67 MUSIC is the music studio inside Shela. You write one sentence, the way you would text a friend. About half a minute later the song is finished: written, performed, mastered, with a title and a cover, in your library and ready to share.
Want an artist to release it under? Say so and Shela invents the whole person, gives them a face and puts them on their own page. Want none of that and just music for yourself, for your set, for your clients? That works too.
No forms, no sliders, no genre wizard. You say what you want; anything you leave out, Shela decides and tells you what she decided.
Hey Shela, make me a new persona: Tiago Vela, from Lisbon, Portugal, he plays Latin tech house. Generate his profile picture, set everything up, and make me two viral TikTok tracks at 126 BPM.
Done. Tiago Vela, 29, Portuguese, from Lisbon, living between Lisbon and Ibiza. Tanned, cropped dark hair, trimmed beard, white linen, a thin gold chain. Warm baritone, 122 do 126 BPM, dry congas up front, never a supersaw.
His portrait, bio and profile are up, and both tracks are mastered: Sal na Pele, hook at 0:12, and Madrugada for the end of a set. If the name or the look is off, say the word and I'll change it.
One sentence in. An artist with a face, a home town and two finished songs out.
Hey Shela, I'm a producer. Give me three ideas for my next release, pop and K-pop, write the hooks and the full lyrics, then render the strongest one at 100 BPM with a female vocal.
Three ideas with full lyrics: Ghost In My Playlist (pop), Neon Hangul (K-pop) and Say Less (pop-R&B), each with the hook inside the first 15 seconds.
The first one is rendered: 100 BPM, female vocal, 2:58, mastered, cover made, in your library. Want the other two as well?
No artist, no persona, no forms. Plenty of people use 67 MUSIC purely for their own production, in any style.
Hey Shela, a two-minute intro for my set tonight: 126 BPM, E minor, sung hook, dry congas, and give me a version without the vocal too.
Both are done: 2:04, 126 BPM, E minor, sung hook at 0:48, mastered to −14 LUFS. The instrumental is the same length and the same master, so either one drops into the set. WAV and MP3 are in your library.
Want it a key lower or thirty seconds longer? Or open it in Wave and rebuild it yourself.
Your production, your rules. Nothing leaves your library until you publish it.
If you asked for an artist, she invents the person: name, country and city, age, look, voice, the rules their sound must always follow, the channels and the label. A portrait comes with it. If you only want a song, she skips this.
One feeling per song. A chorus you can sing in one breath. One image per line, a concrete detail as proof. You read them in the chat and say yes, or ask for changes. This is the one thing you do.
Lyrics and sound rules become a composition plan: sections, styles, where the chorus lands, where the hook has to hit. It is performed and rendered in studio quality (44.1 kHz WAV). A title and cover art are made with it. A full three-minute song takes about 25 seconds, mastering included.
Two passes to −14 LUFS with true peaks under −1.5 dBTP, the level streaming services expect, dynamics kept. Every song gets a measured profile: tempo, key, loudness.
The song lands in your library and, if there is one, on the artist's page. Share links open and play. Publish it and it joins the public chart. Download WAV or MP3 whenever you like, or send it straight into Wave or Video.
67 MUSIC has two layers. At the core is a music model that writes and performs complete arrangements with sung vocals. On top sits Shela's own production method: the lyrics, the plan, the mastering, the artist, the release. The model makes the sound; the method makes it a song; the licence is what lets us hand it to you.
Trained on licensed data only, not a catalogue scraped off the internet. Songs made on paid plans are yours to use, including commercially.
A full arrangement, played and sung, rendered at 44.1 kHz WAV, with vocals or purely instrumental. It can move from one genre to another inside a single song, hold fast rap and dense lyrics, and place sound effects inside the arrangement.
Intro, verse, chorus, bridge: up to 30 sections, each with its own lyrics, styles and inline directions such as a guitar solo or a whispered line. That is what lets Shela plan the song before a single note is rendered.
