How to use RuthTTS
Create and Activate a Conda Environment
conda create -n environment_name
On the terminal, type the above command to establish a conda environment called "environment name." (replace environment_name with the name of the conda environment that we want to construct.) eg: tts-ruth.
conda activate environment_name
Install pytorch locally:
Click here - to Select your preferences and run the install command for installing pytorch.
conda install pytorch torchvision torchaudio cudatoolkit=11.1 -c pytorch -c conda-forge
Recommended:
- Pytorch: Stable version
- Your OS
- Package : Conda
- CUDA : 11.6
- Language: Python
API request
For API request, you can use postman or any other API request tool.
For postman, you can download it from here.
After downloading postman, you can use the following API request to get the output.
http://216.48.183.26/convert
Method: POST
JSON (application/json)
Content-Type: application/json
Body: {
"text": "Hello, how are you?"
}
Run Ruth-TTS
API Request{
"text": "Hello, how are you?",
"voice": "gabby_reading",
"seed": 3,
"rate": 16000
}
Parameters for ruth-TTS
text: The text to be converted to speech.
voice: The voice to be used for conversion.
example "gabby_reading"
seed: The seed for random number generator.
example 3
rate: The sampling rate of the audio.
example 16000
To receive results, use this request body (JSON) to send a POST request to the server.