


Overview
Narro reads any webpage aloud using AI voices.
Narro reads the web page you're on aloud in a natural voice and highlights each sentence as it's spoken, so you can listen, follow along, or look away and keep going. Use a voice that runs entirely in your browser, with no account and nothing sent anywhere, or a cloud voice with your own API key. LISTEN TO ANY PAGE • Click the Narro icon and press Read this page. Narro finds the article and skips menus, sidebars and footers. • Each sentence is highlighted as it's read, and the page scrolls to keep it in view. • Sentences are voiced together, with short pauses between headings and paragraphs, so it sounds like someone reading rather than a list of sentences. • Pick where to start: click Start from… and choose a sentence, select text and right-click Read aloud from here, or Alt-click (Option-click on a Mac) any sentence while reading. • Narro remembers your place on each page and picks up where you left off. EASY TO CONTROL • A small player on the page: play/pause, previous and next sentence, and speed from 0.5× to 3× without changing the voice's pitch. Drag it anywhere; it remembers where you put it. • Keyboard shortcuts are available while the player is showing. • Control reading from any tab with the toolbar popup. A red ▶︎ on the icon shows which tab is reading, and it keeps reading when that tab is in the background. • If a voice service fails, the player says what went wrong, with a Retry button. VOICES THAT RUN IN YOUR BROWSER No account, no API key, and the text never leaves your computer. Each model downloads once and then works offline. • Kokoro: natural English voices, the default • Supertonic 2: 10 voices in English, Spanish, French, Portuguese and Korean. • Piper: voices in many languages, including German, French, Spanish, Italian, Portuguese and Hindi. • Kitten TTS Nano: 8 English voices They use about 700 MB to 1 GB of memory while reading. Kokoro and Supertonic use your graphics card through WebGPU when it's available. The settings show the exact download and memory for your choice. CLOUD VOICES, WITH YOUR OWN KEY • OpenAI, including gpt-4o-mini-tts with style instructions such as "calm audiobook narration". • ElevenLabs, with the voices in your own library. • Google Gemini text-to-speech voices. • OpenRouter: one key for speech models from many providers. • Or any OpenAI-compatible speech server on your own computer, such as Kokoro-FastAPI. • Your computer's built-in system voices work too. LISTEN TO KINDLE BOOKS Kindle Cloud Reader shows pages as images, so most read-aloud tools can't read them. Narro recognises the text on the page you have open, on your computer, then reads it with your chosen voice and turns the page for you. A sentence split across two pages is read once, in full. English only for now. Narro is not affiliated with or endorsed by Amazon; check that your use complies with Amazon's terms. PRIVATE BY DEFAULT • With an in-browser voice, nothing you read leaves your computer. • With a cloud voice, only the text you ask Narro to read is sent, and only to the provider you chose, using your own key. • API keys stay in your browser and are never synced. • No accounts, no analytics, no servers of our own. Privacy policy: https://swrdfish.github.io/Narro/privacy.html FREE AND OPEN SOURCE Narro is free and MIT-licensed. Source code, issues and ideas: https://github.com/swrdfish/Narro
5 out of 51 rating
Details
- Version1.3.1
- UpdatedOctober 28, 2026
- Size15.92MiB
- LanguagesEnglish
- DeveloperWebsite
Email
ghoshbinayak@gmail.com - Non-traderThis developer has not identified itself as a trader. For consumers in the European Union, please note that consumer rights do not apply to contracts between you and this developer.
Privacy
This developer declares that your data is
- Not being sold to third parties, outside of the approved use cases
- Not being used or transferred for purposes that are unrelated to the item's core functionality
- Not being used or transferred to determine creditworthiness or for lending purposes
Support
For help with questions, suggestions, or problems, visit the developer's support site