jetfontanilla / win-sapi-tts-audio-file-generator

using Win SpVoice Interface (SAPI) with python to generate audio files with either text-to-speech or phoneme-to-speech

Windows SAPI Text-to-Speech / Phoneme-to-Speech Audio File Generator

using Win SpVoice Interface (SAPI) with python to generate audio files

Configuration

edit config.ini to change to a different Voice Bank, or change other TTS parameters

Generating Audio

create a CSV file with the unique ID as the first parameter and the transcript to run as the second. it also supports phoneme-based text-to-speech by adding the phonemes in the 3rd column (link for supported phonemes) if phonemes are provided, it will ignore the transcript parameter

to generate the audio files, run this command

$ python generator.py

generated audio files will be in the output folder