Western Name: Tomi (Thomathy Chaston)
Eastern Name: トミ
Kana Pronunciation: トミ
Gender: Male
Age: 16, supposedly. (Age is adaptable and can be changed per users request.)
Release Date: June 20, 2021
Group/Team: VoiceFace
Technical Details
Voiced by: UpTown-P/Thomathy_prod
Managed by: VoiceFace



Voicebank Distribution
Tomi has a wide variety of voice databases up for download, from beginner friendly to advanced, he's perfect for newcomers to the UTAU engine as well as more advanced users who are looking for a unique sound to their original work or even song covers.
Some databases may be distributed on the VoiceFace website and not the FNer website.
All UTAU voice databases produced by UpTown-P and VoiceFace are free for download, as well as free for commercial use as long as the TOS/TOU are followed. Failure to follow Tomi's TOS/TOU will result in termination of your right to use his voice for commercial purposes
【*CORE_DATABASES (CV_JP)*】
「 CV_JP 1.0 」
A single pitch CV with end breaths, as well as a feminine and accented tone, this was the very first database recorded for Tomi.
It is encoded in Romaji, and has hiragana aliases. It can read both romaji and hiragana (CV only)
Recommended configuration settings (Resampler, wavtool, rendering options ect.)
» Engine/resampler: Moresampler
» Wavtool: Default wavtool for UTAU
» Rendering options: eoMb-100
【*CORE_DATABASES (CV_CHN)*】
「 CV_CHN 1.0 」
A single pitch CV recoded in the Chinese language.
This database was recorded with Nohkaras Chinese Rentan-style CV reclist.
Recommended configuration settings (Resampler, wavtool, rendering options ect.)
» Engine/resampler: Unknown
» Wavtool: Unknown
» Rendering options: Unknown
→ Database in production.
【*CORE_DATABASES (VCV_JP)*】
「 VCV_JP 1.0 」
A single pitch VCV with end breaths and vocal fry, as well as a androgynous and accented tone, this was the very first VCV database recorded for Tomi.
It is encoded in Romaji, and has hiragana aliases. It can only read hiragana (VCV only)
Recommended configuration settings (Resampler, wavtool, rendering options ect.)
» Engine/resampler: Moresampler & TIPS
» Wavtool: Default wavtool for UTAU
» Rendering options: eoMb-100g+4A5 (Moresampler), Y0H0B0g+4 (TIPS)
→ VCV_JP 1.0 Download (.UAR installer format)
「 VCV_JP 2.0 (Re-recording) 」~ Recommended for both newcomers and experienced users.
A basic single pitch VCV, as well as an androgynous and accented tone, this was a re-recording his Tomi's original VCV database.
It is encoded in Romaji and has hiragana aliases. It can only read hiragana (VCV only)
It also comes with an EXvoice folder with over 20+ recorded lines in over 9 different tones, totalling up to 300+ EXvoice files in total. EXvoice samples include cursing and crude humour.
This database has an additional (and optional) EXTRA's data pack that include glottal stops, end breaths, 5 breathing samples and vocal fries.
Recommended configuration settings (Resampler, wavtool, rendering options ect.)
» Engine/resampler: Moresampler & TIPS
» Wavtool: Default wavtool for UTAU
» Rendering options: eoMb-100g+4A5 (Moresampler), Y0H0B0g+4 (TIPS)
→ VCV_JP 1.0 Download
→ EXTRA's content Download
「 VCV_JP 3.0 (Alternative tone) 」
A 3 pitch VCV voice database that was recorded to be an alternative tone to the 1.0 & 2.0 VCV databases, it has a feminine vocal range with pitches recorded in E4, G4 and B4 (falsetto.) It was also made to be used by more experienced users.
It does not come with glottal stops, however it does include end breaths as well as vocal fry.
It is encoded in Romaji, and has hiragana aliases. It can only read hiragana (VCV only)
Recommended configuration settings (Resampler, wavtool, rendering options ect.)
» Engine/resampler: Unknown
» Wavtool: Unknown
» Rendering options: Y0H0B0C99g+6eo
【*CORE_DATABASES (ARPASING_ENG)*】
「 ARPASING_ENG 1.0 」
A single pitch ARPASING recorded with Kanru Hua's 2.0 ARPASING ENG reclist. It has an androgynous and accented tone, it is the original ENGLISH database for Tomi. It is recommended to be used in lower octaves.
It is encoded in ARPASING, it cannot read CVVC ENG or VCCV ENG UST's.
Recommended configuration settings (Resampler, wavtool, rendering options ect.)
» Engine/resampler: TIPS
» Wavtool: Default wavtool for UTAU
» Rendering options: Y0H0B0g+5
「 ARPASING_ENG 2.0 (Re-recording)」
A single pitch ARPASING recorded with Cadlaxa's ARPASING ENG reclist. It has an androgynous and accented tone, This is a revised version of Tomis original English database. It is recommended to be used in lower octaves.
It is encoded in ARPASING, it cannot read CVVC ENG or VCCV ENG UST's.
Recommended configuration settings (Resampler, wavtool, rendering options ect.)
