[Resource] RVC voice modules

[Metalhead33]

Here are some AI voices I trained in RVC, mostly with 505 epochs each:

Baldur's Gate 1-2 characters:
- Aerie
- Ajantis Ilvastarr
- Alora
- Anomen Delryn
- Baeloth Barrityl
- Branwen
- Cernd
- Clara
- Coran
- Dorn Il-Khan
- Dynaheir
- Edwin Odesseiron
- Eldoth Kron
- Elminster Aumar
- Faldorn
- Garrick
- Glint Gardnersonson
- Haer'Dalis
- Hexxat
- Imoen
- Jaheira
- Jan Jansen
- Kagain
- Keldorn Firecam
- Khalid
- Kivan
- Korgan Bloodaxe
- Mazzy Fentan
- Minsc
- M'Khiin Grubdoubler
- Montaron
- Nalia de'Arnise
- Neera
- Quayle
- Rasaad yn Bashir
- Safana
- Sarevok Anchev
- Schael Corwin
- Shar-Teel Dosan
- Skie Silvershield
- Tiax
- Valygar Corthala
- Viconia DeVir
- Voghiln
- Xan
- Xzar
- Yeslick Orothiar
- Yoshimo

From Gothic 1:
- Diego (Gothic)
- Gothic Protagonist

From Warhammer 40 000: Rogue Trader:
- Cassia Orsellio
- Jae Heydari
- Yrliet Lanaevyss

From Shogun Total War and Medieval Total War:
- Catholic Commander & Narrator
- Muslim Commander
- Muslim Narrator
- Orthodox Commander & Narrator
- Engrish Voice
- Engrish Voice 2
- Japanese Voice
- Mongol

From Stronghold and Stronghold Crusader:
- The Advisor
- The Scribe
- The Caliph
- The Emir
- The Nizar
- Saladin
- The Sultan
- The Wazir
- The Pig
- The Rat
- The Snake
- The Wolf
- Richard Lionheart
- Lord Woolsack
- Sir Longarm
- Christian Narrator
- Christian Mission Control
- Muslim History
- Muslim Mission Control
- Stronghold Narrator
- Chinese Narrator

From the Hungarian localization of Stronghold Crusader:
- The Advisor, The Caliph & The Snake
- The Scribe
- The Pig
- The Rat
- The Wolf & many others
- The Wazir
- Saladin
- Richard Lionheart
- Christian Narrator & Mission Control
- Muslim Narrator & Mission Control

Others:
- Amamiya Sora, Japanese singer & voice actress
- Itou Miku, Japanese singer & voice actress
- Uesaka Sumire, Japanese singer & voice actress
- Tifa Lockhart from the Final Fantasy 7 remake
- Asuka Kasen, from GTA 3
- Cosmo Jarvis = John Blackthorne from Shogun (2024)
- Anna Sawai = Toda Mariko from Shogun (2024)
- PS1 Hagrid
- Some dude who made a parody of my OC

Alternatively, the full album

All of them can also be downloaded at this link.

No need to credit me, if you use these AI voices anywhere.

OBSOLETE TESTS BELOW, WHEN THEY ALL HAD 60 EPOCHS:

---

The Edwin voice was already tested out at

So, today, I set up RVC and went ahead to alter my voice into Edwin's voice.

My real voice:
https://vocaroo.com/1nju4qOpdstz

Edwin voice transformations:
https://vocaroo.com/1lBT24fxfiuF
https://vocaroo.com/1iYaCxo5ZqA9
https://vocaroo.com/1kMwkh3gVJaT
https://vocaroo.com/1lPLLhvcF29d

Depending on how many Tav lines are there, I could make an attempt to be the "voice double" for wannabe-Edwin Tavs.
And yes, this is my natural accent.

Dynaheir Test:
https://voca.ro/16EwAOK7efLJ

Another test run was performed at:

[Metalhead33]

--- Reserved for later

[maidenhaver]

No, I don't think I will.

