Gurnaýar: “Ora 2”-niň surat modelini tanyşdyryş filmi

Menden soraň: önümiň ady, bir setirlik çykyş, logotip, önümiň 3-6 skrinşotlary, onuň döredýän zatlarynyň (ýa-da suratlarynyň) 40+ suraty, brend reňklerim we şriftim, ElevenLabs API açary we ses ID-si, şeýle hem aýdyň düşürilýän royaltisiz trek (ses faýly we düşürilýän wagt möhüri). Eger bir zady goýbersem, şu standart sazlamalary ulanyň: "Ora 2", "zewk üçin ýasalan surat modeli", Unsplash we Pixabay-dan mugt suratlar, Geist, ink #111214, eleven_v4-däki Samara X-iň sesi (19STyYD15bswVz51nqLf) we Pixabay "Cascade Breathe" (129.83 BPM, 75.39s-da düşürilýär).

<script>
Bu formatda 9 setirlik ses ýazgysyny ýazyň we her setiri meniň önümime uýgunlaşdyryň:
"Bu [at]. Bir [kategoriýa]... [baha] üçin gurlan. [işlik] ISLENILEN stilde. Oňa [giriş] beriň - we ol diňe... düşünýär. Ony näçe köp ulansaňyz, şonça-da GOWY bolýar. Onuň [sazlamasyny] sazlaň. Onuň [sazlamasyny]. Onuň [sazlamasyny]. Her [çykyşyny] - suratlandyryşyňyz ýaly sazlaň. [Ady]. Häzir çykdy."
Duýgulary seýrek ulanyň: dymýan setirlerde [ýumşak] we [Feil] setirinde [tolgundy]. Başlangyç sözüni belliklemäň we ony nokat bilen tamamlaň.
</script>

MCP bolmazdan, açarymy ulanyp, ElevenLabs API-a göni jaň ediň. Bir gezekde 4 sany doly skriptli nusga dörediň we maňa saýlamaga rugsat beriň. Eger bir setir dogry eşidilmese, diňe şol setiri 4 gezek täzeden dörediň we iň gowy wersiýasyny meniň nusgama goşuň.
0,28 sekuntdan uzyn arakesmeleri 0,2 sekunt çenli gysgaldyň, soňra her bir frazany ortaça derejä 85% çenli ýetiriň, güýçlendirmäni diňe arakesmeler wagtynda sazlaň.
Söz wagty üçin, okalyşy 100ms ýa-da ondan köp arakesmelerde bölüň, her bir segmenti Whisper bilen aýratynlykda transkripsiýa ediň we onuň ilkinji sözüni ölçenen başlangyç bilen deňleşdiriň. Whisper-iň ýekeje geçişi sözleri ýarym sekunt gijikdirip biler.

22 sekuntlyk kwadrat surata düşüriş plýonkasy, 60 kadr/s tizlikde, 1440x1440 ölçegli, AI laboratoriýasynyň surata düşüriş stilinde: ak brezent, bir şrift, gara syýa, hakyky suratlar we aýdylýan wagtynda sözme-söz ýazylan düşündirişler.
Her bir dolandyryş (saýt paneli, sazlamalar paneli, ýazgy paneli) suwuk aýnany ulanýar: onuň arkasyndaky sahnany glazur bilen örtüň, şol sahnany gyrasyndan galyň aýna ýaly egiň, soňra ýokarky ýalpyldawuk, ýagty gyra we ýumşak göteriji kölege goşuň. Aýna ýönekeý ak reňkde ýitip gidýär, şonuň üçin brendimiň reňklerinde haýal pastel aura ýa-da onuň arkasyndaky suratyň bulanyk ýuwulmagyny goşuň.
Birinjisi brendimiň reňkleriniň gradiýentinde söz görnüşlerine ünsi çekdi, onuň arkasynda bolsa gowşak ýalpyldawuk bardy.
Hereket düzgünleri: kamerany hereketde saklaň (her sahna üçin 1.0-dan 1.04-e basyň; mazmun indiki sahna geçende, öňki sahnanyň gutaran ýerinden başlaň). Hiç zat derrew peýda bolmaýar: azyndan 0.3s ýeňilleşdirilen reňkleri ulanyň. 16-njy notalardaky suratlary her biri üçin bir gezek basyň. Fraza başlanda ýer sahnasy üýtgeýär we saz düşüşini [Feil] setiri bilen deňleşdiriň. Ekranda nokatlary görkezmeň.
Gadagan edildi: saýlama gutusynyň aýratynlyklary, urgy bilen çalynýan sesler, ak ýalpyldawuklar, 3D, şablonlar.

