Soluzioni - Software Open Source

izSynth - TTS/Text To Speech synthesizer, background music overlay assembler and audio file converter for PBX and Home Automation Systems

izSynth is a bash script running under Linux, written to automate the synthesis of voices used into izPBX System or for realtime TTS (Text To Speech) used into Home Automation solutions.
It can use offline synthesis software like Loquendo (using the Wine environment), eSpeak, Festival, VoiceRSS, NaturalReaders, and other popular online web TTS services to synthesize audio voices from ASCII text files and automatically merging the audio with background music (mp3 and wav format are supported), adding silences and fade in and out.

izSynth INSTALL

CentOS:

yum install -y sox lame mplayer curl espeak wine

Debian:
sudo apt-get update
sudo apt-get install -y sox lame mplayer curl espeak wget bsdmainutils file mawk coreutils

For windows sapi5 support, install the "wine" package and download sapi2wav.exe: wget https://gitlab.mister-muffin.de/josch/novel2audio/raw/master/sapi2wav.exe

 

izSynth USAGE

Before using izsynth, we must configure and try it via command line. Make a quick test with the following command:
izsynth -e naturalreaders -v Peter -t "Welcome home, mr Stark"
NB. Some engines, like voicerss, need an APY KEY before you can use it, follow the onscreen guide to get your APY KEY:
izsynth -e voicerss -H
izSynth is configurable in 3 ways:
  • From command line specifying the options
  • Modifying the variables on the izsynth script itself
  • Using an external config file for overriding the izsynth variables.
I suggest to create an external config file to avoid changes to your configurations when you update izsynth. Run izsynth command with -h option and read the online output:
./izsynth -h

izSynth Development

Fork and contribute the izSynth Development using the official GitHub repository: https://github.com/ugoviti/izsynth

izSynth Download

2016-12-23 | izSynth version 4.5

- Download TAR Archive

ChangeLog:

- introduced playback engines (currently implemented mplayer only)
- many script refactoring

2016-10-28 | izSynth version 4.4

- Download TAR Archive

ChangeLog:

- implemented -C option to write/overwrite the izsynth user config file
- some sanity checks to detect the $HOME directory of user

2016-06-18 | izSynth version 4.3

- Download TAR Archive

ChangeLog:

- implemented PLAYBACK_DEVICE and new -d (specify the output device) -D (list available output devices) options
- is now possibile to override the playback command (-k) and playback command options (-K)
- help menu enhancements

2016-05-24 | izSynth version 4.2

- Download TAR Archive

ChangeLog:

- don't create tts files name longer than 64 chars
- dynamic voices listing for fromtexttospeech engine (not more static list)
- some code cleanup

2016-05-09 | izSynth version 4.1

- Download TAR Archive

ChangeLog:

- added support for auto splitting sentences longer than the supported engine chars
  each engine now have a TTS_LENGTH variable if engine usage is limited. This feature make possible to sinth very long sentences
- speedup the synthesizing process avoiding intermediate convertion to wav format when not remizing o megamixing (this gained 500ms in 4 seconds playback)
- more intuitive feedback when synthesizing
- changed default engine to 'naturalreaders' and voice 'Peter' (english language)
- restored google tts support (limited to 160 chars max)
- added -r option for removing synthesized file after playback
- added support for stdin as input stream, example:
   echo this is only a test | izsynth -
- ispeech tts engine addded (http://www.ispeech.org/)

2016-04-27 | izSynth version 4.0

- Download TAR Archive

ChangeLog:

- added external engine support (put your TTS engines into $HOME/.config/izsynth/engines/YOURENGINE.conf)
- changed default engine to voicerss (before using it, get an APIKEY! type izsynth -H for more info)
- added tts_engine help menu
- enhanced output logging
- minor script syntax fixes
- MEGAMIX feature added (read the examples with -E switch)
- major izsynth restructuration with added smartness ;)
- now is possible to change on the fly the output volume for string TTS
- sox command version check with extra options workarounds
- addedd support for voicerss TTS engine
- addedd external config file for override the script variables and use external services APIKEYs
< Altre Soluzioni