Automatic Lyrics Alignment for Real Voice SynthV script HPsynthV 2023-07-21 | Hi, I've got something new for you.You give this AI program a vocal sound file and lyrics and it will convert the lyrics to phonemes and align them with the sound.Unfortunately works only for English.I added one script to convert the result to Praat's TextGrid, so it can be imported to SynthV with the Real Voice Notes from TextGrid script.Also update the Real Voice scripts! There's a new version for 1.9.0 SynthVgithub.com/hataori-p/real-voiceThe quality is not very good as if you could use it directly without any manual work, but it helps a lot. You need only align the markers better and correct the phonemes sometimes.Like the video if you want me to make an installation tutorial.How to install if you know what to do. This worked for me:git clone github.com/schufo/lyrics-aligner.gitconda create -n aligner python=3.10 numbaactivate alignerconda install pytorch==1.13.1 torchvision==0.14.1 torchaudio==0.13.1 cpuonly -c pytorchpip install pyqt5 decorator ffmpeg audioread resampy librosa pysoundfile praatioOtherwise wait for next video.Update - additional files:---Script onsets2textgrid.pyapp.box.com/s/2w3qtv4df4527ycbl7s47q5g436yg22g(save to lyrics-aligner directory)cmu_word2phonemes.pickleapp.box.com/s/b0kc24lijbnnxhtauq5umc9tcz9ct0uc(save to lyrics-aligner/files directory, then you can use --dataset-name cmu switch)---------------Phoneme level lyrics alignergithub.com/schufo/lyrics-aligner/tree/mainMusic used: Millenium by Republica (YT restricted the video, so I used only drums for the final mix)#realvoice #synthv
High Pitch Voice Conversion with Tsukuyomi-chan [tutorial] HPsynthV 2024-02-14 | This tutorial is about my new program "One Octave Up Voice Converter"github.com/hataori-p/utils?tab=readme-ov-file#foctaveexe---one-octave-up-voice-converterand about troubles you can have converting synthetic voice with SVC.Tsukuyomi-chan will tell you better than me (but don't tell her she has an "akusento" :)00:00 Intro01:09 Octave trick01:51 Doing it with SpectraLayers03:06 Free variant with One Octave Up Voice Converter03:45 How to start a command line from file explorer in Windows04:26 Praat pitch (yes, you need Praat too)06:30 Mixing07:07 ResultsI hope it will help.
【Yuu AI】音の鳴るほうへ (Oto no Naru Hou e) / SouthSoilHome 【SynthV + soVITS SVC cover】 HPsynthV 2024-02-06 | I am back after a while with a cover of a beautiful song composed by @SouthSoilHome (and kindly asking for a permission to have it here).Original song:youtu.be/Hb0nXJPxlwQGo to listen to many other songs too!!Now I finally have everything what I'v always wanted - high quality singing voice synthesizer and possibility to use any voice I want (by use of SVC).-------------Remarks:* stems were separated by Ultimate Vocal Remover 5.6 (great SW!)github.com/Anjok07/ultimatevocalremovergui(I recommend Karaoke 5 model for separation backing vocals, also can remove echo and reverb)* Spectral Layers used for cleaning/separating stems* Praat and RealVoice script were used to convert the main vocal (original AI Kiritan) to SynthVgithub.com/hataori-p/real-voice(script notesFromTextGrid)* Synthesized with Kyomachi Seika AI, params: tension -0.2, breathiness -1, gender 0.25, tone shift -200* converted by soVITS SVC 4.0github.com/voicepaw/so-vits-svc-forkto Yuu voice bank* mixed in Podium
Lyrics Alignment Installation HPsynthV 2023-07-30 | This is the promised installation video.Everything is on Github, all the instructions, commands and files.github.com/hataori-p/lyrics-alignment/tree/main/lyrics-aligner There is also a second way to install it on Github, when this goes wrong.It worked for me on Windows 10. I intentionally install it for CPU only.It is easier and it's not necessary to run it on GPU.After install if it complains some module is missing then try this:pip install name_of_the_missing_module-----------Miniconda install videoyoutu.be/oHHbsMfyNR4free relaxing music Tibetan Bowls composed by Liborio Contino-copyright-music.com/relaxing
Subscribe to Hataoris new Utau & vocal synthesis channel HPsynthV 2022-04-20 | Starting a new channel for Utau and vocal synthesis and copying stuff.Please - subscribe if you are interested!!youtube.com/channel/UCZ53seQRSi1OCuXNHMdUGfgThis HPsynthV channel stays for SynthV covers and scripting.Hataori