Ses bilen baglanyşykly ýedi sahna:

1. "Bu [at]": at uly harplar bilen ýazylanda suratlarymyň kollažy çykýar, soňra kategoriýa setirine geçýär.
2. "[bahasy] üçin ýasalan": iň gowy suratlarymyň doly ekranda ýalpyldawuklary 16-njy notalara öwrülýär, olaryň üstünde ak reňkde setir ýazylýar.
3. Düşüş: aýna çagyryş paneli gysga çagyryş ýazýar. Netije karty her 16-njy notada stilini üýtgedýär, şol bir wagtyň özünde gara stil çipi kiçijik zolakdaky her täze ada öwrülýär.
4. "Oňa keýp tagtasyny görkez": 9 surat 3x3 ölçegli toruň içine uçýar, soňra ekranda "It gets you" ýazgylary çykanda netijäni aýlaň.
5. "Ony näçe köp ulansaňyz, şonça-da gowy bolýar": iki setir ýazyň, gradientde nygtalýan sözi goýuň.
6. Sazlamalar: 3 sürgüçli aýna paneli görkezýär, olaryň her biri onuň adyny göterýän ýaly hereket edýär. Suratyň reňkini üýtgediň, 16-njy böleklere täze tohumlary ördiň, soňra ony plakat görnüşine öwrüň. Onuň reňkleriniň bulanyk görnüşini aýnanyň arkasyna sinhronlaşdyryp süýşüriň.
7. "Her bir [çykyş], görşüňiz ýaly": aýna ýazgy tabletkasynyň arkasyndaky merkezden 120 suratymy daşaryk çykaryň, soňra at ýazylanda olary logotipime birleşdiriň. Aşakda "Häzir çyk" ýazyň we 2 sekunt saklaň.

Çykyş panelini, netijeleri we sürgüçleri önümimiň hakyky giriş, çykyş we sazlamalary bilen çalyşyň.

Aýdymy düşýän nagyş [Verb] setirine düşýän ýaly edip sazlaň we ritm toruny şol ýere berkidiň.
3 zolakly gapdal zynjyr bilen sazy sesiň aşagynda goýuň (pes 30%, orta 85%, howa 55%; 0.3s saklamak, 50ms öňe seretmek, 0.5s goýbermek). Soňra ses 300 Gts bilen 4 kHz aralygynda sazyň üstünde takmynan 9 dB bolýança her bir frazanyň ortalaryny sazlaň.
Her waka üçin bir göçürilip alnan Mixkit SFX ulanyň, onuň ölçeg depesine görä ýerleşdiriň: her surat üýtgeşikligi üçin bir basyş, her ýazylan harp üçin bir düwme sesi, nygtalýan söze ýumşak düşüş, wyşyldawuk sesler we düşüşe we logotipe täsirler. Her birini depesiniň töwereginden kesiň (köp galdyryjylar 4 sekunt). Sazy soňky kartyň aşagyndaky dB egri boýunça gowşadyň. -14 LUFS-a çenli gaty.

1. Bir HTML kanwasy. Her bir çarçuwa seek(t)-iň içinde wagtyň arassa funksiýasydyr we her bir ýazgy we kesim söz tablisasyna eýerýär.
2. Aýna: şekiliň arkasyndaky kanwasy alyň, göwresi üçin takmynan 14 piksel bulandyryň, gyra boýunça 12 piksel zolakda takmynan 1.06x ulaldylan ýeňil bulandyrylan nusgany çyzyň, soňra süýt, ýalpyldawuklyk, gyra we kölege goşuň.
3. 8 sany hereket bulanyşygynyň kiçi kadrlaryny ulanyp, Playwright bilen 60 kadr/sek tizlikde render ediň, soňra ffmpeg bilen kodlaň.
4. Maňa bir zat görkezmezden ozal, suratlaryň kontakt kagyzyny ýasaň, bir kadrly sesleriň kadr tapawutlaryny skanirleň (diňe 16-njy notalardaky sesler böküp biler) we her bir frazanyň ses-saz gatnaşygyny barlaň.

[Gyzgyn] açyjy pyşyrdaýan ýaly eşidilip bilner, [tolgunýan] bolsa ýalan ýaly bolup görünýär. Sözüň arkasyndaky ýagtylandyryjy gutu Windows tekst saýlanyşyna meňzeýär. Kamera geçiş wagtynda 1.0-a gaýtadan başlasa, zum kesilýär. 0.05s peselme derrew peýda bolýan ýaly görünýär.

Giriş maglumatlaryny soraň, ssenarini ýazyň, saýlamak üçin 4 ses ýazgysyny iberiň, soňra doly renderden öň maňa 8 surat görkeziň.

Ask me for: my product name, a one-line pitch, my logo, 3 to 6 screenshots of the product, 40+ images of what it creates (or photos of it), my brand colors and font, an ElevenLabs API key and voice ID, plus a royalty-free track with a clear drop (the audio file and the drop timestamp). If I skip anything, use these defaults: "Ora 2", "an image model made for taste", free images from Unsplash and Pixabay, Geist, ink #111214, the voice Samara X (19STyYD15bswVz51nqLf) on eleven_v4, and Pixabay "Cascade Breathe" (129.83 BPM, drop at 75.39s).

