HugPipe Text Dictator is an easy-to-use text-to-speech (TTS) application powered by the Hugging Face "MMS-TTS" model. It allows you to effortlessly convert written text into spoken words with natural-sounding audio output.
-
Text to Speech Conversion: Seamlessly transform your text into high-quality, expressive audio.
-
Downloadable Audio: Save the generated audio for later use or distribution.
- Installation: Ensure you have the necessary libraries installed:
pip install -r requirements.txt-
Run the Application:
- Clone this repository.
- Navigate to the project directory.
- Launch the Streamlit app:
streamlit run app.py- Input Text: Enter the text you wish to convert into speech in the provided text area.
- Generate Audio: Click the "Convert to Speech" button to generate the audio.
- Audio Player: Utilize the built-in audio player to listen to the generated audio.
- Download Audio: Download the audio file using the "Download Audio" button.
You can fine-tune the TTS model, voice style, and other parameters by modifying the source code in the app.py file.
-
Hugging Face Transformers: We leverage the Hugging Face "MMS-TTS" model for text-to-speech conversion.
-
Streamlit: Our user-friendly interface is built using Streamlit, making it easy for users to interact with the application.
This project is licensed under the MIT License. Refer to the LICENSE file for detailed information.
We welcome contributions and feedback. If you'd like to contribute to this project, please open an issue or submit a pull request.
If you have questions or feedback, please contact Eddie Gulay.