Anna Nyui - 「High Range Test」 暗鳴ニュイ「高音厨音域テスト」 (new synth engine test) HPsynthV 2022-04-09 | This is another test of my own synthesis engine.Voice bank is multipitch this time, pitch ranges for parts selected manually.The quality of the sound is not very good, concatenating not workingwell yet, some rumble, some heavy EQing done to get rid of that.Voice database Anna Nyui 暗鳴ニュイ VCV Raw (multipitch B3, E4, A4, C5 falsetto)aoka45.wixsite.com/annanyui/vcvPostprocessing: EQ, compressor, reverbUsing Praat phonetic program - praat.orgSong: 高音厨音域テスト High-pitched sound range testTuning & timing copied from【Tohoku Kiritan AI】High Range Test【CeVIO AIカバー】 by @2cada youtube.com/watch?v=ZuC3EfZ1qjg(except that highest part where Kiritan goes metal)original performed by 初音ミク Hatsune Mikumusic & lyrics by 木村わいPUST by Lasaillax (Ken-chan)youtu.be/cI5G0UlS2ro#utau #annanyui #highrangetest #暗鳴ニュイ
Anna Nyui - 「Melancholic」 暗鳴ニュイ「メランコリック」 (Utau cover - new synth engine test) HPsynthV 2022-04-03 | This is a first test of my own synthesis engine which works withUtau voice bank. It can also stretch consonants precisely - I need it for natural voice copying.The song has been tuned completely in SynthV with Tsuina-chan and then synthesized by the engine.It is based on a technology which Praat uses for time stretching & pitch shifting (TD PSOLA algorithm). It is actually very simple and fast and no FFT is needed for the synthesis. VB preprocessing is done by Praat script.I am using Lua for experimenting. There is still a lot of work. And the voice banks have to be top quality (sampling and otoing) - only Anna's raw bank works without manual changes.Voice database Anna Nyui 暗鳴ニュイ VCV Raw (only E4 monopitch)aoka45.wixsite.com/annanyui/vcvPostprocessing: EQ, compressor, reverbSong: メランコリック Melancholic A real voice copy (timing and pitch) from [Melancholic Cover by ENE]cover performed by ENEyoutu.be/kgHwOKi5Zlkoriginal performed by 鏡音リン Kagamine Rinmusic & lyrics by Junkynicovideo.jp/watch/sm10444862harmonies by Tsurumaki Maki AIlyrics: karaoke-lyrics.net/lyrics/vocaloid/melancholic-563815#utau #annanyui #melancholic #暗鳴ニュイ
Anna Nyui & Rikka & Tsuina 「ケイタイのウラのプリクラのピース！」 by ANNA☆S (UTAU & SynthV collab cover) HPsynthV 2022-03-25 | A real voice copy (timing, pitch & other params) Utau & SynthV cover.I like this song - there is a lot of semi-speech and shouts.I am starting with Utau. This is tuned in SynthV Studio and exported/imported to OpenUtau via Utaformatix. Then some way tuned - only as I am able.I like Anna Nyui's voice and her many sub-banks. I used a couple of them.Working on Utau Lua plugin.Software:OpenUtau v0.0.643.0Synthesizer V Studio Pro 1.5.0Real Voice scripts github.com/hataori-p/real-voiceUtaformatix project converter sdercolin.github.io/utaformatix3Voice banks:Anna Nyui 暗鳴ニュイ aoka45.wixsite.com/annanyui as AnnaKoharu Rikka AI (ver. 116) as YuunaTsuina-Chan AI (ver. 103) as SuzukaPostprocessing: EQ, compressor, reverb, de-esserSong:ケイタイのウラのプリクラのピース！Keitai no Urano Purikurano Peace!original performed by ANNA☆Snicovideo.jp/watch/sm26364628140 BPM, Eb majLyrics:ieeebd.org/lyrics/annas/%E3%82%B1%E3%82%A4%E3%82%BF%E3%82%A4%E3%81%AE%E3%82%A6%E3%83%A9%E3%81%AE%E3%83%97%E3%83%AA%E3%82%AF%E3%83%A9%E3%81%AE%E3%83%94%E3%83%BC%E3%82%B9%EF%BC%81-anna%E2%98%86s#synthv #utau #annanyui #voicecopy
SynthV Real Voice Series - in Studio Basic - using external Lua scripts HPsynthV 2022-03-11 | I have changed the essential scripts to work outside the SynthV Studio.You could now be able to use it with the free Studio Basic.There is a new Github repo:github.com/hataori-p/real-voice-basicInstallation instructions only for Windows :(PLEASE! - if someone can install it for Linux or Mac - let me knowand if possible - provide others with the intall instructions !!Voice bank used:Koharu Rikka AI (Lite)Vendor: AHS Co., Ltd.Version number: 101Free product.Source voice:さくらんぼ / 大塚 愛 」 cover by Oozyoutu.be/6lo_BQt60e4VSQx from HASUKEI (ハスKEI)youtube.com/watch?v=JR6H7SIXiwQOriginal song: Sakuranbo / さくらんぼ by Otsuka Ai / 大塚愛You can watch this video in this playlist:youtube.com/playlist?list=PLHA_yIumhQPDJ3PULhXeE-gypioT-eearSoftware needed:Synthesizer V Studio Basic Edition by Dreamtonicsdreamtonics.com/en/synthesizervScripts for SynthV Studio BasicFor installation see Github github.com/hataori-p/real-voice-basicLua script languagelua.orgPhonetic program Praatpraat.orgBug reports github.com/hataori-p/real-voice-basic/issuesDiscussions / questions github.com/hataori-p/real-voice-basic/discussions#synthv #script #realvoice #koharurikka #voicecopy #synthvstudiobasic