<script>
Write a 9-line voiceover in this format and adapt every line to my product:
"This is [name]. A [category]... built for [value]. [Verb] in ANY style. Give it a [input] - and it just... understands. The more you use it, the BETTER it gets. Adjust its [setting]. Its [setting]. Its [setting]. Every [output] - exactly as you pictured it. [Name]. Out now."
Use emotion tags sparingly: [softly] on the quiet lines and [excited] on the [Verb] line. Don't tag the opener, and end it with a plain full stop.
</script>

Call the ElevenLabs API directly using my key, without an MCP. Generate 4 full-script takes in one pass and let me choose. If a line doesn't sound right, regenerate just that line 4 times and splice the best version into my take.
Shorten pauses longer than 0.28s to 0.2s, then bring each phrase 85% of the way toward the median level, adjusting gain only during pauses.
For word timings, split the read at pauses of 100ms or longer, transcribe each segment separately with Whisper, and align its first word to the measured onset. A single Whisper pass can place words up to half a second late.

A 22-second square launch film, 1440x1440 at 60fps, in the style of an AI lab launch: white canvas, one typeface, black ink, real images, and captions typed word by word at the exact time they're spoken.
Every control (prompt bar, settings panel, caption pill) uses liquid glass: frost the scene behind it, bend that scene along the edge like thick glass, then add a top sheen, bright rim and soft lift shadow. Glass disappears on plain white, so add a slow pastel aura in my brand colors or a blurred wash of the photo behind it.
The one emphasized word types in a gradient of my brand colors, with a faint glow behind it.
Motion rules: keep the camera drifting (push from 1.0 to 1.04 per scene; when content moves to the next scene, start at the zoom where the previous scene ended). Nothing appears instantly: use eased fades of at least 0.3s. Change images on 16th notes, with a click for each. Land scene changes on phrase starts, and align the music drop with the [Verb] line. Don't show full stops on screen.
Banned: selection-box highlights, beat-snapped slams, white flashes, 3D, templates.

Seven scenes, timed to the voice:

1. "This is [name]": a collage of my images drifts out as the name types in large, then gives way to the category line.
2. "made for [value]": full-screen flashes of my best images switch on 16th notes into the drop, with the line typed in white over them.
3. The drop: a glass prompt bar types a short prompt. The result card changes style every 16th note, while a black style chip rolls to each new name above a thumbnail strip.
4. "Show it a moodboard": 9 images fly into a 3x3 grid, then circle the result as "It gets you" types on screen.
5. "The more you use it, the better it gets": type two lines, with the emphasized word in the gradient.
6. The settings: show a glass panel with 3 sliders, each moving as she names it. Shift the image's hue, roll new seeds on 16ths, then turn it into a poster. Shift a blurred wash of its colors behind the glass in sync.
7. "Every [output], exactly how you see it": burst 120 of my images outward from the center behind a glass caption pill, then bring them together into my logo as the name types on. Put "Out now" underneath and hold for 2s.

Replace the prompt bar, results and sliders with my product's real input, outputs and settings.

Set the song so the drop lands on the [Verb] line, and anchor the beat grid there.
Duck the music under the voice with a 3-band sidechain (lows 30%, mids 85%, air 55%; 0.3s hold, 50ms look-ahead, 0.5s release). Then adjust the mids of each phrase until the voice sits about 9 dB above the music between 300 Hz and 4 kHz.
Use one downloaded Mixkit SFX per event, positioned by its measured peak: a click for each image change, a key sound for every typed letter, a soft landing on the emphasized word, whooshes, and impacts on the drop and logo. Trim each around its peak (many risers are 4 seconds). Fade the music along a dB curve under the end card. Loudnorm to -14 LUFS.

1. One HTML canvas. Every frame is a pure function of time inside seek(t), and every caption and cut follows the word table.
2. Glass: capture the canvas behind the shape, blur it about 14px for the body, draw a lightly blurred copy magnified about 1.06x in a 12px band along the edge, then add the milk, sheen, rim and shadow.
3. Render with Playwright at 60fps using 8 motion-blur subframes, then encode with ffmpeg.
4. Before showing me anything, make a contact sheet of stills, scan frame differences for single-frame pops (only the 16th-note runs may jump), and check the voice-to-music ratio for every phrase.

A [warmly] opener can sound whispered, while [excited] can feel fake. A highlight box behind a word looks like a Windows text selection. If the camera resets to 1.0 during a handoff, the zoom snaps. A 0.05s fade looks like an instant pop-in.

Ask me for the inputs, write the script, send me 4 voice takes to choose from, then show me 8 stills before the full render.

Sorag şu ýerden alyndy poçta @rossaxbt.