Skip to main content
← Back to news

Narro reads web pages and Kindle books aloud with AI voices in the browser

On-device & edge
Source:Hacker News
Narro is a Chrome extension that reads web pages and Kindle books (online reader) aloud using synthetic voices generated locally, in the browser: Kokoro-82M, Supertonic 2 (English, Spanish, French, Portuguese, Korean), Piper and Kitten TTS Nano. In local mode no account and no server are needed; for cloud voices you insert your own API key. No spoken word leaves the machine.
Read original article

Related articles

Local voice: from Whisper to text-to-speech

How to build a fully local voice pipeline: transcription with Whisper, synthesis with Piper or Kokoro-82M, hardware requirements, and practical use cases.

Costs: local vs API, done with real numbers

How much does local really cost compared to a cloud API? Verified per-token prices, GPU amortization, electricity and the break-even point, calculated with real numbers.

MagpieTTS 357M: 12-language speech synthesis that runs on a laptop

NVIDIA's MagpieTTS Multilingual 357M: 12 languages, Italian included, in a 332 MB file that runs locally on a laptop without a GPU. Requirements, a three-command setup, and the honest limits.

Get the next local-AI briefing

Once a week, the top selection from iaLocale: articles, news and resources on local AI, and more.

After signing up you receive a confirmation email (double opt-in). Without confirmation we send nothing. No spam, we promise.

Related resources

Tools and resources from the iaLocale archive relevant to this content.

🎵

Kokoro-82M

Models

82-million-parameter speech synthesis model on a VITS architecture, Apache-2.0 for the weights, with voices in dozens of languages and surprisingly high quality for its size. Runs efficiently on CPU alone.

🗣️

Piper TTS

Inference

Sintesi vocale in locale a bassa latenza basata su ONNX: genera parlato naturale da testo in tempo quasi reale, anche su CPU. Multilingue (italiano incluso) e facile da integrare nei pipeline: download del modello, una riga di comando. MIT.

🔶

OpenAI API

Inference

Inference API for OpenAI's frontier models (GPT series). You pay per token: a fixed price per million input and output tokens, no GPUs to manage, with rate limits per account tier.

🟠

Anthropic Claude

Inference

Inference API for Anthropic's Claude models (Claude 1 since 2023). Like OpenAI, you pay per token, input and output, with request limits per plan: the frontier path with no servers of your own.

Browse all resources