This script generates an audio file (.wav) from a .srt file with timings. There can be unwanted shifts in the final audio if a time interval of a text is not adequate for dubbing.

• pydub: Used for audio segment manipulations.
• pysub-parser: Used for parsing .srt files.
• pyttsx3: An offline text-to-speech library used for dubbing.

Clone the repository and than install the requirements with the following command.

pip install -r requirements.txt

Here is an example usage. with command line options.

python subtitle_to_audio.py -p test/test.srt -r 120 -v 1