[Red7]

does it has text to speech function? the rvc i mean.

[orinEsque]

These voices were trained form Medieval Total War and Shogun Total War:
- Catholic Commander & Narrator
- Orthodox Commander & Narrator
- Muslim Commander
- Muslim Narrator
- Engrish Voice
- Engrish Voice 2
- Japanese Voice
- Mongol Voice

These voices were trained from Stronghold Crusader, with the exception of the last:
- The Advisor
- The Scribe
- Stronghold 1's Original Narrator, Military Campaign
- Christian Narrator
- Christian Mission Control
- Muslim Narrator
- Muslim Mission Control
- The Caliph
- The Emir
- The Nizar
- The Sultan
- The Wazir
- The Pig
- The Rat
- The Snake
- The Wolf
- Richard Lionheart
- Saladin
- Lord Woolsack
- Sir Longarm
- Chinese Narrator from Emperor: Middle Kingdom

These voices were trained from the Hungarian localization of Stronghold Crusader:
- The Advisor
- The Scribe
- Christian Narrator & Mission Control
- Muslim Narrator & Mission Control
- The Wazir
- The Pig
- The Rat
- The Wolf
- Richard Lionheart
- Saladin

All of them can also be downloaded at this link.

What's the Epoch on each of these?

[Magick]

Dynaheir Test:
https://voca.ro/16EwAOK7efLJ

I'd love to see the face on the sweet baby types as they listen to this..

[loregamer]

Not sure what RVC is but I've been using these for AI voices https://rentry.org/Voice-Samples

https://vocaroo.com/16EimJNHxGJH

[Metalhead33]

What's the Epoch on each of these?

200

does it has text to speech function? the rvc i mean.

No. You have to combine it with an actual TTS.

Not sure what RVC is

https://github.com/RVC-Project/Retrieva ... sion-WebUI

[Metalhead33]

Testing out the Stronghold Crusader Christian Narrator. The TTS is from NovelAI.

https://voca.ro/1gFViZGITVGk
https://voca.ro/1e6hmg5gBaQl

[Orvas Dren]

Here are some AI voices I trained in RVC, mostly with 60 epochs each:

Baldur's Gate 1-2 characters:
- Aerie from Baldur's Gate 2
- Ajantis Ilvastarr from Baldur's Gate 1
- Alora from Baldur's Gate 1
- Anomen Delryn from Baldur's Gate 2
- Baeloth Barrityl from Siege of Dragonspear
- Branwen from Baldur's Gate 1
- Cernd from Baldur's Gate 2
- Clara from Baldur's Gate 2
- Coran from Baldur's Gate 1
- Dorn Il-Khan from Baldur's Gate 1-2
- Dynaheir from Baldur's Gate 1
- Edwin Odesseiron from Baldur's Gate 1-2
- Eldoth Kron from Baldur's Gate 1
- Elminster Aumar from Baldur's Gate 1
- Faldorn from Baldur's Gate 1
- Garrick from Baldur's Gate 1
- Glint Gardnersonson from Siege of Dragonspear
- Haer'Dalis from Baldur's Gate 2
- Hexxat from Baldur's Gate 2
- Imoen from Baldur's Gate 1-2
- Jaheira from Baldur's Gate 1-2
- Jan Jansen from Baldur's Gate 2
- Kagain from Baldur's Gate 1
- Keldorn Firecam from Baldur's Gate 2
- Khalid from Baldur's Gate 1
- Kivan from Baldur's Gate 1
- Korgan Bloodaxe from Baldur's Gate 2
- Mazzy Fentan from Baldur's Gate 2
- Minsc from Baldur's Gate 1-2
- M'Khiin Grubdoubler from Siege of Dragonspear
- Montaron from Baldur's Gate 1
- Nalia de'Arnise from Baldur's Gate 2
- Neera from Baldur's Gate 1-2
- Quayle from Baldur's Gate 1
- Rasaad yn Bashir from Baldur's Gate 1-2
- Safana from Baldur's Gate 1
- Sarevok Anchev from Baldur's Gate 1-2
- Schael Corwin from Siege of Dragonspear
- Shar-Teel Dosan from Baldur's Gate 1
- Skie Silvershield from Baldur's Gate 1
- Tiax from Baldur's Gate 1
- Valygar Corthala
- Viconia DeVir from Baldur's Gate 1-2
- Voghiln from Baldur's Gate 1: Siege of Dragonspear
- Yeslick from Baldur's Gate 1
- Yoshimo from Baldur's Gate 2
- Xan from Baldur's Gat 1
- Xzar from Baldur's Gate 1