» Engine/resampler: tn_fnds_PB
» Wavtool: Default wavtool for UTAU
» Rendering options: Y0H0B0C99g+8eo
→ Private distribution through Email.
【*APPEND_DATABASES (CV_JP)*】
「 SOLID_JP 1.0 」
A single pitch CV with a mature and boyish tone, it keeps a steady and bright tone through-out singing.
It is encoded in Romaji, and has Romaji aliases. It can only read Romaji (CV only)
When combined with other CV appends, the "S" prefix can be used to activate the SOLID database.
Recommended configuration settings (Resampler, wavtool, rendering options ect.)
» Engine/resampler: Moresampler
» Wavtool: Default wavtool for UTAU
» Rendering options: eoMb-100
「 FALSETTO_JP 1.0 」
A single pitch CV with a oppera like-voice, it is to be combined with other CV voicebanks. It is recommended to be combined with SOLID.
It is encoded in Romaji, and has Romaji aliases. It can only read Romaji (CV only)
When combined with other CV appends, the "F" prefix can be used to activate the FALSETTO database.
Recommended configuration settings (Resampler, wavtool, rendering options ect.)
» Engine/resampler: Moresampler
» Wavtool: Default wavtool for UTAU
» Rendering options: eoMb-100
「 DARK_JP 1.0 」
A single pitch CV with a dark and soft tone, it is recommended to be combined with other CV voicebanks.
It is encoded in Romaji, and has Romaji aliases. It can only read Romaji (CV only)
When combined with other CV appends, the "D1" prefix can be used to activate the DARK database.
Recommended configuration settings (Resampler, wavtool, rendering options ect.)
» Engine/resampler: TIPS
» Wavtool: Default wavtool for UTAU
» Rendering options: Y0H0B0
「 DEATH_JP 1.0 」
A single pitch CV with a growling and screamo-like voice, it is good for heavy metal or screamo.
It is encoded in Romaji, and has Romaji aliases. It can only read Romaji (CV only)
When combined with other CV appends, the "D" prefix can be used to activate the DEATH database.
Recommended configuration settings (Resampler, wavtool, rendering options ect.)
» Engine/resampler: tn_fnds
» Wavtool: Default wavtool for UTAU
» Rendering options: eo
「 POWER_JP 1.0 」
A three pitch CV with a powerful and sassy tone, the voice is feminine and accented.
It is encoded in Romaji, and has Romaji aliases. It can only read Romaji (CV only)
Recommended configuration settings (Resampler, wavtool, rendering options ect.)
» Engine/resampler: Moresampler
» Wavtool: Default wavtool for UTAU
» Rendering options: eoMb-100
【*APPEND_DATABASES (CV-VV_JP)*】
「 FANG_JP 1.0 」
A 3 pitch CV-VV database that has a laughing and experimental tone. The pitches recorded in are C4, E4 and G4.
It has vocal fries and end breaths, however it does not come with glottal stops.
It is encoded in Romaji, and has hiragana aliases. It can read both Romaji and Hiragana, although VV strings will only work with hiragana. (CV and VV only)
Recommended configuration settings (Resampler, wavtool, rendering options ect.)
» Engine/resampler: model4
» Wavtool: Default wavtool for UTAU
» Rendering options: Y0H0B0C99F0
【*APPEND_DATABASES (VCV_JP)*】
「 GUTTERAL_JP 1.1 」
A single pitch VCV database that is to be added to the original VCV 1.0 database. The voice has a more open-mouthed like tone and is more sing-song like compared to most other databases.
It is encoded in Romaji, and has hiragana aliases. It can only read Hiragana (VCV only)
Recommended configuration settings (Resampler, wavtool, rendering options ect.)
» Engine/resampler: Moresampler + TIPS
» Wavtool: Default wavtool for UTAU
» Rendering options: eoY0H0B0C99
「 BITE_JP 1.0 」
A 3 pitch VCV database with a SOFT C4 pitch. It has a slurred but powerful voice.
It is encoded in Romaji, and has hiragana aliases. It can only read Hiragana (VCV only)
To activate the SOFT pitch, use the "C4_S" prefix to activate the SOFT pitch. The pitch also automatically activates below F3.
Recommended configuration settings (Resampler, wavtool, rendering options ect.)
» Engine/resampler: TIPS
» Wavtool: Default wavtool for UTAU
» Rendering options: Y0H0B0C99
「 PAIN_JP 1.0 」
A 1 pitch VCV database with a screaming and growling like tone, It is to be combined with other databases to create a growling like voice. this database was configured by MoonFighter.
It is encoded in Romaji, and has hiragana aliases. It can only read Hiragana (VCV only)
When combined with other VCV appends, the "P" prefix can be used to activate the PAIN database.
Recommended configuration settings (Resampler, wavtool, rendering options ect.)
» Engine/resampler: TIPS
» Wavtool: Default wavtool for UTAU
» Rendering options: Y0H0B0C99
「 BOLD_JP 1.0 」
A 1 pitch VCV database with a short tempered and frustrated tone.
It is encoded in Romaji, and has hiragana aliases. It can only read Hiragana (VCV only)
When combined with other VCV appends, the "BL" prefix can be used to activate the BOLD database.
