htsengine(1)

💖 htsengine — HMM-based speech synthesis engine 💖

okay bestie, welcome to the htsengine(1) manual page, General Commands Manual edition. this is the one that makes your computer literally speak, and we're gonna walk through it together. grab a strawberry 🍓 and let's go.

---

✨ NAME ✨

hts_engine — HMM-based speech synthesis engine

like. it synthesizes speech. from HMMs. main character energy fr fr 👑

---

🌸 SYNOPSIS 🌸

hts_engine [options]  [infile]

that's it. that's the whole vibe. options go in, optionally an infile goes in, speech comes out 🦋

---

💅 DESCRIPTION 💅

so this manual page documents the hts_engine command, briefly. quick little rundown, no yapping.

ngl this page was written for the Debian distribution because the original program does not have a manual page. not me showing up to write the docs nobody else wrote 😭 instead, it has documentation in the GNU Info format — see below (iykyk).

hts_engine is a program that synthesizes a speech waveform from HMMs trained by the HMM-based speech synthesis system (HTS). that's the whole point. that's the gig. it takes trained models and turns them into actual audible words. iconic.

---

🎀 OPTIONS 🎀

a summary of options is included below. here's the full menu, no skips, no cuts:

• -m htsvoice — HTS voice files. this is your voice model bestie, the whole personality lives here.
• -od s — filename of output label with duration
• -om s — filename of output spectrum
• -of s — filename of output Log F0
• -ol s — filename of output low-pass filter
• -or s — filename of output raw audio (generated speech)
• -ow s — filename of output wav audio (generated speech)
• -ot s — filename of output trace information
• -vp — use phoneme alignment for duration
• -i i f1 .. fi — enable interpolation & specify number(i), coefficient(f)
• -s i — sampling frequency [auto][1--]
• -p i — frame period (point) [auto][1--]
• -a f — all-pass constant [auto][0.0--1.0]
• -b f — postfiltering coefficient [0.0][0.0--1.0]
• -r f — speech speed rate [1.0][0.0--]
• -fm f — add half-tone [0.0][--]
• -u f — voiced/unvoiced threshold [0.5][0.0--1.0]
• -jm f — weight of GV for spectrum [1.0][0.0--]
• -jf f — weight of GV for Log F0 [1.0][0.0--]
• -z i — audio buffer size (if i==0, turn off) [0][0--]
• infile — label file

and the tea on the output files 🫖: the generated spectrum, log F0, and low-pass filter coefficient sequences are saved in natural endian, binary (float) format. so don't go opening those in a text editor and expecting a cute little readable file, okay? that's not what they are. 💀

---

🌈 EXAMPLE 🌈

if you installed hts-voice-nitech-jp-atr503-m001 in the current directory, the following command lets you make a voice file from input.lab:

% hts_engine -s 48000 -p 240 -a 0.55 \
-m nitech_jp_atr503_m001.htsvoice \
-ow output.wav \
input.lab

see how the backslashes keep the command going across lines? that's the move. output.wav walks out the door and it's literally talking. obsessed. 🔥

---

👑 AUTHOR 👑

this manual page was written by Koichi Akabe <vbkaisetsu@gmail.com> for the Debian system (and may be used by others). permission is granted to copy, distribute and/or modify this document under the terms of the GNU General Public License, Version 2 or any later version published by the Free Software Foundation.

on Debian systems, the complete text of the GNU General Public License can be found in /usr/share/common-licenses/GPL. go read it if you want the full lore, it's giving required reading 📚

---

and that's the whole page bestie!! this was the htsengine(1) manual, General Commands Manual, and yes the footer really is just htsengine(1) again — no version number, no date, just the name doing a little encore. periodt. 💜✨