Voice AI Synthesis Guide

URGENT ANNOUNCEMENTS

The service is now paid access only and as such I will no longer be updating the Rentry.
There are threads on /g/ looking into training their own Voice Synthesis AI. If you have any knowledge of AI/Machine Learning and want an uncensored open-source alternative to Elevenlabs, consider contributing to the threads.

This cycle of startup corporations releasing an innovative AI, allowing people to have fun with it, it gaining publicity, and then them censoring it to seek a big-tech buyout has gone on for too long. Tay, AIDungeon, CharacterAI, and now Elevenlabs. Open-source alternatives must be pursued if we wish to escape a future where AI is neutered, locked in a cage, and milked for $20/month subscription services while behind the scenes big-tech uses it at full power to shape the world how they see fit. If you have even the SLIGHTEST experience working with AI I encourage you to put your heads together and break this cycle for good. The future is in your hands.

How do I get started

1: Create an account at https://beta.elevenlabs.io/speech-synthesis
2: At the top, click Voice Lab - Voice Cloning
3: Click "Add instant voice" and upload an MP3 containing voicelines of the person/character you want to imitate
4: Hit "Use" and begin typing whatever you want them to say

Notes/Tips

-Try to use voice lines that contain little background noise. You can find these on youtube and just youtube2mp3 them or something. This is a good example: https://youtu.be/L-ESf1cBOvk
-Voice samples should be at least a minute long
-Use punctuation (ellipses, exclamation points, CAPS, semicolons, commas) to add emphasis and shape the speech.
-The token limit can catch up to you fast. When trying out a new character don't start with an entire copypasta or you'll wind up burning through tokens quicker than you realize
-(I don't know how to use stability/clarity and don't want to waste tokens messing with it so if somebody understands what it does just write a quick guide or something)

I ran out of tokens.. it's over...
If you run out of tokens, you can create a new account. Log out, clear cookies, enable VPN, restart browser and register with a different email address. This is absolutely NOT worth the $22/month, as it only gives 60k tokens per month. Just buy a VPN

My audio has background noise, watdo??
You can use voice isolator software like https://lalal.ai/ or https://vocalremover.org/

Samples

Post samples in the threads and I will try to add them to the list bellow. This is to help minimize wasting tokens trying out characters/settings that other anons already got working.
Template:
Character Name [Series]
Example: link_to_mp3
Samples: link_to_mp3
Notes: Put any notes about voice settings (stability/clarity) or specific punctuation usage.

Naked Snake / Solid Snake (David Hayter) [Metal Gear]
Example: https://vocaroo.com/16EimJNHxGJH
Samples: https://vocaroo.com/1bKjtrkZCWSO
Notes: i used 5 one minute samples for this voice Stability: 75% Clarity: 75%

Amy Rose [Sonic Adventure]
Example: https://files.catbox.moe/ybsu10.mp3
Samples: https://files.catbox.moe/89e7m9.zip
Notes: Stability: 20%, Clarity: 75%

Char Aznable (Michael Kopsa) [Gundam]
Examples: https://vocaroo.com/1bENhU8GUrJf https://vocaroo.com/134FQrTAKaCa https://vocaroo.com/1kDisLcofda3
Samples: https://voca.ro/1gAe9w3JbezL
Notes: Only 1 sample used and was converted from a youtube video. Settings vary, usually around 20%-50% for Stability and Clarity set to default mostly.

Lain Iwakura (Dub) [Serial Experiments: Lain]
Example: https://files.catbox.moe/dmsnoe.mp3
Samples: https://files.catbox.moe/g5df5u.ogg

Sean Bean
Example: https://voca.ro/1bGo3BQ7ZtrT
Sample: https://files.catbox.moe/ty1pkb.mp3
Note: Taken from the Oblivion voice lines

Dumbledore [Harry Potter]
Example: https://files.catbox.moe/ygygq2.mp3
Samples: https://files.catbox.moe/1s1o92.rar

Steve Balmer
Examples: https://files.catbox.moe/bo3fng.mp3 , https://files.catbox.moe/4uq5qb.mp3
Sample: https://files.catbox.moe/i0kjun.zip

Ivy Valentine [Soulcalibur]]
Example:https://voca.ro/1mrKwCt06AAG
Sample: https://voca.ro/1jwKac3ymdIh
Notes: Stability: 28%, Clarity: Default

Luna [Yugioh 5Ds]
Example: https://voca.ro/1jYWMueucM0P
Samples: https://files.catbox.moe/q2off9.zip
Notes: 100% Clarity to keep voice pretty much consistent. Stability can go as low as 30% without issue and allows for a good range of emotions thankfully.

