Narro

Narro is a Chrome extension that reads web pages aloud using cloud or in-browser AI voices with sentence highlighting.

Narro is a Chrome extension that reads web pages aloud and highlights each sentence as it is spoken. Users can choose cloud voices from OpenAI, ElevenLabs, Google Gemini, and OpenRouter, or run local models in the browser such as Kokoro-82M, Supertonic 2, Piper, and Kitten TTS Nano. It also supports system voices and local OpenAI-compatible servers. The extension includes a floating player, playback speed controls, and a point-and-select feature to start reading anywhere. Additionally, Narro supports Kindle Cloud Reader by performing on-device OCR and automatically turning pages. The source code is released under the MIT License.

Narro at a glance

Best for: Software engineer, Student
Runs on: Chrome extension
Pricing: Free
Released: October 2026
Category: AI audio tool
Website: github.com/swrdfish/narro

Key features

Sentence highlighting with automatic page scrolling
Playback speed control from 0.5x to 3x with pitch preserved
Point and select to start reading from any sentence
Kindle Cloud Reader support with on-device OCR
Cloud voice integration with OpenAI, ElevenLabs, and Google Gemini
Local in-browser AI voices using Kokoro, Supertonic, Piper, and Kitten TTS
Background audio playback via offscreen document

Use it for

Reading web articles aloud hands-free
Listening to Kindle Cloud Reader books with automatic page turns
Listening to text offline using local browser models
Following along with synchronized sentence highlighting

Alternatives to Narro

NaturalReader — It offers content-aware AI voices in over 90 languages with cross-device compatibility.
Auricle — Runs entirely in the browser via Rust and WebAssembly with low latency and high accuracy.
Superwhisper — Transcribes speech offline and online with custom AI modes and templates.
Book2Speech — It converts DRM-free books into audiobooks with hundreds of natural AI voices and read-along highlighting.
browser-whisper — Transcribes audio and video locally with zero servers involved.
kokoro-onnx — Runs local TTS inference with efficient ONNX runtime performance.
sherpa-onnx — Runs complex audio AI tasks offline on local devices and embedded hardware.
Kokoro-FastAPI — Generate hours of high quality speech with an OpenAI-compatible endpoint.
Vosk — It enables offline, low-latency speech recognition on small devices.
CueLight demo — Runs entirely in the browser with no audio leaving the device.
OpenLess — Keeps data local and allows the use of your own preferred ASR and LLM providers.
Speakrail — Runs fully local on a single RTX 4090 with low latency and real-time interruption handling.

All Narro alternatives