SynthV Real Voice Series - Notes to TextGrid - even easier with a project file (BONUS at the end) HPsynthV 2022-03-06 | Thanks for 300 subscribers!This is a demonstration video of a new script "RV Notes to TextGrid"and updated "RV Notes from TextGrid" from Real Voice Series.If you can get notes with lyrics from some project file,the sync work in Praat is way much easier.Source voice:さくらんぼ / 大塚 愛 」 cover by Oozyoutu.be/6lo_BQt60e4VSQx from HASUKEI (ハスKEI)youtube.com/watch?v=JR6H7SIXiwQOriginal song: Sakuranbo / さくらんぼ by Otsuka Ai / 大塚愛Voice banks used:Koharu Rikka AI (version 116)Tsuina-Chan AI (version 103)You can watch this video in this playlist:youtube.com/playlist?list=PLHA_yIumhQPDJ3PULhXeE-gypioT-eearSoftware needed:RV Notes to TextGrid:github.com/hataori-p/real-voice/blob/main/notesToTextGrid.luaRV Notes from TextGrid (ver.2)github.com/hataori-p/real-voice/blob/main/notesFromTextGrid.luaScripts for SynthV Studio Pro (working only in Pro)For installation see Github github.com/hataori-p/real-voicePhonetic program Praatpraat.orgBug reports github.com/hataori-p/real-voice/issuesDiscussions / questions github.com/hataori-p/real-voice/discussions#synthv #script #realvoice #koharurikka #voicecopy
SynthV AI All Stars 「Don Fiction ドンフィクション」 by Tokimeki♡Sendenbu とき宣 (SynthV cover, params tracking) HPsynthV 2022-02-23 | A real voice copy (timing, pitch & other params) cover.Tried to automatically track params - tension, tone shift, gender & loudness.It's quite complicated, can't make it with a simple script.The principle is to compare the vowel spectrum of the note with synthetic vowels pre-generated with different parameters - about 60k combinations (30 pitches, 6 vowels, 7 tensions, 7 genders, 7 tone shifts). Used Praat's MFCC coefficients for comparing the spectra and determination of the loudness difference.I wanted a song with about 5 singers singing separately to assign different AI voice banks to them and compare how will they resemble the originals.If you know the song or the group tell me in the comments which one is the most similar.Synthesizer V Studio Pro 1.5.0Voice banks:Kyomachi Seika AI (ver. 102)Tsuina-Chan AI (ver. 103)Tsurumaki Maki AI (ver. 107)Koharu Rikka AI (ver. 116)Saki AI (version 118)Postprocessing: EQ, compressor, reverb, de-esserSong: ドンフィクション Don Fictionoriginal performed by ときめき♡宣伝部 Tokimeki♡Sendenbuyoutube.com/watch?v=ReZFG5bSiRA155 BPM, Ab majReal Voice SVP by Hataori@HPsynthV (please credit me if you want)app.box.com/s/6rljt4hl2tmiysi7z752846ep95onby8Lyricsmyjpop.jspinyin.net/lyrics-%E3%81%A8%E3%81%8D%E3%82%81%E3%81%8D%E2%99%A1%E5%AE%A3%E4%BC%9D%E9%83%A8-tokimeki%E2%99%A1sendenbu-%E3%83%89%E3%83%B3%E3%83%95%E3%82%A3%E3%82%AF%E3%82%B7%E3%83%A7%E3%83%B3-don-fiction#synthv #ときめき宣伝部 #voicecopy
Kyomachi Seika AI 「Koi wa Sensou」 Love is War 京町セイカ AI 「恋は戦争」 (SynthV cover + SVP) HPsynthV 2022-02-14 | A real voice copy (timing and pitch) of FyeI used the new RV Growl script (maybe too much)Script: github.com/hataori-p/real-voice/blob/main/growl.luaVideo is partially blocked - here is a MP3 file for listeningapp.box.com/s/tijd1p0d6i94isf9tspxj3k0d7ho3rxj SVP + instrumental app.box.com/s/3ez8ceu2czxknp5asaod0g2s4v04macgSynthesizer V Studio Pro 1.5.0Voice banks Kyomachi Seika AI (version 102), Saki AI (version 118)VB parameters:Seikatension: 0 / 0.800breathiness -0.598gender -0.320tone shift: -300Saki (harmonies)tension: 0.800breathiness -0.560gender 0.240tone shift: 314Postprocessing: EQ, compressor, reverb, de-esser, Clone Ensemble v4.2Song: 恋は戦争 Koi wa Sensou (Love is War)voice source cover performed by Fyeyoutu.be/2aUncIe3nE8original performed by 初音ミク Hatsune Mikumusic & lyrics by ryo (supercell)Real Voice SVP by Hataori@HPsynthV (please credit me if you want)app.box.com/s/3ez8ceu2czxknp5asaod0g2s4v04macgLyricslyricsfreak.com/h/hatsune+miku/love+is+war_20905392.html(there are some mistakes in the covers - Fye's & this too)#synthv #seika #loveiswar
