git and setting up the Python environment.
- Download the Installer: Get the install-update.bat file.
-
Run the File: Double-click
install-update.baton your Windows computer. -
The Script Will:
- Check for and install Git (if missing).
- Clone the repository.
- Run the setup and prepare the Python backend.
Creating your first audiobook is a straightforward process. (Video tutorials coming soon!)
| Step | Action | Description |
|---|---|---|
| 1 | Source | Grab a .txt file (e.g., from Project Gutenberg). |
| 2 | Import | Drop the file into the TTS-Story web interface. |
| 3 | Configure | Choose your model and narrator(s). |
| 4 | Process | Convert text blocks into audio segments. |
| 5 | Export | Combine segments into your final long-form audio file. |
Hardware Note: Because this runs locally, your conversion speed depends on your CPU/GPU. For massive novels, it's best to let it run in the background.
- Clean your text: Ensure your source text doesn't have "OCR artifacts" (like broken page numbers) before you start.
- Voice Testing: Use the "Preview" feature on a small paragraph before committing to a 10-hour render.
If you run into bugs or have feature requests, please check the Issues tab or stay tuned for our upcoming video walkthroughs!