English, Spanish, French, German, Japanese and many more: the vocal follows the language of the lyrics you approve. Our own releases are sung in Serbian. Ask for one singer or two in harmony, for a whisper or a belted chorus.
Genre, mood, instrumentation, tempo and production era. Bone-dry drums, plate reverb, a belted chorus, two singers harmonising in C, "the lyrics start at 15 seconds". BPM and key are held precisely enough to layer the result with your own material.
Pick one part of a finished song and have just that part written and performed again, or extend it, or condition a new song on a 30-second slice of an old one. Uploaded audio steers the feel, the groove and the palette without copying the notes.
Songs you make on a paid plan are yours to use, including commercially: online, in advertising, on social media and in podcasts. Film, television and game studios are the exception for now, ask us about those. Every upload and every reference is screened for copyright before anything is made, and prompts naming real artists are rewritten into descriptive styles.
The music is made by AI. Nothing is recorded live, no session musician stands in a room. Because it is a model, a similar song can be produced for someone else, so we do not promise yours is one of a kind. What is only yours: the persona, the lyrics you approved, and everything you do with the song afterwards in Wave.
Anyone can send a prompt to a music model and get a track back. That track is a starting point, not a release. This is the work that sits between the two, and it is the part 67 MUSIC does for you.
| The engine on its own | 67 MUSIC | |
|---|---|---|
| The song | a track from a prompt, or from a plan you build yourself | the same engine, driven by a plan written from the lyrics you approved and the artist's own sound rules |
| The lyrics | you write them, or you get whatever a general model writes | a lyrics-first method with measured rules: one feeling, a chorus you can sing in one breath, one image per line, a concrete detail as proof |
| The artist | none. Every song stands on its own | a persona with a home city, a face, a voice and rules that hold, reused on every track under that name |
| Title, cover, portrait | none. You get audio | a title and cover art with every song, a painted portrait for the artist |
| Mastering | the raw render | a two-pass master to −14 LUFS with true peaks under −1.5 dBTP, plus a measured profile: tempo, key, loudness |
| Stems and MIDI | not part of the model | four separated stems and a MIDI file for any song, ready for your own DAW |
| Editing | none. What comes out is what you have | Wave: timeline, EQ, compressor, sidechain, mixer, on-screen keyboard and instruments, piano roll, step sequencer, 150 loops, chord detection, beat slicing, mastering assistant |
| Starting from your own sound | an uploaded clip can steer the style | upload a recording, a demo or stems, edit the plan it extracts, regenerate one section, extend it, or get two versions to choose from |
| Video | none | a short-form editor that already knows the beat and the sung words: 58 effects, 42 transitions, karaoke captions, cuts on the beat |
| Release | a file on your disk | an artist page, a public chart, share links that open and play, a library where every track keeps its cover |
| Playback | as rendered | native 432 Hz playback, one tap, on by default |
| Where it happens | an interface or an API you drive yourself | one conversation with Shela. She writes, generates, masters, names, illustrates and files the song, and sets the artist up |
Most songs are finished when they land in your library. Wave is there for shaping the music yourself, Video for turning it into a clip. Both run in your browser, on every plan, and neither is required.
Wave takes any finished song, splits it into separate tracks and lets you change whatever you want. The original stays as it is; Wave saves a new version.
Video already knows your song: its beat, its lyrics and the timing of every word. You add the pictures, or let it make them.
Every song under one name keeps the same voice, sound and character, because the rules are written down once and reused.
One tap retunes the whole recording from 440 to 432 Hz. A few small clinical studies link 432 Hz music to a lower heart rate and less stress hormone than 440 Hz.
Download the four stems and a MIDI file for any song. Studio WAV out. Your own DAW is welcome.
Public artist pages, Explore and Top Songs, likes and plays, playlists, share links with previews. No account needed to listen.
Full details on the pricing page.
Open Shela and write what you want: an artist, a track for your set, ideas in your genre. Approve the lyrics, and listen about half a minute later.
