v2.0.1

Introduced the --silent argument to mute all voices.

Full Changelog: v2.0.0...v2.0.1

v2.0.0

• Switched from GPT-NEO to the transformers library, making switching models much easier
• Reduced VRAM usage
• Introduced float precision argument to further reduce VRAM usage
• Switched from YourTTS to xTTS v2, improving voice quality
• Support for multiple alternating speakers for narration and dialogues

Full Changelog: v1.1.0...v2.0.0

v1.1.0

Switched TTS model to YourTTS, allowing for customization using short WAV files as voice samples. Included two samples from librispeech. See FAQ in README.md for instructions on how change voices.

Full Changelog: v1.0.2...v1.1.0

v1.0.2

Fixed text generation on CPU. You'll need at least 25 GB of RAM and add the --cpugpt flag to play.sh or play.ps1 (whichever you use). The time it takes to generate text on CPU is in minutes instead of seconds, so be patient.

v1.0.1

Fixed minor issues with linux compatibility.

v1.0.0

First stable release