MaryTTS

by DFKI

Java-based open-source TTS platform — research and academic deployments.

TL;DR

Java-based open-source TTS platform — research and academic deployments.

Best for java/JVM applications and academic research needing a multilingual TTS server. Pricing: free (LGPL).

Category
Open source
License
—
Stars
—
Last push
—
Pricing
free (LGPL)
Platforms
Linux, macOS, Windows

What it is

MaryTTS is an open-source multilingual TTS platform from DFKI Saarbrücken. JVM-based, with HMM and unit-selection voices in 11 languages. LGPL. Best fit: research and JVM apps where neural TTS is overkill. Consent posture: synthetic-only.

Best for: Java/JVM applications and academic research needing a multilingual TTS server.
Watch out for: Concatenative / HMM voices — predates the neural-TTS era.

Install / use

Download from github.com/marytts/marytts/releases

Features

Speaker diarizationNo
Word-level timestampsNo
Streaming / real-timeNo
Languages supported11
HIPAA eligibleNo

MaryTTS vs Whipscribe

FeatureMaryTTSWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfree (LGPL)free beta
Speaker diarization—Yes
Word timestamps—Yes
Streaming—No
Languages1199
PlatformsLinux, macOS, WindowsWeb, API, MCP

Alternatives to MaryTTS

OpenAI Whisper
OpenAI

The reference open-source multilingual ASR model from OpenAI.

OSS · MIT ★ 98.1k
whisper.cpp
Georgi Gerganov

C/C++ port of Whisper — runs on anything, from a Raspberry Pi to Apple Silicon.

OSS · MIT ★ 48.8k
faster-whisper
SYSTRAN

4× faster than reference Whisper using CTranslate2 — production sweet spot.

OSS · MIT ★ 22.3k

Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.