open_jtalk — Japanese TTS system
Contents
Description
This manual page documents briefly the open_jtalk command.
This manual page was written for the Debian distribution because the original program does not have a
manual page. Instead, it has documentation in the GNU Info format; see below.
open_jtalk is a program that synthesize speech waveform from Japanese texts. It uses HMMs trained by the
HMM-based speech synthesis system (HTS).
Example
If you installed hts-voice-nitech-jp-atr503-m001 in the current directory, the following command let you
make a voice file from input.txt:
% open_jtalk -s 48000 -p 240 -a 0.55 \
-m nitech_jp_atr503_m001.htsvoice \
-ow output.wav \
-x dic_dir input.txt
Name
open_jtalk — Japanese TTS system
Options
A summary of options is included below.
-xdir dictionary directory
-mhtsvoice
HTS voice files
-ows filename of output wav audio (generated speech)
-ots filename of output trace information
-si sampling frequency [ auto][ 1-- ]
-pi frame period (point) [ auto][ 1-- ]
-af all-pass constant [ auto][ 0.0-- 1.0]
-bf postfiltering coefficient [ 0.0][ 0.0-- 1.0]
-rf speech speed rate [ 1.0][ 0.0-- ]
-fmf additional half-tone [ 0.0][ -- ]
-uf voiced/unvoiced threshold [ 0.5][ 0.0-- 1.0]
-jmf weight of GV for spectrum [ 1.0][ 0.0-- ]
-jff weight of GV for log F0 [ 1.0][ 0.0-- ]
-zi audio buffer size (if i==0, turn off) [ 0][ 0-- ]
infile text file [stdin]
Synopsis
open_jtalk [options] [infile]