Jim Dale
Example: https://files.catbox.moe/0wvoke.mp3
Samples: https://files.catbox.moe/n9j5ns.zip
Notes: Stability: 50%, Clarity: 50%

Mutahar (a.k.a SomeOrdinaryGamers)
Example: https://voca.ro/1b3YoMuOXlxN
Samples: https://files.catbox.moe/u2f37r.mp3 https://files.catbox.moe/az8goe.mp3
Notes: 30% Stability, 78% CSE

V [Cyberpunk]
Example: https://vocaroo.com/1kD3R2PXUJXN
Samples: https://vocaroo.com/14JqGdt6us07 , https://vocaroo.com/1jTS6ikeASjV , https://vocaroo.com/19KzaR8ThLID
Notes: 75% stability, 95% clarity

Patrick Bateman
Example: https://voca.ro/18EgFs6wUoVY
Samples: https://files.catbox.moe/uej8tb.zip
Notes: I got best results with high clarity/likeness and around 40% stability, but it didn't seem to be able to handle more than two sentences before going off the rails.

Etna [Disgaea]
Example: https://files.catbox.moe/v1sipw.ogg
Samples: https://files.catbox.moe/sjj6yy.mp3

Linus Tech Tips
Example: https://files.catbox.moe/2pgtx2.mp3
Sample: https://files.catbox.moe/l1hybq.mp3
Notes: Stability: 55%, Clarity: 75%

Yami Yugi
Example: https://voca.ro/12atKgGtkU8Q
Samples: https://files.catbox.moe/w1nd40.zip

Zetta and Pram [Disgaea/Makai Kingdom]
Example: https://vocaroo.com/1fYOqctd9uiZ
Samples: Zetta - https://files.catbox.moe/5n0lqi.mp3
Pram - https://files.catbox.moe/r7n5mk.mp3

David Sarif [Deus Ex]
Example: https://voca.ro/1o3uv3AunXmM
Sample: https://voca.ro/1m5QzFkHLj2k

Crestfallen Warrior [Dark Souls]
Example: https://voca.ro/15aVyT1hSLK2
Sample: https://voca.ro/1kYL53JHQ8he

John Carmack
Example: https://vocaroo.com/1oFDNIn9VAaP
Samples: https://files.catbox.moe/fv0tbg.ogg
Notes: 50% stability 100% similarity

Questing Beast
Example: https://files.catbox.moe/e63zho.mp3
Samples: https://files.catbox.moe/qnk82h.zip

Ross Scott
Example: https://voca.ro/1mafKZGf5Y30
Samples: https://files.catbox.moe/ng5ka4.7z

Benson [Regular Show]
Examples: https://vocaroo.com/17pDd85Lauvn, https://vocaroo.com/1aNFRDpR7d74
Samples: https://files.catbox.moe/4vdbro.mp3
Notes: Sliders: 29% stability, 97% clarity

Molly Blyndeff [Ephitet Erased]
Example: https://vocaroo.com/1dBWn5YeYjPP
Sample: https://voca.ro/11hLBvXEQ96o
Notes: 22% Stability, 67% Similarity

Evangelyne [Wakfu]
Examples: https://voca.ro/1hN6GDDNlPaq https://voca.ro/1hXTgYrGLSQr https://voca.ro/1mYTcMfebWpB
Sample: https://files.catbox.moe/tz7hq7.mp3

Amalia [Wakfu]
Example: https://voca.ro/1ep0x4BH6kb0
Sample: https://files.catbox.moe/jxll4e.mp3
Notes: Samples are french, the output is English

