|
|
--- |
|
|
license: mit |
|
|
--- |
|
|
TARS Voice Model |
|
|
This repository contains a Text-to-Speech (TTS) model trained to emulate the voice of TARS from the movie Interstellar. The model was developed using XTTSv2. |
|
|
|
|
|
License |
|
|
This project is licensed under the MIT License. |
|
|
|
|
|
Model Details |
|
|
Architecture: XTTSv2 |
|
|
Training Data: Audio samples extracted from Interstellar featuring TARS's voice. |
|
|
Purpose: To generate speech that closely resembles TARS's distinctive voice. |
|
|
|
|
|
Installation |
|
|
Download the files to a folder and put the folder named tars in your tts models dir. |
|
|
|
|
|
Then launch tts with: |
|
|
python xtts_api_server --listen --deepspeed --lowvram --model-folder "D:\AI_Tools\xtts-api-server\xtts_models" --model-source local --version tars |
|
|
|
|
|
|
|
|
Use the provided scripts or interface to input text and receive audio output in TARS's voice. |
