Package Exports

This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (echogarden) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

Readme

Echogarden

Echogarden is an integrated speech system that provides a variety of synthesis, recognition, alignment, and other processing tools, designed to be directly accessible to end-users:

Easy to install and update
Runs on Windows (x64), macOS (x64, ARM64) and Linux (x64)
Written in TypeScript, for the Node.js runtime
Doesn't require Python, Docker, or similar system-level dependencies
Doesn't rely on any essential platform-specific binaries. Engines are either ported via WebAssembly, imported using the ONNX runtime, or written in pure JavaScript

Feature highlights

Fast, high-quality offline multilingual text-to-speech voices based on the VITS neural architecture
Accurate offline speech recognition using OpenAI Whisper models
Supports a large variety of offline and cloud engines, including services by Google, Microsoft, Amazon, Elevenlabs and others
Word-level timestamps for all synthesis and recognition outputs
Speech-to-transcript alignment using dynamic time warping (DTW), and dynamic time warping with recognition assist (DTW-RA) methods, including support for multi-pass (hierarchical) processing
Advanced subtitle generation, accounting for sentence and phrase boundaries
Can translate speech in any one of 98 languages, transcribe it directly to English, and produce near word-level synchronized subtitles for the translated transcript
Attempts to improve TTS pronunciation accuracy on some engines: adds text normalization (e.g. idiomatic date and currency pronunciation), heteronym disambiguation (based on a rule-based model) and user-customizable pronunciation lexicons
Internal package system that auto-downloads and installs voices, models and other resources, as needed
Other features include: language detection (for both audio and text), voice activity detection, and speech denoising

Installation

Ensure you have Node.js v16.0.0 or later installed.

then:

npm install echogarden -g

Additional required tools:

ffmpeg: used for codec conversions
sox: used for the CLI's audio playback and recording

Both tools are auto-downloaded as internal packages on Windows and Linux.

On macOS, they are not currently auto-downloaded, due to security issues with unsigned binaries. It is recommended to install them via a package manager like Homebrew (brew install ffmpeg sox) and ensure they are available on the system path.

Updating to latest version

npm update echogarden -g

Interfacing with the system

Currently, the software is operated mainly through a command-line interface, which enables powerful customization and is especially useful for long-running bulk operations.

Development of more graphical and interactive tooling is currently ongoing.

If you are a developer, you can also import the package as a module or interface with it via a WebSocket service.

Guides and resource pages

Credits

This project consolidates, and builds upon the effort of many different individuals and companies, as well as contributing a number of original works.

Designed and developed by Rotem Dan.

License

GNU General Public License v3

Licenses for components, models and other dependencies are detailed on this page.