Recommended configuration settings (Resampler, wavtool, rendering options ect.)
» Engine/resampler: TIPS/Moresampler
» Wavtool: Default wavtool for UTAU
» Rendering options: Y0H0B0C99g+3/eoMb-100g+3
「 ITALIX_JP 1.0 」
A 2 toned VCV database, the first tone, E4, sounds shy and reserved while the other tone, G4, is poppy and cute.
It is encoded in Romaji, and has hiragana aliases. It can only read Hiragana (VCV only)
When combined with other VCV appends, the "IT" and "IT_G4" prefix can be used to activate either tones of the ITALIX database.
Recommended configuration settings (Resampler, wavtool, rendering options ect.)
» Engine/resampler: TIPS
» Wavtool: Default wavtool for UTAU
» Rendering options: Y0H0B0C99
「 GRITT_JP 1.0 」
A 1 pitched VCV database with a voice that sounds like it was gritting through the teeth.
It is encoded in Romaji, and has hiragana aliases. It can only read Hiragana (VCV only)
When combined with other VCV appends, the "GT" prefix can be used to activate the GRITT database.
Recommended configuration settings (Resampler, wavtool, rendering options ect.)
» Engine/resampler: TIPS
» Wavtool: Default wavtool for UTAU
» Rendering options: Y0H0B0C99
【*APPEND_DATABASES (CVVC_JP)*】
「 STRIKETHROUGH_JP 1.0 」
A 2 pitched CVVC database with a masculine voice, the pitches recorded are D#3 and F#3
It is encoded in Romaji, and has hiragana aliases. It can only read Hiragana (CV/CVVC only)
Recommended configuration settings (Resampler, wavtool, rendering options ect.)
» Engine/resampler: TIPS/tn_fnds_PB
» Wavtool: Default wavtool for UTAU
» Rendering options: Y0H0B0C99g+5
「 BLOODMOON_JP 1.0 」
A 3 pitched CVVC database with deep and husky tone, it is specifically designed for alternative rock and rock music genres. This database is configured by MoonFighter
It is encoded in Romaji, and has hiragana aliases. It can only read Hiragana (CV/CVVC only)
Recommended configuration settings (Resampler, wavtool, rendering options ect.)
» Engine/resampler: ?
» Wavtool: Default ?
» Rendering options: ?
【*AI_DATABASES(Diff-SVC)*】
「 Tomi_AI_LITE 」
A Diff-SVC database comprised of English and Japanese training data, It was trained using the official Diff-SVC repo as well as UtaUtaUtau's repo. The data provided is comprised of singing samples only and uses pretrained models like Opencpop and Nyaru for better stability in voice. The data model was trained at 24khz, has 40 minutes of data and 100k steps of training.
The voice is young and feminine in tone while having a higher falsetto range and a boyish lower range, it is good for music genres like metal, indie, rock and techno. The range is roughly G3 - F5
Recommended render settings
» add_noise_step : 800 or higher.
» Recommended to use gt_mel (image-to-image rendering method)
→ Sign ups are now closed, however distribution may resume after Tomi_AI_REGULAR is released.
「 Tomi_AI_REGULAR 」
A Diff-SVC database comprised of English and Japanese training data, It was trained using the official Diff-SVC repo as well as UtaUtaUtau's repo. The data provided is comprised of singing samples as well as speach samples. It uses pretrained models like Nehito, LIEE and a multilang speaker model made by lilyyy for better stability in voice and a wider range of language. The data model is currently being trained at 44.1khz, has 1h20m of data and 62ksteps of training at the time of writing.
Similar to Tomi AI LITE, the voice is young and feminine in tone while having a higher falsetto range and a boyish lower range, it is good for music genres like metal, indie, rock and techno. The range is roughly G3 - F5
Recommended render settings
» add_noise_step : ?
» Recommended rendering method: ?
→ Database in production
Terms of Use
R-18 Content Allowed? See Additional Terms of Use
Commercial Use of Voicebank Allowed? See Additional Terms of Use
Commercial Use of Character Allowed? See Additional Terms of Use
Do these terms apply to derivative characters/voices? Yes, but derivatives must be created with permission
Click here to view the terms of use for this UTAU.
Click here to view commercial license info for this UTAU.
Voice Sample(s)
Character Details
Height: 183cm
Weight: 168lbs
Tomi's origins come from a project called Friday Nighters (Verse)/FNV/FNer. He still has place in that project, however, recently he has become a part of a company called VoiceFace.
Tomi is a demon that possessed the body of a life-sized art doll, his body is made out of a canvas like material, with his joints being similar to that of a ball jointed doll.
He is very introverted and shy because of self-isolation, and can become clingy and jealous to those he is close to. Tomi deals with several mental disorders and disabilities such as anxiety and ASD.
Personality can be discarded in favour of user's personal preference. Personalities and ages of character also vary between appends (examples: Tomi FANG is a 12 year old who is chaotic and mischievous, Tomi BOLD is serious and considers himself a leader.)
He has a keen interest in music production and singing.
Tomi is often associated or paired with the following UTAUs;
Joca (FNV)
Springy (FNV)
Cotton (FNV)