SynthV Real Voice Series - Growl / Scream Script featuring Kyomachi Seika 京町セイカ HPsynthV 2022-02-10 | Inspired by a growl in Rishie-P's latest videoI tried to create a growling script for SynthV.This is a demonstration video of the script.Tuning is from Rishie-P (only part for demo)Rishie-P - Kocchi Muite Baby coveryoutu.be/AGleu_5GFy8UST from Yura Crossmansoundcloud.com/yura-crossman/kocchi-muite-babyVoice banks used:Kyomachi Seika AI 京町セイカGenbu - liteYou can watch this video in this playlist:youtube.com/playlist?list=PLHA_yIumhQPDJ3PULhXeE-gypioT-eearSoftware needed:RV Growl script:github.com/hataori-p/real-voice/blob/main/growl.luaScript for SynthV Studio Pro (working only in Pro)For installation see Github github.com/hataori-p/real-voiceBug reports github.com/hataori-p/real-voice/issuesDiscussions / questions github.com/hataori-p/real-voice/discussions#synthv #script #kyomachiseika #京町セイカ
SynthV Real Voice Series - New Easier Method 2 - Consonants HPsynthV 2022-01-31 | THANK YOU for 200 subscribers !!The 2nd part of the new method.You don't need anything new for this - only scripts as in the last video.This time I used Maki ENG speech for demonstration.In short - add additional markers for consonants and label it by ! exclamation mark.You can watch this video in this playlist:youtube.com/playlist?list=PLHA_yIumhQPDJ3PULhXeE-gypioT-eearSoftware needed:Scripts for SynthV Studio Pro (working only in Pro)For installation see Github github.com/hataori-p/real-voice(please update, new scripts & versions)Bug reports github.com/hataori-p/real-voice/issuesDiscussions / questions github.com/hataori-p/real-voice/discussionsPhonetic program Praat (multiplatform)praat.orgYou will also need some clean voice track without instruments.There is some online & offline software - search for "stem separation".Online:lalal.aisplitter.aiOffline:github.com/tsurumeso/vocal-remover#synthv #voicecopy #praatprogram
SynthV Real Voice Series - New Easier Method 1 - Labeling in Praat HPsynthV 2022-01-17 | First of all - THANK YOU for 100 subscribers !!This video is a new - I think more straightforward and perhaps easierway to do the voice copy from real voice to synth voice.Although I use Japanese it should be language independent.You have to know the phonetics of your language used.The rule of thumb is to mark starts of vocals and pauses and label the vocalsby whatever you would write as lyrics in SynthV.There is also an option to deal with consonants - wait for another video.I hope someone will try it. If so - let me know!You can watch this video in this playlist:youtube.com/playlist?list=PLHA_yIumhQPDJ3PULhXeE-gypioT-eearSoftware needed:Scripts for SynthV Studio Pro (working only in Pro)For installation see Github github.com/hataori-p/real-voice(please update, new scripts & versions)Bug reports github.com/hataori-p/real-voice/issuesDiscussions / questions github.com/hataori-p/real-voice/discussionsPhonetic program Praat (multiplatform)praat.orgYou will also need some clean voice track without instruments.There is some online & offline software - search for "stem separation".Online:lalal.aisplitter.aiOffline:github.com/tsurumeso/vocal-remover#synthv #voicecopy #praatprogram
Saki AI - Kassai - Applause (Hirauchi Maya voice copy) サキAI 「喝采」（平内真矢のボイスコピー）SynthV cover HPsynthV 2022-01-17 | A voice copy (timing and pitch) of Hirauchi Maya's voice to Saki's voice.Another enka style song from another ASH (Actor's School Hiroshima) graduate - Hirauchi Maya (now aka Hima).12 yo in the video, qualified in Singing King 2016 contest with Chiaki Naomi's song.Song range E3 - Db5 is quite low. I like her deep voice.Please, check up her channel! youtube.com/c/hima0113channelSynthesizer V Studio Pro 1.4.1Voice database: Saki AI ver.115Postprocessing: EQ, compressor, reverb, deesserSong: 「喝采」 (Kassai - Applause)Original Artist: ちあきなおみ Chiaki NaomiCover Artist: 平内真矢 Hirauchi Maya (陽真 Hima)Voice from: youtu.be/61ChdKm-udgOfficial web: hima-music.comYT: youtube.com/c/hima0113channelYT playlist: youtube.com/playlist?list=PLsu4gBgyEZ0bEsPgT04_P5l13yZayE8hKLyrics:lyricsondemand.com/c/chiakinaomilyrics/kassailyrics.html#synthv #sakiAI #平内真矢 #陽真 #enka
