MaryTTS

by DFKI

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

Looking at MaryTTS? Try this first.

Drop your audio. Transcript in seconds. First transcript free, then $4 = 300 min

TL;DR

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

Category
Open source
License
NOASSERTION
Stars
★ 2.6k
Last push
2025-01-17
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

Links

GitHub repo ↗

MaryTTS vs Whipscribe

FeatureMaryTTSWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfree (LGPL)$4–$24 one-time packs (credits never expire) · $2 single unlock · 60 min free on signup
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 ★ 107.0k
whisper.cpp
Georgi Gerganov

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

OSS · MIT ★ 52.8k
faster-whisper
SYSTRAN

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

OSS · MIT ★ 24.8k

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.