OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Audio & Voice AI

Echogarden

Echogarden is a TypeScript speech-processing toolset for Node.js, usable from a command-line interface or as an npm package. Its engines support text-to-speech, speech recognition, transcript alignment, speech translation, voice isolation and language detection, alongside denoising, voice activity detection and subtitle generation.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Echogarden — OpenViST project profile in Audio & Voice AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Echogarden when a workflow needs one or more documented speech-processing operations through a CLI or Node.js integration, and you can choose among its available engines.

Who it is for

  • People who need command-line speech-processing operations such as transcription, synthesis or voice isolation.
  • Node.js developers adding speech or audio-processing tasks to an application.

Documented uses

  • Transcribe audio into text.
  • Generate speech from text.
  • Align a transcript with spoken audio or translate speech.
  • Detect language, remove background noise or separate voice from music and ambience.
Before you choose

Requirements & limits

The documented setup uses npm and requires Node.js v18 or later; v22 or later is recommended. The project lists Windows, macOS and Linux support and states that it is open source under GPL v3.

  • Engine availability varies by task; review the engines list and options reference before designing a workflow.
  • The project offers both offline and online engines, so the chosen engine determines whether a task uses a cloud service.
  • The tool can download voices, models and other resources as needed.
  • The README describes word-level timestamps for recognition, synthesis, alignment and translation outputs.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Echogarden’s command-line tool

Set up the global CLI on a supported system.

Before you start

  • Node.js v18 or later; v22 or later is recommended.
  • Windows, macOS or Linux.

Steps

  1. Install Echogarden globally with the command below.

    Documented command
    npm install -g echogarden@latest

  2. For npm v12 or later, add --allow-scripts=onnxruntime-node,wtf_wikipedia if required by the installation notes.

Expected outcome

The Echogarden command-line utility is installed for speech-processing tasks.

Guide limitations

  • The installation notes say npm v12 or later may require allowing the listed post-install scripts; ONNX Runtime uses a post-install script to download binaries on some platforms.
Documentation 1 ↗
Source-based practical guide

Transcribe an audio file from the CLI

Run the documented speech-to-text command on an audio file.

Before you start

  • Echogarden installed as a CLI.
  • An audio file accessible to the command line.

Steps

  1. Run echogarden transcribe speech.mp3, replacing the example filename with the audio file to process.

  2. Consult the CLI guide and options reference for supported operations and configuration.

Expected outcome

The CLI performs the documented transcription operation on the specified audio file.

Guide limitations

  • The example does not specify an engine, output format or configuration; consult the CLI documentation and engine list for those details.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
echogarden-project/echogarden · Official homepage title · retained in its source language
How we review sourcesSuggest a correction