SpeakFlow is an intuitive desktop application for text-to-speech (TTS) synthesis, designed to convert text documents into high-quality audio files. Utilizing the power of Edge TTS, it offers a wide selection of natural-sounding voices in multiple languages, allowing users to easily generate speech and save it in MP3 format.
Here are a few screenshots of the SpeakFlow application:
The easiest way to run SpeakFlow is to download the compiled executable (.exe) from the Releases section of our repository.
1. Go to the latest release page.
2. Download the latest ZIP archive (e.g., SpeakFlow_v1.0.0.zip
).
3. Unpack the archive to any folder on your computer.
4. Run SpeakFlow.exe
.
If you wish to run the application from source code or make modifications:
Clone the repository:
bash
git clone [https://github.com/Olegiiich/SpeakFlow.git](https://github.com/Olegiiich/SpeakFlow.git)
cd SpeakFlow # Navigate into the project folder
Create and activate a virtual environment:
bash
python -m venv .venv
# For Windows (CMD):
.venv\Scripts\activate
# For Windows (PowerShell):
.venv\Scripts\Activate.ps1
# For macOS/Linux (if you happen to work there):
source .venv/bin/activate
Install required dependencies:
bash
pip install -r requirements.txt
Run the application:
bash
python lecture_tts.py
If you like SpeakFlow and find it useful, you can support our project with a donation. Your support helps us continue to develop the application and add new features.
Support our project with a donation
This project is licensed under the MIT License.
Have questions or suggestions? Contact us:
* Telegram channel: Mlntsk Soft Channel
* GitHub profile: Olegiiich
* Email: melnitskiy95@gmail.com