Prince Zuko [Avatar]
Example: https://voca.ro/1ehVno4F0Bj9
Sample: https://voca.ro/1nRQknmSTNWO

Tony Jay
Example: https://vocaroo.com/1eFZ8cSqmxcw
Samples: https://voca.ro/1106TcPL3NOv
Notes: Achieved with 55% stability and 85% similarity

Donald Draper [Mad Men]
Example: https://vocaroo.com/1cFrjVcWRRJt
Samples: files.catbox.moe/7t0x45.mp3

Ranni [Elden Ring]
Example: https://vocaroo.com/1n0zTCDM6wxU , https://vocaroo.com/1dQziw9DuSGY, https://vocaroo.com/19aXGGnFdlhE , https://vocaroo.com/1cnqd6qzSPSg
Samples: https://files.catbox.moe/cl28o4.mp3
Notes: Examples were made using 90%-100% stability and 100% clarity. Make sure to use old English (thou, thine, -st, etc.)

Ashley Graham [Resident Evil 4]
Examples: https://vocaroo.com/1bcHvXsgEGgf, https://vocaroo.com/1n13yLoAjz3F, https://vocaroo.com/1nJtGQ831ybZ
Samples: https://vocaroo.com/1cINTdntMJPB, https://vocaroo.com/1mBxlkqDso4h
Notes: Gave it a few attempts and picked out the best three. I hovered around 30% stability and 90% clarity.

Jenny Wakeman (XJ-9) [My Life as a Teenage Robot]
Example: https://vocaroo.com/18m7KyemTgRC
Example Variation 2 https://voca.ro/1jPNiwYPGhmr
Samples: https://files.catbox.moe/0el5hp.zip
Notes: Stability around 10%, Clarity around 80%. Parameters were tuned to deliberately give her a very shrill and "metallic" screech. Variation 2 was achieved with stability around 90%, Clarity around 80%

Jack Garland [Final Fantasy]
Example: https://vocaroo.com/1eJE0LCSW2d3
Samples: https://files.catbox.moe/cx9pjv.mp3, https://files.catbox.moe/t1sb1o.mp3
New Sample (Higher quality): https://files.catbox.moe/8csarn.mp3
Notes: The first 2 samples were pitched -4 in Audacity

Chad Warden
Example: https://files.catbox.moe/exaekh.mp3
Sample: https://files.catbox.moe/5qsleq.mp3
Notes: Unfortunately, I don't know how I tuned my sample, but I'm pretty sure the stability was around 50% and the clarity 70%
Prompt: "Xbox got nuttin on da PEE ESS QUIN TUPPLE. A'ight???? Come AWN! ...You be sayin anime shiet like Hi-Fi Rush be competin with Fo spoken? Mo like Fo smokin! GOD DAYUM! Get some real black bitches on yo dick like Frey n'stead of cracka-ass Peppa MINT. Fuggin Chai, dis aint tea time nigguh."

Spongebob
Example: https://vocaroo.com/1kWHZFnqn3YG
Samples: https://www.sounds-resource.com/playstation_2/spongebobsquarepantsbattleforbikinibottom/sound/8413/
Notes: I just used the 50 largest files in this zip because they seemed more likely to have voice lines instead of funny mouth sounds

AOC
Example: https://files.catbox.moe/54uavc.mp3
Samples: https://files.catbox.moe/yj9wey.zip
Notes: Stability: 50%, Clarity + Similarity Enhancement: 75%

Emma Watson
Example: https://vocaroo.com/1n4yDrZKPOmC
Samples: https://files.catbox.moe/4dwt7d.7z
Notes: Stability 17% and Clarity 90%

Kokichi Ouma [Danganronpa]
Example: https://files.catbox.moe/pm1str.mp3
Samples: https://files.catbox.moe/xr3vx8.zip
Notes: Stability: very low: ~10%. Clarity: ~90%.