Comparing tools? See how 67 MUSIC stands against other AI music tools.
67 MUSIC je glasbeni studio znotraj Shele. Napišeš en stavek, tako kot bi pisal prijatelju. Čez kakšnega pol minute je pesem končana: napisana, odigrana, masterirana, z naslovom in naslovnico, v tvoji knjižnici in pripravljen za deljenje.
Hočeš izvajalca, pod katerim ga izdaš? Reci in Shela si izmisli celo osebo, ji da obraz in jo postavi na njeno stran. Nočeš nič od tega in hočeš samo glasbo zase, za svoj set, za svoje stranke? Tudi to gre.
Brez obrazcev, brez drsnikov, brez čarovnika za zvrsti. Poveš, kaj hočeš; kar izpustiš, odloči Shela in ti pove, kaj je odločila.
Hej Shela, mi narediš novo persono, Tiago Vela, iz Lizbone na Portugalskem, vrtel bo latin tech house. Generiraj profilno sliko, postavi vse in naredi kar dve pesmi, viralni za TikTok, 126 BPM.
Narejeno. Tiago Vela, 29 let, Portugalec iz Lizbone, živi med Lizbono in Ibizo. Porjavel, kratki temni lasje, pristrižena brada, belo laneno oblačilo, tanka zlata verižica. Topel bariton, 122 do 126 BPM, suhe konge spredaj, nikoli supersaw.
Portret, biografija in profil so postavljeni, obe pesmi pa masterirani: Sal na Pele s hookom pri 0:12 in Madrugada za konec seta. Če ti ime ali videz ne ustreza, povej in zamenjam.
En stavek noter, ven izvajalec z obrazom, domačim mestom in dvema končanima pesmima.
Hej Shela, sem producent. Daj mi tri ideje za naslednjo izdajo, pop in K-pop, napiši hooke in cela besedila, potem pa najmočnejšo izriši na 100 BPM z ženskim vokalom.
Tri ideje s celimi besedili: Ghost In My Playlist (pop), Neon Hangul (K-pop) in Say Less (pop-R&B), pri vseh je hook v prvih 15 sekundah.
Prvo sem izrisala: 100 BPM, ženski vokal, 2:58, masterirano, z naslovnico, v tvoji knjižnici. Naj naredim še drugi dve?
Brez izvajalca, brez persone, brez obrazcev. Marsikdo uporablja 67 MUSIC samo za svojo produkcijo, v katerem koli slogu.
Hej Shela, dvominutni intro za moj nocojšnji set: 126 BPM, e-mol, zapet hook, suhe konge, in daj mi še različico brez vokala.
Oboje je narejeno: 2:04, 126 BPM, e-mol, zapet hook pri 0:48, masterirano na −14 LUFS. Instrumental je iste dolžine in istega masterja, tako da lahko v set vržeš katerega koli. WAV in MP3 sta v tvoji knjižnici.
Hočeš pol tona nižje ali trideset sekund daljše? Ali pa ga odpri v Wave in ga sestavi sam.
Tvoja produkcija, tvoja pravila. Iz knjižnice ne gre nič, dokler ne objaviš.
Če si prosil za izvajalca, si izmisli celo osebo: ime, državo in mesto, starost, videz, glas, pravila, ki jim mora zvok vedno slediti, kanale in založbo. Zraven pride portret. Če hočeš samo pesem, to preskoči.
Eno čustvo na pesem. Refren, ki ga zapoješ v enem dihu. Ena slika na vrstico, konkreten detajl kot dokaz. Prebereš v pogovoru in rečeš da, ali zahtevaš spremembe. To je edina stvar, ki jo narediš.
Besedilo in pravila zvoka postanejo načrt kompozicije: deli, slogi, kje pade refren, kje mora udariti hook. Pesem se odigra in izriše v studijski kakovosti (WAV 44,1 kHz). Skupaj z njim nastaneta naslov in naslovnica. Za triminutno pesem je to okoli 25 sekund, z masteringom vred.
