Echogarden
Echogarden is an easy-to-use speech toolset that includes a variety of speech processing tools.
- Easy to install, run, and update
- Written in TypeScript, for the Node.js runtime
- Can be used either as a command-line utility, or imported as a standard
npm package
- Runs on Windows (x64, ARM64), macOS (x64, ARM64) and Linux (x64, ARM64)
- Doesn't require Python, Docker, or other system-level dependencies
- Doesn't rely on essential platform-specific binaries. Engines are either written in pure TypeScript, ported via WebAssembly, or imported using the ONNX runtime
- Fully open-source (GPL v3)
Features
- Text-to-speech using high-quality Kokoro and VITS offline models for many languages and dialects, and 16 other offline and online engines, including cloud services by Google, Microsoft, Amazon, OpenAI and ElevenLabs
- Speech-to-text using a custom TypeScript/ONNX port of the OpenAI Whisper speech recognition architecture, whisper.cpp, and several other engines, including cloud services by Google, Microsoft, Amazon and OpenAI
- Speech-to-transcript alignment using several variants of dynamic time warping (DTW, DTW-RA), including support for multi-pass (hierarchical) processing, or via guided decoding using Whisper recognition models. Supports 100+ languages
- Speech-to-text translation, translates speech in any of the 98 languages supported by Whisper, to English, with near word-level timing for the translated transcript
- Speech-to-translated-transcript alignment synchronizes spoken audio in one language, to a provided English-translated transcript, using the Whisper engine
- Speech-to-transcript-and-translation alignment synchronizes spoken audio in one language, to a translation in a variety of other languages, given both a transcript and its translation
- Text-to-text translation, translates text between various languages. Supports cloud-based Google Translate engine
- Language detection identifies the language of a given audio or text. Includes Whisper or Silero engines for spoken audio, and TinyLD or FastText for text
- Voice activity detection attempts to identify segments of audio where voice is active or inactive. Includes WebRTC VAD, Silero VAD, RNNoise-based VAD and a built-in Adaptive Gate algorithm
- Speech denoising attenuates background noise from spoken audio. Includes the RNNoise and NSNet2 engines
- Source separation isolates voice from any music or background ambience. Includes the MDX-NET deep learning architecture
- Word-level timestamps for all recognition, synthesis, alignment and translation outputs
- Advanced subtitle generation, accounting for sentence and phrase boundaries
- For the Kokoro, VITS and eSpeak-NG synthesis engines, includes enhancements to improve TTS pronunciation accuracy: adds text normalization (e.g. idiomatic date and currency pronunciation), English heteronym disambiguation (based on a simple rule-based model), various pronunciation corrections, and accepts user-provided pronunciation lexicons
- Internal package system that auto-downloads and installs voices, models and other resources, as needed
Installation
Ensure you have Node.js v18 or later installed (v22 or later is recommended).
then:
npm install -g echogarden@latest
Update
Simple, but may not always update to the very latest major version:
npm update -g echogarden
You can also use npm-check-updates to check for a newer version:
npm install -g npm-check-updates
ncu -g echogarden
Then, if an updated version is available, use the command line ncu provides to make the update.
Using the command-line interface
A small sample of command lines:
echogarden speak "Hello World!"
echogarden speak-file story.txt --engine=kokoro
echogarden transcribe speech.mp3
echogarden translate-speech speech.webm subtitles.srt
echogarden align speech.opus transcript.txt
echogarden isolate speech.wav
See the command-line interface guide for more details on the operations supported, and the configuration options reference for a comprehensive list of all options supported.
Using the Node.js API
If you are a developer, you can also directly import the package as a dependency in your code. The API operations and options closely mirror the CLI.
Documentation and guides
Credits
This project consolidates, and builds upon the effort of many different individuals and companies, as well as contributing a number of original works.
Developed by Rotem Dan (IPA: /ˈʁɒːtem ˈdän/).
License
GNU General Public License v3
Licenses for components, models and other dependencies are detailed on this page.