Sawt

صوت (sawt): Arabic for "voice" or "sound".

Listen to any web page, or turn a whole book into an audiobook, with a natural voice that runs on your own computer.

Free, private, offline. No account, no subscription, no usage limits, and nothing you read is ever sent to a server: the voice model (Kokoro, 82M parameters) runs locally on your CPU.

• Read any article aloud from the browser: one click or Alt+R. Menus, ads and sidebars are skipped, the sentence being spoken is highlighted, and every page resumes where you left off.
• Convert books (EPUB, PDF, TXT) into .m4b audiobooks with chapter markers, mastered to audiobook loudness standards.
• 28 English voices, American and British, with adjustable speed.

Status: v0.1, early. It works well for the author daily; expect rough edges. Bug reports and contributions are very welcome. See CONTRIBUTING.md.

How it works

 Browser extension                        Your computer
┌───────────────────────┐   article text   ┌──────────────────────────────┐
│ finds the article     │ ───────────────▶ │ sawt serve              │
│ plays + highlights    │ ◀─────────────── │ Kokoro voice model (CPU)     │
└───────────────────────┘   sentence audio  └──────────────────────────────┘
                     only over 127.0.0.1 - never the internet

The extension can't run a voice model by itself, so it talks to a small engine you run locally. The engine keeps the model loaded, synthesizes a few sentences ahead of playback, and caches the audio, so re-opening an article plays instantly.

Install

1. Install the engine. You need uv, the Python installer (skip this if uv --version already works):

# macOS / Linux
curl -LsSf https://astral.sh/uv/install.sh | sh
# Windows (PowerShell)
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Then:

uv tool install sawt
sawt agent install   # downloads the voice model once (~350MB), then runs in the background

From then on the engine starts by itself when you log in and restarts if it stops, so there is no window to keep open. sawt agent status checks on it and sawt agent uninstall removes it. To run it only when you want, use sawt serve and keep that terminal open instead.

After uv tool upgrade sawt, run sawt agent install again to restart on the new version.

2. Add the browser extension from the Chrome Web Store. Its setup page checks that the engine is running.

3. Open any article and press Alt+R.

Usage

Reading web pages

Do this	To
Toolbar icon → Read this page, or Alt+R	Read the article
Alt+R again	Pause / resume
Right-click selected text → Read selection aloud	Hear just that, when the page's article detection picks the wrong block
Popup → voice / speed	Change it mid-article; reading continues from the current sentence

More: docs/extension.md (highlighting, resume, limits).

Converting books

Needs FFmpeg on your PATH.

sawt extract ~/Downloads/mybook.epub     # -> chapters
sawt inspect                             # check what extraction produced
sawt synth                               # synthesize (hours for a novel; resumable)
sawt build                               # -> ~/Sawt/out/<book>.m4b

Or several at once, unattended: sawt batch books/*.epub --voice af_bella --speed 0.85. The full guide (voices, pronunciation fixes, trimming front matter, quality checks): docs/books.md.

Run sawt with no arguments for every command.

Configuration

Setting	Default	What it does
SAWT_HOME	~/Sawt	Where books, output, the audio cache and pronounce.json live
SAWT_MODELS	~/.cache/sawt/models	Where the voice model is stored
SAWT_EXTENSION_IDS	the published extension	Extra extension IDs the engine accepts (comma-separated), e.g. a fork with its own ID
sawt serve --port	7865	Port the engine listens on (the extension expects 7865)
pronounce.json	—	Whole-word pronunciation fixes, e.g. {"Gregor": "Gregg or"}

Platform support

	Engine	Start at login	Extension
macOS	✅	✅ sawt agent install (launchd)	✅ Chrome; other Chromium browsers should work
Linux	✅	⚠️ sawt agent install (systemd user service), new and lightly tested	✅ Chrome / Chromium
Windows	⚠️ expected to work, untested	⚠️ sawt agent install (Task Scheduler), new and untested	✅ Chrome

English only for now. Firefox and Safari are not supported yet.

Privacy and security

• The extension reads a page only when you ask, and sends its text only to 127.0.0.1.
• The engine makes one network request ever: the first-run model download, verified against pinned SHA-256 hashes.
• The engine refuses requests from web pages and from other extensions. Details in SECURITY.md; the full policy is in PRIVACY.md.

Troubleshooting

Problem	Fix
Popup says the engine isn't running	sawt agent status, then sawt agent install to (re)start it. The log is ~/Sawt/work/serve.log. Check it answers: curl -H "X-Sawt: 1" http://127.0.0.1:7865/health
sawt: command not found after install	Open a new terminal, or run uv tool update-shell
Nothing is read on a page	Scroll first if the page loads text lazily, or select the text and right-click → Read selection aloud
A name is mispronounced	Add it to pronounce.json in SAWT_HOME with a phonetic spelling
build fails	Install FFmpeg (brew install ffmpeg, apt install ffmpeg, or winget install ffmpeg)

Roadmap

• A desktop app that bundles the engine, so no terminal is needed
• Firefox support
• More languages (Kokoro has voices for Spanish, French, Hindi, Italian, Japanese, Portuguese and Chinese)

Ideas and votes welcome in issues.

Contributing

Pull requests are welcome, from typo fixes to new features. Start with CONTRIBUTING.md (setup takes a couple of minutes) and docs/architecture.md for a map of the code. Issues marked good first issue are a gentle way in.

Credits

• Kokoro by hexgrad, the voice model (Apache-2.0)
• kokoro-onnx, which runs it on the CPU (MIT)
• Readability by Mozilla, which finds the article on a page (Apache-2.0)
• Pronunciation falls back to espeak-ng (GPL-3.0), installed as a dependency of kokoro-onnx

Convert books you own, public-domain texts and your own writing. Distributing a synthesized copy of an in-copyright book is not allowed.

Licence

MIT