FREEDOM251

Freedom251 › Text-to-Speech Software

MaryTTS

by MaryTTS

Free plan APILinuxMacSelf-hostedWebWindows

Visit MaryTTS Alternatives Pricing

MaryTTS's own site

What MaryTTS is

MaryTTS is a Java platform for turning text into synthesized speech across multiple languages. Version 5.2 supports German, British and American English, French, Italian, Luxembourgish, Russian, Swedish, Telugu, and Turkish. Its toolkits let developers add language support and build unit-selection or HMM-based voices. The project provides runtime and builder packages, as well as a web installer; version 5.2 requires Java 1.7 or later. A browser-based speech interface offers a way to use the system through the web, and the Java implementation has API documentation. MaryTTS can be deployed through its API, on Linux, macOS, or Windows, on the web, or as a self-hosted system. It provides WAVE output, not MP3. The main project license is GNU LGPL v3.0, while the builder and voices have separate licensing terms; voice licenses may restrict commercial use. A Plone Speech Synthesis Tool connects a Plone portal to a MaryTTS server. MaryTTS is free, with the listed plan at no cost. The project directs questions to the MARY users mailing list and uses GitHub for issue reporting.

Who it suits

MaryTTS suits developers seeking a free, multilingual Java speech synthesis platform with API access and options to build voices or extend language support. It may also fit teams deploying speech synthesis on Linux, macOS, Windows, the web, or their own hosting environment.

What it does well

  • Free, open-source text-to-speech platform written in Java.
  • Version 5.2 supports ten listed languages and English variants.
  • Toolkits support language additions and multiple voice-building approaches.
  • Offers API access and a browser-based speech interface.
  • Supports WAVE output and several deployment options.

What to know first

  • Does not provide MP3 output.
  • Version 5.2 requires Java 1.7 or later.
  • Builder and voice licenses are separate from the main project license.

Limits

The listed plan is free. MaryTTS does not provide MP3 output, and individual voice licenses may restrict commercial use; the builder is GPL-licensed.

Plans

PlanBilled and limitsPrice
MaryTTSOpen-source multilingual text-to-speech platform; runtime is LGPL; builder and voices have separate licensesFree

As marytts.github.io lists them, read 12 Oct 2026. The maker's own page has the final word.

Getting started

  1. Visit the MaryTTS website and open the downloads page.
  2. Choose the web installer, runtime package, or builder package.
  3. Install a recent Java Runtime; version 5.2 lists Java 1.7 or later.
  4. Use the browser speech interface or deploy MaryTTS through the API or a listed platform.
  5. For questions, use the MARY users mailing list.

Verdict

Choose MaryTTS if you need a free Java speech synthesis platform with multilingual support, API access, and voice-building tools. Look elsewhere if you require MP3 output or a single license covering the runtime, builder, and every voice.

Questions

How much does MaryTTS cost?

The listed MaryTTS plan is free, and the product is free.

Which languages does version 5.2 support?

It supports German, British and American English, French, Italian, Luxembourgish, Russian, Swedish, Telugu, and Turkish.

What platforms can run MaryTTS?

Listed platforms include API, Linux, macOS, self-hosted, web, and Windows.

Does MaryTTS output MP3 audio?

No. The FAQ says MaryTTS does not provide MP3 output; WAVE is listed as an export format.

What license applies to MaryTTS?

The project license page lists GNU LGPL v3.0. The builder is GPL-licensed, and individual voice licenses may have their own terms.

What does MaryTTS require to install?

The download page calls for a recent Java Runtime and lists Java 1.7 or later for version 5.2.

Facts from MaryTTS's own pages

API
The documentation page links to Javadoc for the Mary system Java implementation. · marytts.github.io, 12 Oct 2026
API access
Yes · marytts.github.io, 20 Sept 2026
Audio formats
The FAQ says MaryTTS does not provide MP3 output and notes compressed audio support is not a planned near-term milestone. · marytts.github.io, 12 Oct 2026
Audio limitation
The FAQ says MaryTTS does not provide MP3 output and that compressed audio support is not a planned near-term milestone. · marytts.github.io, 12 Oct 2026
Browser demo
The homepage links to a speech synthesis interface that runs directly in a web browser. · marytts.github.io, 12 Oct 2026
Commercial use
The FAQ says the runtime is LGPL-licensed and allows commercial use, modification, and redistribution; builder components are GPL-licensed, and voice licenses vary. · marytts.github.io, 12 Oct 2026
Current listed version
The project summary lists version 5.2, and the download page dates its release to 2016-09-15. · marytts.github.io, 12 Oct 2026
Deployment
The project offers runtime and builder packages, and the download page says a recent Java Runtime is required. · marytts.github.io, 12 Oct 2026
Developer support
The site directs users to the MARY users mailing list for questions and provides documentation and Java API documentation. · marytts.github.io, 12 Oct 2026
Distribution
The 5.2 downloads include a web installer, runtime package, and builder package. · marytts.github.io, 12 Oct 2026
Export formats
WAVE · marytts.github.io, 20 Sept 2026
Free plan
Yes · marytts.github.io, 20 Sept 2026
Headquarters
Kaiserslautern, Germany · marytts.github.io, 28 Sept 2026
Integration
A Plone Speech Synthesis Tool connects a Plone portal to a MaryTTS server. · marytts.github.io, 12 Oct 2026
Issue reporting
The project page says GitHub is used to manage issues, bugs, and feature requests. · marytts.github.io, 12 Oct 2026
Java requirement
The download page says a recent Java Runtime is needed and lists Java 1.7 or later for version 5.2. · marytts.github.io, 12 Oct 2026
Languages
Version 5.2 supports German, British and American English, French, Italian, Luxembourgish, Russian, Swedish, Telugu, and Turkish. · marytts.github.io, 12 Oct 2026
License
The project license page lists GNU Lesser General Public License v3.0. · marytts.github.io, 12 Oct 2026
License limits
The FAQ says marytts-builder is GPL-licensed and voices have individual licenses that may restrict commercial use. · marytts.github.io, 12 Oct 2026
Maintainers
The project was originally developed by DFKI’s Language Technology Lab and Saarland University’s Institute of Phonetics, and is now maintained by the Multimodal Speech Processing Group and DFKI. · marytts.github.io, 12 Oct 2026
Platforms
web,windows,macos,linux,api,self_hosted · marytts.github.io, 20 Sept 2026
Product
MaryTTS is an open-source, multilingual text-to-speech synthesis platform written in Java. · marytts.github.io, 12 Oct 2026
Project organization
The project summary lists DFKI GmbH as the project organization. · marytts.github.io, 12 Oct 2026
Release information
The download page lists MaryTTS 5.2, released 2016-09-15. · marytts.github.io, 12 Oct 2026

Where MaryTTS stands on Freedom251

Look at these too