Dva prehoda na −14 LUFS z vrhovi pod −1,5 dBTP, kar pričakujejo pretočne platforme, dinamika pa ostane. Vsaka pesem dobi izmerjen profil: tempo, tonaliteto, glasnost.
Pesem pristane v tvoji knjižnici in, če izvajalec obstaja, na njegovi strani. Povezave za deljenje se odprejo in takoj zaigrajo. Ko ga objaviš, se uvrsti na javno lestvico. WAV ali MP3 preneseš, kadar hočeš, ali pa jo pošlješ naravnost v Wave ali Video.
67 MUSIC ima dve plasti. V jedru je glasbeni model, ki napiše in odigra cele aranžmaje z zapetim vokalom. Na vrhu je Shelina lastna produkcijska metoda: besedilo, načrt, mastering, izvajalec, izdaja. Model naredi zvok; metoda iz njega naredi pesem; licenca pa je razlog, da ti jo lahko izročimo.
Učen samo na licenciranih podatkih, ne na katalogu, postrganem s spleta. Pesmi s plačljivih paketov so tvoje za uporabo, tudi komercialno.
Cel aranžma, odigran in zapet, izrisan v WAV 44,1 kHz, z vokalom ali čisto instrumentalno. Sredi pesmi zna preiti iz ene zvrsti v drugo, zdrži hiter rap in goste besedne vrstice, zvočne učinke pa nosi kar v aranžmaju.
Intro, kitica, refren, bridge: do 30 delov, vsak s svojim besedilom, slogom in navodili, kot sta kitarski solo ali šepetana vrstica. Zato lahko Shela pesem načrtuje, preden se izriše ena sama nota.
Angleško, špansko, francosko, nemško, japonsko in še veliko drugih: vokal sledi jeziku besedila, ki ga potrdiš. Naše lastne izdaje so zapete v srbščini. Zaprosiš lahko za enega pevca ali dva v harmoniji, za šepet ali za izpet refren.
Zvrst, razpoloženje, instrumentacija, tempo in produkcijska doba. Suhi bobni, plate reverb, izpet refren, dva pevca v harmoniji, "besedilo se začne pri 15 sekundah". BPM in tonaliteto drži dovolj natančno, da rezultat plastiš s svojim materialom.
Izbereš en del končane pesmi in samo tistega daš na novo napisati in odpeti, ga podaljšaš ali pa novo pesem nasloniš na 30-sekundni odsek stare. Naložen zvok usmerja občutek, groove in paleto, not pa ne kopira.
Pesmi, ki jih narediš na plačljivem paketu, so tvoje za uporabo, tudi komercialno: na spletu, v oglaševanju, na družbenih omrežjih in v podcastih. Film, televizija in igralniški studii so zaenkrat izjema, za to naju vprašaj. Vsak naložen posnetek in vsaka referenca gresta pred izdelavo skozi preverjanje avtorskih pravic, ukazi z imeni pravih glasbenikov pa se prepišejo v opis sloga.
Glasbo ustvari umetna inteligenca. Nič ni posneto v živo, noben studijski glasbenik ne stoji v sobi. Ker gre za model, lahko podobna pesem nastane tudi komu drugemu, zato ne obljubljamo, da je tvoj edini na svetu. Samo tvoja pa so persona, besedilo, ki si ga potrdil, in vse, kar s pesmijo narediš potem v Wave.
