Umamusume TTS

Convert your text into speech using your favorite UmaMusume character's voice.

Prerequisites

Install the required packages :

Run the following command to install dependencies:

pip install -r requirements.txt

Note: Some packages may not be compatible with certain systems. If you encounter issues, remove the incompatible packages from requirements.txt and try again.

Running the API

To start the API server, run:

python app.py

Testing the API :

Text-to-Speech (TTS) API

Send a POST request to the /synthesize endpoint with the following payload:

curl -X POST -H "Content-Type: application/json" \
     -d '{
           "speaker_name": "Rice Shower",
           "text": "ライスね、、お兄様のこと、だーーい好き！",
           "noise_scale": 0.37,
           "noise_scale_w": 0.46,
           "length_scale": 1.3
         }' \
     http://localhost:18343/synthesize --output output.ogg

The response will be an audio file saved as output.ogg.

Get Available Speakers

Fetch a list of available speakers with an optional search term:

curl -v -X POST http://localhost:18343/speakers -H "Content-Type: application/json" -d '{"search": "mejiro"}'

Notes

Ensure your Python environment is properly set up with pip and other dependencies before running the application.
Modify the config_path and checkpoint_path in app.py to point to the correct configuration and model files if they are not in the default locations.

1.5 KiB Raw Blame History