File	Date	Author	Commit
audio_archive	2024-05-11	Peter Romero	[ba0646] SpeakLogPSU Version: 00.00.16
audio_reference	2024-05-11	Peter Romero	[ba0646] SpeakLogPSU Version: 00.00.16
tts	2024-05-23	Peter Romero	[202cb7] SpeakLogPSU Version: 00.00.18 with new coqiu fork
.gitignore	2024-04-18	Peter Romero	[a280e4] SpeakLogPSU Version: 00.00.00
config.db.json	2024-05-19	Peter Romero	[6503ee] SpeakLogPSU Version: 00.00.18
readme.txt	2024-05-19	Peter Romero	[852dfd] SpeakLogPSU Version: 00.00.18
setup.bash	2024-04-27	Peter Romero	[c7a772] SpeakLogPSU Version: 00.00.08
speakLogPSU.py	2024-07-13	Peter Romero	[88bb7b] SpeakLogPSU Version: 00.00.19
speakLogPSU.spec	2024-07-02	Peter Romero	[8ed82d] SpeakLogPSU Version: 00.00.18 with pyinstaller ...
startTemplate.bash	2024-04-27	Peter Romero	[b0a62c] SpeakLogPSU Version: 00.00.07

Read Me

reads the log and sends the text to piper.
~/.config/Epic/PSUnreal/Saved/Logs/Pongo_Donjo_chat.txt



download:
https://www.planeshift.it/Download


#####################
SETUP
#####################

RUN bash setup.bash inside the folder in a shell

OR:

https://github.com/rhasspy/piper

The config.db.json is a list of NPCs and their voices.
If no voices are found in ~/piper/voices the default voice will be used.
Please download en_US-joe-medium.onnx and en_US-joe-medium.onnx.json
and copy it to this folder.

create the folder audio_archive to let the script create the .wav files
before playback but this is optional.

.
├── audio_archive
├── config.db.json
├── piper
│   └── voices
└── speakLogPSU.py



#####################
RUN
#####################

e.g.
python3.8 'speakLogPSU.py' "Pongo Donjo"

#####################
CONFIGURE
#####################

~/config.db will get created and updated with the config.db.json
if you press the button "update DB"


#####################
SUPORT FOR COQUI VOICE CLONING
#####################

To use it you need to run the tts/setup.bash inside the tts folder
with python3.10.
An example can be found in config.db.json.
The CPU time is between three and five minutes for each wav file.
If you don't like the voice of Trasok_Starhammer you can remove the folder.

.
├── audio_archive
│   └── Trasok_Starhammer
│       ├── 025ba861d09c61ee84052e9f2ce2d446047cf196.wav
│       ├── aace9686e3354e35c29ca85fa54c5136b607dbff.wav
│       ├── b5da59af609eb059f21f9f11affbe185fd6eb9b8.wav
│       ├── b7b5eb918c9f59548800eeea656caeee8741b5cc.wav
│       ├── bde0f9014e2bafe06d2841c79320ad7badbacc0f.wav
│       ├── c41aaed6500374b61afab245266fd04db3b888d3.wav
│       ├── c908dd1981c620034e0d7de20ea77e1e6abf3874.wav
│       ├── d01ad5605643075c2ec5b26fef1de4497ae7d5f2.wav
│       ├── e25ae6244e75c2035ff8071dc37a1f6edb0e2862.wav
│       ├── e8dffb42583ee384decf35c3a64e17501c1722c3.wav
│       ├── ea723392077ae048afc718fe63e56cd20a08951a.wav
│       ├── fb142e3fe76241d47f6f7705b0d362f91307bfa7.wav
│       └── fbcdb43f7cfec8465a72d24bcc2bc73a6d664856.wav
├── audio_reference
│   └── planeshift-code-r10021-trunk-data-voice
│       └── sammich
│           └── 1Sothelowly-1.wav
├── config.db.json
├── piper
│   └── voices
├── readme.txt
├── setup.bash
├── speakLogPSU.py
├── startTemplate.bash
└── tts
    └── setup.bash