Other Neutrino

mahalisyarifuddin

Passionate Fan
Apr 9, 2018
138
24
Palembang, Indonesia
So I guess there are no people covering this, and yeah, I made this thread.

There's a new, deep-learning-based voice synthesizer called Neutrino. Developed by Shachi, and released freely to the public since yesterday.

It's kinda different to use, so you must prepare a MusicXML file to be synthesized, set some stuff, and it takes time to render the voice. And yeah, the performance depends on your PC specs, so you'll need a PC with 8 gig or more memory, i5/Ryzen 5 or better, and at least 10 gig storage to get somewhat desirable results, or else it takes forever to render.

Thanks to the deep-learning technique, it's kinda successful to capture the natural singing style from the original voices (though some people force-tuned it with 3rd party programs to make it somewhat smooth or customize the singing style). The results kinda reminds me with that Hoya's VoiceText where from the simple MusicXML with no pitchbend parameter, the program add the pitchbend itself and yeah. And people who are too lazy to tune can take benefits with this program. And though this program still have that noise quirk, idk if it's just me but this is my impression on any deep-learning-based voice synthesizers.

It comes with 2 VBs. The one is Youko (it's the same with the Sinsy VB)

And, you know this character, it's Tohoku Kiritan! (it's based on that publicly-released singing dataset)

You could try this by yourself by visiting the official site and download the program.
 
Last edited:

Mika

crying over Rune Factory 5
Jul 5, 2018
244
24
Germany
Neutrino sounds really promising! I feel like you can hear the engine noise the most in lower ranges while in higher ranges you barely hear any engine noise. Which is good! Definitely sounds more pleasant than CeVIO to me too.

 

Blue Of Mind

The world that I do not know...
Apr 8, 2018
619
It's a shame that the specs are quite taxing on many PCs right now, because I do like the lack of engine noise on most of the notes. Maybe Neutrino will advance and slowly reduce the amount of power needed for it to work?
 

kozet

Conlanger
Jul 5, 2019
70
flirora.xyz
For those of you having troubles with double free errors when running the Linux version, the problem might arise from the distro you're running on. If you're not running Ubuntu 18.04, then try running NEUTRINO under a Docker image.

In your Dockerfile:

Code:
FROM ubuntu:bionic

WORKDIR /home/neutrino

RUN apt update

RUN apt install libgomp1
Place your NEUTRINO directory in the same place as the Dockerfile. Then build the image using docker build -t neutrino, then docker run -v $(pwd)/NEUTRINO:/home/neutrino -it neutrino /bin/bash to start a shell in a container.
 

Prism

Enthusiast
Jul 18, 2019
510
Neutrio version . 3 came out and we got a beta voice jsut it seems like a child's voice it's very cute.
 

uncreepy

Retired (mostly)
Apr 9, 2018
1,605
Tohoku Itako is going to be available on NEUTRINO on the 18th.

Sources:
 

Rylitah

kiyoteru enthusiast
Staff member
Moderator
Apr 8, 2018
562
As tomorrow is Kiritanpo Day, Kiritan NEUTRINO is being updated. (Don't think it's out as of me posting this, the tweet says "tomorrow or the day after.")

Changes:
- Sound quality improvement
- Sampling rate is now 48kHZ (it was 32kHZ before)
- Noise reduction

 

Stardust

Vocal Synth Enthusiast
Aug 14, 2020
173
She sounds much better, and a bit more distinctive now. That odd sound that you used to hear is gone now as well. I do not think it was engine noise since JSUT, Itako and Yoko do not have it, so perhaps it was a error?
 

Prism

Enthusiast
Jul 18, 2019
510
There's a new voice bank in development. Her name is No.7 she is voiced by Kotori Koiwai but in a different voice than MEIKA Hime & MikotoVvdwu9CA-2048x1174.jpg7cef10a711ee715f909730c2d8daee41-2048x1195.jpg
 
Last edited:

peaches2217

The One With the Sunflower Hairclip
Sep 11, 2019
1,861
25
Arklahoma
There's a new voice bank in development. Her name is No.7 she is voiced by Kotori Koiwai but in a different voice than MEIKA Hime & MikotoView attachment 4539View attachment 4540
Up until high school I had a dog named Six. For that reason alone I've decided Seven is my new baby. I hope you're chasing your brothers through fields of tall grass, sweetheart :kaito_lili:

I really do hope she doesn't fall victim to what... well, every single Neutrino vocal has fallen victim to. She's so pretty, and I'd love for her to stand out vocally!
 

TheStarPalace

Hardcore Fan
Apr 8, 2018
471
Version 0.431 is now released! Nakumo is out now too (in the download folder, he's in alpha test state so he doesn't have a profile on the website yet). He will eventually have a character design.
According to the update, breath sounds have been fixed too.

 
  • Like
Reactions: Stoo-S and uncreepy

uncreepy

Retired (mostly)
Apr 9, 2018
1,605
Here are some examples of people using him:




I feel like he sounds slightly off for some reason, like he's kind of straining to sing (like he could push his voice further but is holding back)/about to go off key. I checked out a lot of examples on NND and Twitter. I think slow acoustic or light pop songs fit him best.
 

Users Who Are Viewing This Thread (Users: 0, Guests: 0)