https://github.com/c0ntradicti0n/tts
Text to speech in bash for long texts (wrapper for tacotron2)
https://github.com/c0ntradicti0n/tts
tts
Last synced: about 2 months ago
JSON representation
Text to speech in bash for long texts (wrapper for tacotron2)
- Host: GitHub
- URL: https://github.com/c0ntradicti0n/tts
- Owner: c0ntradicti0n
- Created: 2022-07-18T13:46:58.000Z (almost 3 years ago)
- Default Branch: master
- Last Pushed: 2022-11-24T00:06:13.000Z (over 2 years ago)
- Last Synced: 2025-02-15T00:42:21.469Z (4 months ago)
- Topics: tts
- Language: Python
- Homepage:
- Size: 2.27 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Simple Text To Speech on command line
Using some modern TTS package with simple use in sh.
At the moment:
* tacotron2, wave-form with speechbrain. it predicts spectograms and then waveforms from them.
Text input must be chunked for that into sentences producing single soundfiles, that are concatenated finally.
## Installation
``` sh
git clone [email protected]:c0ntradicti0n/text2speech.git
cd text2speech
python -m venv venv
. activate /venv/bin/activate
pip install -r requirements.txt
```
### Requirements
* oggCat
for Ubuntu
``` sh
sudo apt-get install oggvideotools
```
## Usage
``` sh
python tts.py --help 3s + ✱ ● ~/P/text2speech
usage: tts.py [-h] [-i [INPUT_FILE]] [-t [TMP_DIR]] out
Process some integers.
positional arguments:
out name of output_file
optional arguments:
-h, --help show this help message and exit
-i [INPUT_FILE], --input_file [INPUT_FILE]
name of input file
-t [TMP_DIR], --tmp_dir [TMP_DIR]
directory for temporary files
```
Pipe or type the text into the script:
**It will create ogg-Files!**
``` sh
. activate /venv/bin/activate
cat test.txt | python tts.py out.ogg
```
Or with `-i`-Flag or `echo` or with pipin into `stdin`