This Discord bot allows users to convert text to speech using pre-trained models in .onnx format. The bot utilizes Piper, a tool for TTS (text-to-speech) conversion.
-
Clone the repository and copy your models .onnx in models foolder:
git clone https://github.com/HirCoir/PiperTTS-Discord-Bot.git cd PiperTTS-Discord-Bot -
Build the Docker image:
docker build -t piper_discord_bot . -
Run the Docker container:
docker run -d --name piper_bot piper_discord_bot
Ensure that you have Docker installed on your system before proceeding with the installation.
-
Invite the bot to your Discord server using the invite link generated by Discord after creating the bot application.
-
Use the following commands to interact with the bot:
/piper help: Provides information on how to use the bot./piper list: Lists available models for TTS conversion./piper [model_number] [text]: Converts the provided text using the specified model number. Replace[model_number]with the model number obtained from the list command and[text]with the text you want to convert.
BOT_TOKEN: Replace this with your Discord bot token.temp_audio_folder: Set the temporary audio folder path.piper_binary_path: Set the path to the Piper binary.model_folder: Set the path to the folder containing .onnx model files.
Ensure that the Docker container has access to necessary resources such as model files and Piper binary. Please note that you need to replace BOT_TOKEN placeholder with your Discord bot token.