Loading UTAU voice banks into the Python data structure.
Project description
strcuta - Loading UTAU voice banks into the Python data structure
Little example
from strcuta import voicebank
# Load the voice bank "Yamine Renri VCV ver.1.5" (Thanks to the owner :D).
renri = voicebank.load("../闇音レンリ・連続音Ver1.5")
# Resolve the spell (u-ta) and the pitch (F#5) into the voice as a wave data in
# accordance with the "oto.ini"s and the "prefix.map".
uta = renri.voice("u た", "F#5")
# Save the data with the WAVE format.
uta.write("uta_fs5.wav")
# Cut the specific segment of the voice and then save it.
# "Overlap"
uta.ovl().write("uta_ovl.wav")
# "Preutterance"
uta.pre().write("uta_pre.wav")
# "Consonant". con() or fixed()
uta.con().write("uta_vc-.wav")
# "Vowel". vow() or stretchable()
uta.vow().write("uta_-v.wav")
# Except for the preutterance
uta.intime().write("uta_intime.wav")
# Also play voices with the "sounddevice" package. (This is an optional
# feature. Install the "strcuta[play]" instead of the "strcuta" to install the
# "sounddevice" together.)
uta.play()
uta.con().play()
Currently, strcuta
can load -
*.wav
*.frq
oto.ini
prefix.map
.
You can find the early releases in the release history.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
strcuta-0.0.15rc1.tar.gz
(5.8 kB
view hashes)
Built Distribution
Close
Hashes for strcuta-0.0.15rc1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 402676cfdf42662f9224c5dafc3b7d4d1e304789822a0ed55e93cfdb83541223 |
|
MD5 | 869561c9587aebf456b879cd52c7a3b0 |
|
BLAKE2b-256 | 9e40253b52747f46891967fd830ff18a0ef739b614d33020474227509cbdec3d |