PitchHut logo
Kokoro TTS Add-on
Local Neural Text-to-Speech for Firefox/Chrome—fast and private.
Pitch

Kokoro TTS Add-on is a extension that enables users to convert text into natural-sounding speech without an internet connection. With a lightweight local server and privacy-respecting features, it delivers fast performance on various systems, making it suitable for users with low-end CPUs.

Description

Kokoro TTS Add-on is an innovative browser extension designed for Firefox that enables the conversion of selected or pasted text into natural-sounding speech, all while maintaining user privacy and operating offline. By utilizing a lightweight Flask server paired with the Kokoro model, this tool processes text-to-speech tasks seamlessly on local machines, ensuring that sensitive data remains secure without the need for internet connectivity.

Key Features

  • Neural Text-to-Speech: Enjoy high-quality speech synthesis with multiple voice options.
  • Privacy-Focused: Operates entirely offline, eliminating the risk associated with cloud-based services.
  • Lightweight: Features a compact model size of just 82M parameters, which is efficient even on low-end CPUs.
  • Cross-Platform Support: Compatible with Linux, macOS, and Windows systems, making it accessible to a wide audience.

System Requirements

The add-on functions effectively without the need for a high-performance GPU, although performance is significantly enhanced when one is available. It requires Python 3.8 or higher installed on the system along with pip for managing dependencies.

Testing the Add-on

After installation, users can verify the functionality by visiting http://localhost:8000/health where a simple "healthy" JSON response verifies that the server is operational. The intuitive interface allows users to paste text, select a voice, and generate speech effortlessly.

Visual Previews

The extension offers various user-friendly features, including a popup UI for text selection, playback notifications during speech generation, and a settings panel for configuration options. Users can also browse through the available voice models, which support multiple accents, including:

  • American English
  • British English
  • Spanish
  • French
  • Italian
  • Brazilian Portuguese
  • Hindi
  • Japanese
  • Mandarin Chinese

Video Overview

For a deeper insight into Kokoro TTS Add-on and its performance capabilities, view the comparison video showcasing offline generation versus online counterparts here.

Kokoro TTS Add-on provides a robust solution for those seeking an offline, privacy-respecting text-to-speech experience in their browser.

0 comments

No comments yet.

Sign in to be the first to comment.