Ukaz glasbenemu modelu lahko pošlje vsak in dobi pesem nazaj. Ta pesem je izhodišče, ne izdaja. Vmes je delo, in prav to 67 MUSIC opravi namesto tebe.
| Sam pogon | 67 MUSIC | |
|---|---|---|
| Pesem | pesem iz ukaza ali iz načrta, ki ga sestaviš sam | isti pogon, voden z načrtom, napisanim iz besedila, ki si ga potrdil, in iz pravil zvoka izvajalca |
| Besedilo | napišeš ga sam ali dobiš, kar napiše splošen model | metoda "najprej besedilo" z izmerjenimi pravili: eno čustvo, refren, ki ga zapoješ v enem dihu, ena slika na vrstico, konkreten detajl kot dokaz |
| Izvajalec | nobenega. Vsaka pesem stoji sama zase | persona z domačim mestom, obrazom, glasom in pravili, ki držijo, uporabljena na vsaki pesmi pod tem imenom |
| Naslov, naslovnica, portret | nič. Dobiš zvok | naslov in naslovnica ob vsaki pesmi, naslikan portret za izvajalca |
| Mastering | surov izris | master v dveh prehodih na −14 LUFS z vrhovi pod −1,5 dBTP in izmerjen profil: tempo, tonaliteta, glasnost |
| Stemi in MIDI | ni del modela | štirje ločeni stemi in datoteka MIDI za vsako pesem, pripravljeni za tvoj DAW |
| Urejanje | nič. Kar pride ven, to imaš | Wave: časovnica, EQ, kompresor, sidechain, mikser, zaslonska klaviatura in inštrumenti, piano roll, step sequencer, 150 loopov, zaznava akordov, rezanje ritma, asistent za mastering |
| Začetek iz lastnega zvoka | naložen posnetek lahko usmerja slog | naložiš posnetek, demo ali steme, urediš načrt, ki ga izlušči, daš en odsek na novo napisati, ga podaljšaš ali dobiš dve različici za izbiro |
| Video | nič | urejevalnik kratkih videov, ki že pozna dobe in zapete besede: 58 učinkov, 42 prehodov, karaoke napisi, rezi na dobo |
| Izdaja | datoteka na disku | stran izvajalca, javna lestvica, povezave, ki se odprejo in zaigrajo, knjižnica, kjer vsaka pesem obdrži naslovnico |
| Predvajanje | kot je izrisano | vgrajeno predvajanje na 432 Hz, en dotik, privzeto vklopljeno |
| Kje se zgodi | vmesnik ali API, ki ga vodiš sam | en pogovor s Shelo. Napiše, generira, masterira, poimenuje, ilustrira in shrani pesem ter postavi izvajalca |
Večina pesmi je končanih, ko pristanejo v knjižnici. Wave je za to, da glasbo oblikuješ sam, Video za to, da jo spremeniš v posnetek. Oba tečeta v brskalniku, v vsakem paketu, nobeden ni obvezen.
Wave vzame katero koli končano pesem, ga razdeli na ločene steze in ti pusti spremeniti, kar hočeš. Izvirnik ostane, kot je; Wave shrani novo različico.
Video tvojo pesem že pozna: njegove dobe, besedilo in čas vsake besede. Ti dodaš slike, ali pa jih naredi on.
Vsaka pesem pod enim imenom obdrži isti glas, zvok in značaj, ker so pravila zapisana enkrat in se uporabijo vsakič znova.
Z enim dotikom cel posnetek preuglasiš s 440 na 432 Hz. Manjše klinične študije povezujejo glasbo na 432 Hz z nižjim srčnim utripom in nižjo ravnjo stresnega hormona kot pri 440 Hz.
Za vsako pesem preneseš štiri steme in datoteko MIDI. Studijski WAV ven. Tvoj DAW je dobrodošel.
Javne strani izvajalcev, Explore in Top Songs, všečki in predvajanja, seznami, povezave za deljenje s predogledom. Za poslušanje ne rabiš računa.
Vse podrobnosti na strani s ceniki.
Odpri Shelo in napiši, kaj hočeš: izvajalca, pesem za svoj set, ideje v svoji zvrsti. Potrdi besedilo in čez kakšnega pol minute poslušaj.
Primerjaš orodja? Poglej, kako se 67 MUSIC postavi ob bok drugim orodjem za AI glasbo.