0 Fork 0

T

2023-12-08 09:42:30 +00:00

Initial Build

2023-12-08 09:35:53 +00:00

Initial Build

2023-12-08 09:35:53 +00:00

.gitignore

Initial commit

2023-12-08 09:35:19 +00:00

config.json

Initial Build

2023-12-08 09:35:53 +00:00

harvard_sentences.txt

Initial Build

2023-12-08 09:35:53 +00:00

languages.json

Initial Build

2023-12-08 09:35:53 +00:00

modeldownload.json

Initial Build

2023-12-08 09:35:53 +00:00

modeldownload.py

Initial Build

2023-12-08 09:35:53 +00:00

README.md

Update README.md

2023-12-08 09:42:30 +00:00

requirements.txt

Initial Build

2023-12-08 09:35:53 +00:00

script.py

Initial Build

2023-12-08 09:35:53 +00:00

style.css

Initial Build

2023-12-08 09:35:53 +00:00

tts_server.py

Initial Build

2023-12-08 09:35:53 +00:00

alltalk_tts

AllTalk is an updated version of the Coqui_tts extension for Text Generation web UI. Features include:

Settings page to adjust your base startup settings.
Low VRAM mode to improve performance where your LLM takes up your VRAM.
DeepSpeed voice processing, giving a 3-4x performance boost (requires DeepSpeed installing).
Local/Custom models (API Local and XTTSv2 Local).
Configurable deletion of old wav file outputs.
Built in manual & settings on a web page.
Clear command line output for any warnings or issues.