cnnmmd

cnnmmd_xoxxox_ttsply

Engines: Fixed output: Fixed output of speech synthesis: Send one of the audio files in a specified folder from multiple folders each turn.

Implementation/Rights (Source Code/License): [※E]

・

https://github.com/cnnmmd/cnnmmd_xoxxox_ttsply

※E

This code is available to the public so you can see how it works (it's still being cleaned up for collaboration).

dependence:

・

cnnmmd_xoxxox_libtlk

・

cnnmmd_xoxxox_envweb

overview

The configuration file could look something like this - if the received number (in text format) doesn't match any of the others, the first folder will be chosen:

{
  "output": "random",
  "strext": ".wav",
  "dicdir": {
    "0": "/opt/strage/vce000",
    "1": "/opt/strage/vce001",
    "2": "/opt/storage/vce002"
  }
}

Rights: Use

This plugin uses voice files generated from the following characters from the following text-to-speech models:

・

https://github.com/VOICEVOX/voicevox_core

・

VOICEVOX: Shikoku Metan