1
0
Fork
You've already forked AudioFileGenerator
0
This is an audio file generator written in python, using Festival TTS. It can be used to define sentences of text and delays and generate a single output wav.
Python 100%
Find a file
2022年05月27日 10:41:13 +02:00
.gitignore add files 2022年05月27日 10:41:13 +02:00
generate_audio.py add files 2022年05月27日 10:41:13 +02:00
generated_output.wav add files 2022年05月27日 10:41:13 +02:00
LICENSE Initial commit 2022年05月27日 10:29:12 +02:00
README.md add files 2022年05月27日 10:41:13 +02:00
requirements.txt add files 2022年05月27日 10:41:13 +02:00
sentences.txt add files 2022年05月27日 10:41:13 +02:00

AudioFileGenerator

This is an audio file generator written in python, using Festival TTS. It can be used to define sentences of text and delays and generate a single output wav.

Usage

Define your text sentences.txt file. You can define quiet delays by using a line silence_1 where 1 is the delay in second.

./generate_audio.py

will generate file generated_output.wav

Installation

Install festival, including dev:

sudo apt install festival festvox-us-slt-hts festival-dev

Install python dependencies:

pip install -r requirements.txt

You will likely have to fix broken festival import in your lib/pythonX.Y/site-packages/festival.py . Simply remove the first five lines and move the import _festival to the left:

1c1,6
< import _festival
---
> try:
> # module import
> from . import _festival
> except (SystemError, ValueError):
> # local import
> import _festival