v1.1

Changed

• With --ssml, input from stdin is assumed to be one document instead of lines (override with --stdin-format lines)
• Bump gruut to version 2.1 for inline lexicons
• Include /usr/share/ca-certificates in Docker scripts

v1.0

[1.0.0] - 20 Oct 2021

Added

• Support for a subset of SSML (--ssml flag)
• Ability to use CUDA (--cuda) and half-precision inference (--half)

v0.5

New features include:

• Automatic downloading of new voices (command-line and web interface)
• 50 voices across 9 languages
• Improved command-line interface, with support for streaming synthesis (by line or paragraph)
• Inline word pronunciations, both phonetically and using known words/segments
• Accented speech using automatic phoneme guessing between languages (beta)

v0.4.0

Allow <voice>;<vocoder> format for MaryTTS voice

2021-03-28

Add samples page