Tsuina-Chan AI 「Anata no Utahime」 Your Diva ついなちゃん AI 「あなたの歌姫」 (SynthV cover + SVP) HPsynthV 2022-01-14 | A real voice copy (timing and pitch) of Saya Scarlet's voiceSynthesizer V Studio Pro 1.5.0Voice database Tsuina-Chan AI (version 103)ah-soft.com/synth-v/tsuina/index.htmlVB parameters:tension 0.095breathiness 0.085gender -0.060Postprocessing: EQ, compressor, reverb, deesserSong: あなたの歌姫 Anata no Utahime (Your Diva)voice source cover performed by Saya Scarletyoutu.be/dICIQyc-CHcoriginal performed by 初音ミク Hatsune Mikumusic & lyrics by azuma aka Boku-P ボクPvsqx by Hatsune Danyoutube.com/watch?v=LWYX-Xj7cvE(link in comments)Real Voice SVP with Pitch Deviation by Hataori@HPsynthV (please credit me if you want)app.box.com/s/szumjomngsby0jtf94y7l9ck29eyqyzqLyricsvocaloidlyrics.fandom.com/wiki/%E3%81%82%E3%81%AA%E3%81%9F%E3%81%AE%E6%AD%8C%E5%A7%AB_(Anata_no_Utahime)#synthv #tsuinachan #あなたの歌姫
Speech Test SynthV AI - Saki, Maki, Rikka, Tsuina + bonus HPsynthV 2022-01-10 | Test of a real voice copy (timing and pitch) of a speech part (phone call) from Berryz Koubou song Maji Good Chance Summerperformed by Shimakura Rika from BeyooooondsDifferent SynthV AI voice banks + bonusWho do you like the most?No synthesizer can keep up with Rika sama, I had to omit some syllablesSynthesizer V Studio Pro 1.5.0Voice databases: Koharu Rikka AI ver.116, Tsurumaki Maki AI (JPN) (version 107), Tsuina-Chan AI (version 103), Saki AI (version 118),GENBU (Lite) Animen JP (version 100)Song: Maji Good Chance Summer マジ グッドチャンス サマー (speech part)performed by 島倉りか Shimakura Rika (member of BEYOOOOONDS ビヨーンズ)Original artist: Berryz工房 Berryz Koubouyoutu.be/Plpq0H5wYSM (live)Lyrics: uta-net.com/song/68464#synthv #voicecopy #ついなちゃん #弦巻マキ #小春六花 #サキちゃん
Saki AI - Arekara (Misora Hibari AI voice copy) サキAI 「あれから」（美空ひばり[AI歌唱]のボイスコピー） HPsynthV 2022-01-06 | An AI voice copy (timing and pitch) of Misora Hibari's AI voice to Saki's voiceI could not resist adding a choir of all my singersThe backing vocals are autotuned by SynthV Studio, timing is randomized by my new scriptgithub.com/hataori-p/real-voice/blob/main/randomizeOnsets.luaSVP project available app.box.com/s/qmcckaa7fkdatimpi14s4khqfs11ziuoSynthesizer V Studio Pro 1.4.1Voice database: Saki AI ver.115Choir: Tsurumaki Maki AI, Genbu (Lite), Koharu Rikka AI, Tsuina chan AIPostprocessing: EQ, compressor, reverb, deesserSong: 「あれから」 (Arekara - Since Then)Sound from: youtu.be/y4I_s74V2w4Video from: youtu.be/ZKl9Rqi9xMIArtist: 美空ひばり Misora Hibari (died 1989, VOCALOID:AI recreation of her singing voice, performed 2019 on NHK with her 3D rendering)Lyrics:myjpop.jspinyin.net/lyrics-%E7%BE%8E%E7%A9%BA%E3%81%B2%E3%81%B0%E3%82%8A-ai%E6%AD%8C%E5%94%B1-%E3%81%82%E3%82%8C%E3%81%8B%E3%82%89-nhk%E3%82%B9%E3%83%9A%E3%82%B7%E3%83%A3%E3%83%AB%E3%83%BB%E3%83%90%E3%83%BC%E3%82%B875 BPM, Dbmaj#synthv #sakiAI #美空ひばり #enka
Tsuina-Chan AI - 「Iroha Uta」 ついなちゃん AI 「いろは唄」 (SynthV cover) HPsynthV 2021-12-30 | A real voice copy (timing and pitch) from [いろは唄 cover by yuki]Synthesizer V Studio Pro 1.5.0Voice database Tsuina-Chan AI (version 103)ah-soft.com/synth-v/tsuina/index.htmlPostprocessing: EQ, compressor, reverb, delay, deesserTsuina-Chan synthv.fandom.com/wiki/Tsuina-chanSong: いろは唄 Iroha Utacover performed by yukiyoutu.be/i8IisPSzO8Qoriginal performed by 鏡音リン Kagamine Rinmusic & lyrics by Ginsakunicovideo.jp/watch/sm6115924harmonies by Saki AIlyrics: vocaloidlyrics.fandom.com/wiki/%E3%81%84%E3%82%8D%E3%81%AF%E5%94%84_(Iroha_Uta)#synthv #tsuinachan #いろは唄
SynthV Real Voice Series - chapter II - Real Voice Tuning - part 4 HPsynthV 2021-12-28 | This is a second part (chapter) of the promised demo how to do a voice copy in Synth V.(I'm sorry for so many parts - I can upload only 15 min videos)You can watch it in this playlist:youtube.com/playlist?list=PLHA_yIumhQPDJ3PULhXeE-gypioT-eearBug reports github.com/hataori-p/real-voice/issuesDiscussions / questions github.com/hataori-p/real-voice/discussionsSoftware needed:Scripts for SynthV Studio Pro (working only in Pro)For installation see Github github.com/hataori-p/real-voicePhonetic program Praatpraat.orgYou will also need some clean voice track without instruments.There is some online & offline software - search for "stem separation".Online:lalal.aisplitter.aiOffline:github.com/tsurumeso/vocal-remover#synthv #voicecopy