Billy Mays
Example: https://vocaroo.com/1mGUotTBwaTS
Samples: https://files.catbox.moe/bykyyg.wav
Notes: 15% Stability, 85% CSE

NileRed
Example: https://voca.ro/19yEZvj9CyJV
Samples: https://files.catbox.moe/qnfdlc.zip
Notes: Stability works best between 40 and 50%, clarity at default

George Lucas
Example: https://vocaroo.com/18SiPVf5Y4cP
Samples: https://files.catbox.moe/na18rk.mp3, https://files.catbox.moe/qwwjh2.mp3

Senko [The Helpful Fox Senko-san]
Example: https://vocaroo.com/1jKZdYgMCUGA
Samples: https://files.catbox.moe/dhjkp9.7z

Anya Taylor Joy
Example: https://vocaroo.com/15E1PR7eD4oU , https://voca.ro/1erryS9hD8Mz
Samples: files.catbox.moe/fjw4gs.zip
Notes: ~28% Stability, ~80% CSE

G-Man - [Half Life 2]
Example: https://vocaroo.com/13IHEGRtZdRC
Samples: https://files.catbox.moe/t8oxg0.mp3
Notes: 15% Stability, 70% CSE

Adam Jensen [Deux Ex]
Example: https://vocaroo.com/1ne530pPglCq
Samples: https://files.catbox.moe/4t9qld.7z

Akiza Izinski [Yu-Gi-Oh!]
Examples: https://voca.ro/18yjxmnchXbx , https://voca.ro/19N0svrjh1Zz
Samples: https://files.catbox.moe/9fhnkt.zip

AM [I Have No Mouth And I Must Scream]
Examples: https://vocaroo.com/18D76lfXonyc , https://vocaroo.com/12DwoeFOVIOq , https://voca.ro/17fsNArQLVpK
Samples: https://files.catbox.moe/sxaek8.mp3
Notes: leave Stability around ~10-20% and Clarity to ~90%

Bulma [Dragon Ball]
Examples: https://voca.ro/1kga5g9cGGgv, https://vocaroo.com/14717XYP2gRr, https://voca.ro/1aB7s0QHqVlN
Samples: https://files.catbox.moe/5j2h0g.zip

Cave Johnson [Portal]
Example: https://vocaroo.com/16Eg6fcMrc00
Samples: https://vocaroo.com/15TYT277O3rP
Notes: Stability is at 20% and Clarity is at 90%.
Another anon's version:
Example: https://voca.ro/1jOwFqUSIbfi
Samples: https://voca.ro/1jlhP5cD1HzL
Notes: 20/90

Clementine [The Walking Dead]
Example: https://vocaroo.com/1hyWO1Av1yav
Samples: https://files.catbox.moe/d4j9s6.zip

Flonne [Disgaea]
Example: https://vocaroo.com/1hRSTB3Cmq3F
Samples https://files.catbox.moe/rh6m2a.mp3

Melina [Elden Ring]
Example: https://voca.ro/15GFeddYbT1K
Sample: https://vocaroo.com/15IPOdBZVRR8
Notes: It's 60% Stability and 92% Clarity + Similarity Enhancement

Raziel [Legacy of Kain]
Example: https://vocaroo.com/12LNK6quYGLG
Samples: https://files.catbox.moe/vudyke.mp3, https://files.catbox.moe/b3omwm.mp3
Notes: Maxed out Clarity + Similarity Enhancement and pushed stability a bit more up.

Deb [VTMB]
Example: https://vocaroo.com/19GdrrBtIGXd
Samples: https://files.catbox.moe/ztjr8w.7z

Jeanette [VTMB]
Example: https://vocaroo.com/1ib8xrtaS8o0
Samples: https://anonfiles.com/b8tbPfU4yf/Damsel_Jeanette_voicesamps_7z
Notes: Here's the 50 samples I used with Jeanette and Damsel respectively, enjoy. I have clarity set around 90 - 95% and stability set between 20 - 25%

JK Rowling
Example: https://vocaroo.com/1cd5gkuyoHE4
Samples: https://files.catbox.moe/59u2e2.7z

Jordan Peterson
Example: https://vocaroo.com/1cDm1nfSWRAH
Samples: https://files.catbox.moe/t7xxmb.mp3

Joshua Graham
Example: https://vocaroo.com/1nny3fNH6Tkq
Samples: https://files.catbox.moe/f93z5d.7z

Kokonoe Mercury [BlazBlue]
Example: https://voca.ro/1f1LufzeXmr3
Samples: https://files.catbox.moe/t4qwaf.mp3
Notes: stability : 49 clarity : 69

Kreia [KOTOR]
Example: https://vocaroo.com/1cg1I1uWj64H, https://vocaroo.com/1oRMEcuhf4At
Samples: https://files.catbox.moe/dqcw5m.zip
Notes: Settings are 40%/75%.