Others:
- Amamiya Sora, Japanese voice actress and singer
- Itou Miku, Japanese voice actress and singer
- Uesaka Sumire, Japanese voice actress and singer
- Asuka Kasen from GTA 3
- Tifa Lockhart from Final Fantasy 7 Remake
- PS1 Hagrid
- Some random dude who made a parody of my OC, very low-quality

Alternatively, the full album

No need to credit me, if you use these AI voices anywhere.

The Edwin voice was already tested out at

So, today, I set up RVC and went ahead to alter my voice into Edwin's voice.

My real voice:
https://vocaroo.com/1nju4qOpdstz

Edwin voice transformations:
https://vocaroo.com/1lBT24fxfiuF
https://vocaroo.com/1iYaCxo5ZqA9
https://vocaroo.com/1kMwkh3gVJaT
https://vocaroo.com/1lPLLhvcF29d

Depending on how many Tav lines are there, I could make an attempt to be the "voice double" for wannabe-Edwin Tavs.
And yes, this is my natural accent.

Dynaheir Test:
https://voca.ro/16EwAOK7efLJ

Another test run was performed at:

Do you have a good primer for using RVC?

[Metalhead33]

Do you have a good primer for using RVC?

I used the default settings for everything, except for GPU batches and epochs (60 epochs for the Baldur's Gate 1-2 characters, 200 for everyone else).
Otherwise, I'm not sure what you mean by "primer". If you are looking for a good TTS, I recommend NovelAI - it allows you to download the generated speech, which can then be transformed with RVC.

[Orvas Dren]

Do you have a good primer for using RVC?

I used the default settings for everything, except for GPU batches and epochs (60 epochs for the Baldur's Gate 1-2 characters, 200 for everyone else).
Otherwise, I'm not sure what you mean by "primer". If you are looking for a good TTS, I recommend NovelAI - it allows you to download the generated speech, which can then be transformed with RVC.

RVC is voice-to-voice out of the box right?

[Metalhead33]

Do you have a good primer for using RVC?

I used the default settings for everything, except for GPU batches and epochs (60 epochs for the Baldur's Gate 1-2 characters, 200 for everyone else).
Otherwise, I'm not sure what you mean by "primer". If you are looking for a good TTS, I recommend NovelAI - it allows you to download the generated speech, which can then be transformed with RVC.

RVC is voice-to-voice out of the box right?

Yep. It is. You need to provide it with a voice input: either your own voice recordings, or something generated by a TTS.

[Orvas Dren]

I used the default settings for everything, except for GPU batches and epochs (60 epochs for the Baldur's Gate 1-2 characters, 200 for everyone else).
Otherwise, I'm not sure what you mean by "primer". If you are looking for a good TTS, I recommend NovelAI - it allows you to download the generated speech, which can then be transformed with RVC.

RVC is voice-to-voice out of the box right?

Yep. It is. You need to provide it with a voice input: either your own voice recordings, or something generated by a TTS.

Thanks, I'll just try it out again. For whatever reason I failed to get it to work the last time I attempted a couple months back, though it may have just been due to my own error.

[Metalhead33]

Thanks, I'll just try it out again. For whatever reason I failed to get it to work the last time I attempted a couple months back, though it may have just been due to my own error.

Oh, and the .pth files go into the assets/weights folder, while the other file goes into the assets/indices folder.