SynthV Real Voice Series - chapter II - Real Voice Tuning - part 3 HPsynthV 2021-12-28 | This is a second part (chapter) of the promised demo how to do a voice copy in Synth V.(I'm sorry for so many parts - I can upload only 15 min videos)You can watch it in this playlist:youtube.com/playlist?list=PLHA_yIumhQPDJ3PULhXeE-gypioT-eearBug reports github.com/hataori-p/real-voice/issuesDiscussions / questions github.com/hataori-p/real-voice/discussionsSoftware needed:Scripts for SynthV Studio Pro (working only in Pro)For installation see Github github.com/hataori-p/real-voicePhonetic program Praatpraat.orgYou will also need some clean voice track without instruments.There is some online & offline software - search for "stem separation".Online:lalal.aisplitter.aiOffline:github.com/tsurumeso/vocal-remover#synthv #voicecopy
SynthV Real Voice Series - chapter II - Real Voice Tuning - part 2 HPsynthV 2021-12-28 | This is a second part (chapter) of the promised demo how to do a voice copy in Synth V.(I'm sorry for so many parts - I can upload only 15 min videos)You can watch it in this playlist:youtube.com/playlist?list=PLHA_yIumhQPDJ3PULhXeE-gypioT-eearBug reports github.com/hataori-p/real-voice/issuesDiscussions / questions github.com/hataori-p/real-voice/discussionsSoftware needed:Scripts for SynthV Studio Pro (working only in Pro)For installation see Github github.com/hataori-p/real-voicePhonetic program Praatpraat.orgYou will also need some clean voice track without instruments.There is some online & offline software - search for "stem separation".Online:lalal.aisplitter.aiOffline:github.com/tsurumeso/vocal-remover#synthv #voicecopy
SynthV Real Voice Series - chapter II - Real Voice Tuning - part 1 HPsynthV 2021-12-28 | This is a second part (chapter) of the promised demo how to do a voice copy in Synth V.(I'm sorry for so many parts - I can upload only 15 min videos)You can watch it in this playlist:youtube.com/playlist?list=PLHA_yIumhQPDJ3PULhXeE-gypioT-eearBug reports github.com/hataori-p/real-voice/issuesDiscussions / questions github.com/hataori-p/real-voice/discussionsSoftware needed:Scripts for SynthV Studio Pro (working only in Pro)For installation see Github github.com/hataori-p/real-voicePhonetic program Praatpraat.orgYou will also need some clean voice track without instruments.There is some online & offline software - search for "stem separation".Online:lalal.aisplitter.aiOffline:github.com/tsurumeso/vocal-remover#synthv #voicecopy
SynthV Real Voice Series - chapter I - Project Preparation HPsynthV 2021-12-28 | This is a first part of the promised demo how to do a voice copy in Synth V.You can skip this chapter to the second one, which is more interesting and come back if you decide to try it.Skip to youtube.com/watch?v=kAF0oj_4RnEYou can watch it in this playlist:youtube.com/playlist?list=PLHA_yIumhQPDJ3PULhXeE-gypioT-eearBug reports github.com/hataori-p/real-voice/issuesDiscussions / questions github.com/hataori-p/real-voice/discussionsSoftware needed:Scripts for SynthV Studio Pro (working only in Pro)For installation see Github github.com/hataori-p/real-voicePhonetic program Praatpraat.orgYou will also need some clean voice track without instruments.There is some online & offline software - search for "stem separation".Online:lalal.aisplitter.aiOffline:github.com/tsurumeso/vocal-remover#synthv #voicecopy