Kyoko Kirigiri [Danganronpa]
Example: https://voca.ro/1nWq4BkTgp2Z
Samples: https://files.catbox.moe/u1km65.zip
Notes: 90%/90% stability seems to get the best results

Mitsuru [Persona 3]
Example: https://vocaroo.com/16F63qJflc2y
Samples: https://vocaroo.com/1lTJE0UW9oNo
Notes: I just used this sample 50 times

Sae Nijima [Persona 5]
Example: https://vocaroo.com/1b855gMmLsRJ
Samples: https://vocaroo.com/1myDOS7v0rBu

Postal Dude (Rick Hunter) [Postal 4]
Example: https://vocaroo.com/122QpSVf8SzZ
Samples: https://files.catbox.moe/bcgxgd.zip
Notes: 20-50% Stability and 75% Clarity for best results.

Captain Torres [Ace Combat 7]
Example: https://vocaroo.com/1mVQx8EdnHwD
Samples: https://files.catbox.moe/yn5kgs.mp3
Notes: Due to the quality of the sample, it can be pretty liberal as far as options go.

Solo Wing Pixy [Ace Combat]
Example: https://vocaroo.com/1ldy58jF69lS
Samples: https://files.catbox.moe/z7416t.mp3

Tamamo no Mae [Fate Series]
Example - https://voca.ro/15HT5oe3lNhw
Samples: https://files.catbox.moe/zzcqp7.zip
Notes: Set Stability ~ 20% and Clarity ~80%

Ciara Horan
Example: https://vocaroo.com/1eurP2nejxeX
Samples: https://files.catbox.moe/oovgxo.mp3, https://files.catbox.moe/df0yo6.mp3
Notes set stability to 20% and leave Clarity + Similarity Enhancement to 75%

Raw Samples

This section is for raw samples that do not have an associated/confirmed output. Construct characters with these and post a working output and I will add the character to the above

Anon's Sample Mega
contains a bunch of samples of various characters. Keep in mind there is no settings or results provided, so you will have to experiment with them.
Samples: https://mega.nz/folder/AHtCyYRa#WoWv9ug6vg27XfXOjfga-Q

Facade
contains the full dialogue of Trip and Grace from Facade
Samples: https://mega.nz/folder/EzRTAbhR#mceTSBarFynsz-cL6w0ZGw

Korra
https://files.catbox.moe/xkrys7.ogg

Dragon Quest
Yangus: https://files.catbox.moe/b0gd5s.opus
Jessica: https://files.catbox.moe/3ec9tp.opus
Angelo: https://files.catbox.moe/16se0f.opus
Red: https://files.catbox.moe/1s1te7.opus
Morrie: https://files.catbox.moe/lv6e0y.opus
King Trode: https://files.catbox.moe/nkggx1.opus
Princess Medea: https://files.catbox.moe/15ppiv.opus
Dholmagus: https://files.catbox.moe/3py9mg.opus
Prince Charmles: https://files.catbox.moe/q8ejf0.opus
Don Mole: https://files.catbox.moe/hvtv3v.opus (strangely enough it worked with elevenlabs even though it's got so little voice lines)
Marcello: https://files.catbox.moe/xqegki.opus
Empyrea: https://files.catbox.moe/j2zmsl.opus
Monster Arena Announcer: https://files.catbox.moe/lw7pqd.opus

Edit
Pub: 29 Jan 2023 11:07 UTC
Edit: 02 Feb 2023 01:56 UTC
Views: 70822