[orinEsque]

I suggest you go 500 on bg1 and 2 voice lines. There's too few lines.
Could be why your Edwin sounds a bit off

[Metalhead33]

Could be why your Edwin sounds a bit off

I think that might have more to do with either my microphone, or the way I speak. I noticed that even when I use a module trained with 200 epochs, some weird things happen, like my Ms turning into Bs, or the Ss being muted, regardless of the AI module I use. The same issue does not happen when I feed a TTS's output to the RVC AI.
Maybe I have a cold without knowing it?

[orinEsque]

Could be why your Edwin sounds a bit off

I think that might have more to do with either my microphone, or the way I speak. I noticed that even when I use a module trained with 200 epochs, some weird things happen, like my Ms turning into Bs, or the Ss being muted, regardless of the AI module I use. The same issue does not happen when I feed a TTS's output to the RVC AI.
Maybe I have a cold without knowing it?

I've had issues getting some enunciations to work even with input lines from Native English speakers as well.

Had to rerecord multiple times to get the right alphabet sound sometimes as well T.T

[Metalhead33]

I think that might have more to do with either my microphone, or the way I speak. I noticed that even when I use a module trained with 200 epochs, some weird things happen, like my Ms turning into Bs, or the Ss being muted, regardless of the AI module I use. The same issue does not happen when I feed a TTS's output to the RVC AI.
Maybe I have a cold without knowing it?
[/quote]
I've had issues getting some enunciations to work even with input lines from Native English speakers as well.

Had to rerecord multiple times to get the right alphabet sound sometimes as well T.T
[/quote]

I noticed that - regardless of the AI module I use (60 epoch BG1-2 vs 200 epoch TW/SH) - it works well with clean recordings taken from video games, TTS outputs, as well as.... this.



https://voca.ro/15lgEIbFEao3
https://voca.ro/1bnefPultpZg
https://voca.ro/13mFWqELfrm8
https://voca.ro/1oH5aSwAl4kk

Versus using my own voice as an input:
https://voca.ro/17bxrKMKWkc9
https://voca.ro/15xf4MdvXJpv
Tfw my English was Engrish all along.

[Metalhead33]

Semi-related, but when training for AI, the audio could be pre-cleaned with this: https://podcast.adobe.com/enhance

Haven't used it before, but in a video, the results are impressive:

[orinEsque]

You definitely need more epochs. The conversions are too tinny.

[Metalhead33]

You definitely need more epochs. The conversions are too tinny.

I'll re-train some of the BG 1-2 ones tomorrow.

[rusty_shackleford]

Semi-related, but when training for AI, the audio could be pre-cleaned with this: https://podcast.adobe.com/enhance

Haven't used it before, but in a video, the results are impressive:

"enhanced"??

[Metalhead33]

"enhanced"??

Cleaned up.

[rusty_shackleford]

"enhanced"??

Cleaned up.

"cleaned up"???
It sounds far worse.

[Oyster Sauce]

"enhanced"??

Cleaned up.

"cleaned up"???
It sounds far worse.

You going to train AI on a voice sample smothered with static?

[rusty_shackleford]

Cleaned up.

"cleaned up"???
It sounds far worse.

You going to train AI on a voice sample smothered with static?

If I wanted it to sound like how those actually sounded, yes.

[Oyster Sauce]

"cleaned up"???
It sounds far worse.

You going to train AI on a voice sample smothered with static?

If I wanted it to sound like a fan-voiced Skyrim mod, yes.

[rusty_shackleford]

You going to train AI on a voice sample smothered with static?

If I wanted it to sound like a fan-voiced Skyrim mod, yes.

Did you listen to the video? It doesn't even sound like the same person.

[rusty_shackleford]

This reminds me of how people are unaware pixel art for consoles was designed around the limitations of the medium which is why it looks like **** without scanlines.
Yes, they knew the audio recording devices had limitations, and they were making voices that sounded best within that limitation, not something to be cleaned up later.