Saki AI - Look at the stars in the sky (Dambara Ruru voice copy) サキAI 「見上げてごらん夜の星を」（段原瑠々のボイスコピー） HPsynthV 2021-12-22 | A real voice copy (timing and pitch) of Dambara Ruru (Juice=Juice) to Saki's voice.I think that Saki is a little underrated and Ruru is a utahime 歌姫 (no wonder, she's from Actor's School Hiroshima).There's no official picture of Saki, so I made very stylized "deepfake" video from original Ruru by AnimeGANv2 neural net.SW:AnimeGANv2: github.com/TachibanaYoshino/AnimeGANv2Synthesizer V Studio Pro 1.4.1Voice database: Saki AI ver.115Postprocessing: EQ, compressor, reverb, deesserSong: 「見上げてごらん夜の星を」 (Look at the stars in the sky) from Juice=Juice channelyoutu.be/D7P4lA8RIb8Artist: 段原瑠々 Dambara Ruru (original artist 坂本九 Sakamoto Kyuu)Lyrics:lyricstranslate.com/en/%E8%A6%8B%E4%B8%8A%E3%81%92%E3%81%A6%E3%81%94%E3%82%89%E3%82%93%E5%A4%9C%E3%81%AE%E6%98%9F%E3%82%92miagetegoran-yorunohoshiwo-look-stars-sky.html(there are different translations to English around, this one is by Norio Shimizu, native Japanese with fluent English)#synthv #sakiAI #段原瑠々
Tsuina Chan AI + Tsurumaki Maki AI 「PoPiPo ぽっぴっぽー」 (Synth V Cover) HPsynthV 2021-12-18 | This is not a real voice copy.I used UST from Ken-chan, converted to musicxml and synthesized with Neutrino AI Kiritan.Then took lengths of phonemes from Neutrino .lab file and changed lengths of notesin synthV. Then used synthV's Auto Pitch Tuning, also remade the English part for Makiand tuned some parts manually.I wanted to have phoneme lengths also tuned by AI. But it's too complicated.Synthesizer V Studio Pro 1.4.1Voice databases: Tsuina-Chan AI (version 100), Tsurumaki Maki AI (ENG) (version 102)Postprocessing: EQ, compressor, reverb, chorus, delaySong: PoPiPo ぽっぴっぽーOriginal by Lamaze-P feat. Hatsune Miku ラマーズP feat. 初音ミク youtu.be/ikgQhG4AlVkUST: Ken-chan (Lasaillax) youtu.be/ijcXOON90fM (THANK YOU!!)popipo.musicxml converted by python program from UST app.box.com/s/ibbjuzzhipfuv7764f7x0hqejo6vhwua#synthv #ついなちゃん #弦巻マキ
Tsuina Chan AI + Tsurumaki Maki AI 「Colorful x Melody カラフル×メロディ - short」 (Synth V Cover) HPsynthV 2021-12-08 | A real voice copy from 朝霞しお＆天秤ひなみ cover(only first 1:29)Synthesizer V Studio Pro 1.4.0Voice databases: Tsuina-Chan AI (version 100), Tsurumaki Maki AI (JPN) (version 105)Postprocessing: EQ, compressor, reverbSong: カラフル×メロディ Colorful x MelodyOriginal by Hatsune Miku & Kagamine Rin youtu.be/bmUyiSkz7d4Source of voices: Cover by朝霞しお＆天秤ひなみ youtu.be/I1p7f4Ckmtw#synthv #ついなちゃん #弦巻マキ
Koharu Rikka AI - Mirai e (Kudou Yume voice & motion copy) 小春六花AI 「未来へ」（工藤由愛のボイスとモーションコピー） HPsynthV 2021-12-02 | A real voice copy (timing and pitch) of Kudou Yume (Juice=Juice) to Rikka's voice.I tried different AI voices, only Rikka and Saki were able to sing it right. Chose Rikka for her voice color.Animation of Rikka generated by neural network (RESRGAN) from one picture, motions transfered by another AI from Yume's orignal video.(poor quality)This is how Rikka could look in real life. :)Here is 1600x1600 hi res picture of Rikka IRL (public domain):app.box.com/s/iicllriqhz1cirpp3fvfyfj8ej4zjzd1SW:Real-ESRGAN github.com/xinntao/Real-ESRGANFirst Order Model (motion transfer) github.com/AliaksandrSiarohin/first-order-modelSynthesizer V Studio Pro 1.4.0Voice database Koharu Rikka AI ver.109 JapanesePostprocessing: EQ, compressor, reverbSong: 「未来へ」 Mirai e (To the Future) from Juice=Juice channelyoutu.be/5tbThKxArywFmaj, 76 BPMArtist: 工藤由愛 Kudou Yume (original artist Kiroro bilibili.com/video/BV1ov411p7nj)Lyrics: lyricstranslate.com/en/mirai-future.html#synthv #小春六花 #KoharuRikka
GENBU (Lite) - 「家庭の事情 Family Matters by ZORN」 (rap, SynthV partial cover) HPsynthV 2021-11-29 | A real voice copy (timing and pitch)I wanted to try a male rap.There was a discussion at VI CONTROL forumvi-control.net/community/threads/synthesizer-v-vocaloid-haters-might-want-to-check-this.115973/page-6#post-4980399The quality is bad, it is a lite voice bank. I didn't bother much with loudness.I had to transpose it 1 tone up to get in Genbu's vocal range.It is better when transposed back down one tone into original scale, but formatns are shifted (MP3 to listen):app.box.com/s/lq5yx22xza9iht2iypohck95guekvpyfIf someone is interested in trying it with GENBU full, here is the project file and instrumental:app.box.com/s/v69fmw0hls38svkd12une3s1wfem9qu8I would be glad to hear it.Synthesizer V Studio Pro 1.4.0Voice database GENBU (Lite) (version 100)Postprocessing: EQ, compressor, reverb, flanger, delaySong: ZORN / 家庭の事情 (katei no jijō, Family Matters)only 3rd verse and final chorusyoutu.be/Sql6hLQCAXUstart time 2:33#synthv #genbu #zorc
Tsuina-Chan AI - 「Melancholic」 ついなちゃん AI 「メランコリック」 (SynthV cover) HPsynthV 2021-11-26 | A real voice copy (timing and pitch) from [Melancholic Cover by ENE]Synthesizer V Studio Pro 1.4.0Voice database Tsuina-Chan AI (version 100)ah-soft.com/synth-v/tsuina/index.htmlPostprocessing: EQ, compressor, reverbTsuina-Chan synthv.fandom.com/wiki/Tsuina-chanSong: メランコリック Melancholic cover performed by ENEyoutu.be/kgHwOKi5Zlkoriginal performed by 鏡音リン Kagamine Rinmusic & lyrics by Junkynicovideo.jp/watch/sm10444862harmonies by Tsurumaki Maki AIlyrics: karaoke-lyrics.net/lyrics/vocaloid/melancholic-563815#synthv #tsuinachan #melancholic
Tsurumaki Maki 【Ashita sekai ga owaru to shite / by Ni-na】 (SynthV cover) 弦巻マキ 【明日世界が終わるとして・ニーナ】 HPsynthV 2021-11-16 | A real voice copy cover (timing and pitch) of Ni-na's original song to Maki's voice.This is my most favorite song from Ni-na.Synthesizer V Studio Pro 1.3.0Voice databases: Tsurumaki Maki AI (JPN) (version 104)Postprocessing: EQ, compressor, reverbSong: 明日世界が終わるとして (Ashita sekai ga owaru to shite, As the world ends tomorrow) by ニーナ (Ni-na)youtu.be/3ASfSZ6B4mQOriginal artist: ニーナ Ni-nasinger & song writerYoutube Channel: youtube.com/channel/UCEZ5Owd9ke6zjBgQpk_dZOwTwitter @nachippootwitter.com/nachippooOther social network summary site:https://lit.link/nachippoo#synthv #弦巻マキ #ニーナ
Saki AI - 「Boku no Migi Te」「僕の右手」「나의 오른손」 / Paran Maum (SynthV cover) HPsynthV 2021-11-12 | A real voice copy (timing and pitch) of Doona Bae to Saki AI.Synthesizer V Studio Pro 1.3.0Voice database Saki AI (version 110)Postprocessing: EQ, compressorSong: 僕の右手 (Boku No Migi Te - My Right Hand) performed by Paran Maum (orig. Blue Hearts)from EP We Are Paranmaum (2005) youtu.be/gjaiDXCjtu4Lyrics Video from movie Linda Linda Lindayoutu.be/1FfNKySqL9ESinger: Doona Bae 두나넷http://www.doona.net#synthv #SakiAI #ParanMaum
Koharu Rikka AI + Tsurumaki Maki AI 「GIRL ZONE - Rap Part」 by 雨ノ森 川海 (Synth V Cover) HPsynthV 2021-11-09 | A real voice copy (timing and pitch) of 雨ノ森 川海's song to Rikka's and Maki's voices.I was interested in how the rapping will go.Synthesizer V Studio Pro 1.3.0Voice databases: Koharu Rikka AI ver.100 Japanese, Tsurumaki Maki AI (JPN) (version 104)Postprocessing: EQ, compressor, reverb, delaySong: Girl Zone (rap part) by 雨ノ森 川海 Ame no Mori Kawa Umi (subgroup of BEYOOOOONDS ビヨーンズ)youtu.be/TTagXI2EPyo (rap part)youtu.be/kR0zkyEJBys (live)Lyrics: cafekica.blogspot.com/2019/08/ame-no-mori-kawa-umi-girl-zone-color.html#synthv #小春六花 #弦巻マキ
Koharu Rikka AI - Vitamin ME / BEYOOOOONDS (cover) 小春六花AI 「ビタミンME」BEYOOOOONDS（カバー） HPsynthV 2021-10-25 | A real voices copy (timing and pitch) of BEYOOOOONDS' song (part) to Rikka's voice.There is an expressive speech in the song - interesting for synthesis.Synthesizer V Studio Pro 1.3.0Voice database Koharu Rikka AI ver.100 JapaneseBacking vocals: Tsurumaki Maki AI (JPN Lite) (version 101), Saki AI (Lite) (version 101)Postprocessing: EQ, compressor, reverb, CloneEnsembleV42 for the shoutsSong: ビタミンME Vitamin ME (first part) from ビヨーンズ BEYOOOOONDS channelyoutu.be/YhJHUxQtnkM#synthv #小春六花 #synthesizerv
Koharu Rikka AI - Hatsukoi Cider (Yofuu Runo voice copy) 小春六花AI 「初恋サイダー」（豫風瑠乃のボイスコピー） HPsynthV 2021-10-22 | A real voice copy (timing and pitch) of Yofuu Runo (Tsubaki Factory) to Rikka's voice.Synthesizer V Studio Pro 1.3.0Voice database Koharu Rikka AI ver.100 JapanesePostprocessing: EQ, compressor, reverbSong: 初恋サイダー Hatsukoi Cider (short ver) from Tsubaki Factory channelyoutu.be/bYqlYSo0wWkArtist: 豫風瑠乃 Yofuu Runo (original artist Buono! youtu.be/JmTA0mPjnwE)#synthv #小春六花 #synthesizerv
Koharu Rikka AI - Hikkosenai Kimochi (Oda Sakura voice copy) 小春六花AI「引越せない気持ち」（小田さくらのボイスコピー） HPsynthV 2021-10-18 | I tried to copy a real voice (timing and pitch) of Oda Sakura from Morning Musume to Rikka's voice.This song also has many dynamics changes, so I tried to use some tension control.Synthesizer V Studio Pro 1.3.0Voice database Koharu Rikka AI ver.100 JapanesePostprocessing: EQ, compressor, reverbSong: 引越せない気持ち Hikkosenai Kimochi from live Hello!Project Solo Fest 2020youtu.be/a0T8Tc3zOW0Artist: 小田さくら Oda Sakura, Morning Musume '20 (original artist 松浦亜弥 Matsuura Aya)#synthv #小春六花 #synthesizerv
