Ag socrú: Scannán seolta samhail íomhá Ora 2

Iarr orm: ainm mo tháirge, cur i láthair aonlíne, mo lógó, 3 go 6 scáileán den táirge, 40+ íomhá den rud a chruthaíonn sé (nó grianghraif de), dathanna agus cló mo bhranda, eochair API ElevenLabs agus ID gutha, móide rian saor ó ríchíosanna le titim shoiléir (an comhad fuaime agus stampa ama an titim). Má scipeáilim aon rud, bain úsáid as na socruithe réamhshocraithe seo: "Ora 2", "samhail íomhá déanta le haghaidh blas", íomhánna saor in aisce ó Unsplash agus Pixabay, Geist, dúch #111214, an guth Samara X (19STyYD15bswVz51nqLf) ar eleven_v4, agus Pixabay "Cascade Breathe" (129.83 BPM, titim ag 75.39s).

<script>
Scríobh guthú 9 líne sa fhormáid seo agus cuir gach líne in oiriúint do mo tháirge:
"Seo é [ainm]. Catagóir [ainm]... atá tógtha le haghaidh [luach]. [Briathar] in AON stíl. Tabhair [ionchur] dó - agus tuigfidh sé... é. Dá mhéad a úsáideann tú é, is amhlaidh is FEARR a éiríonn sé. Coigeartaigh a [socrú]. A [socrú]. A [socrú]. Gach [aschur] - díreach mar a shamhlaigh tú é. [Ainm]. Amuigh anois."
Bain úsáid as clibeanna mothúchánacha go spárálach: [go bog] ar na línte ciúine agus [ar bís] ar an líne [Briathar]. Ná cuir clibeanna ar an gcéad fhocal, agus críochnaigh é le lánstad simplí.
</script>

Glaoigh ar API ElevenLabs go díreach ag baint úsáide as mo eochair, gan MCP. Gin 4 thógáil scripte iomlán in aon phas amháin agus lig dom rogha a dhéanamh. Mura bhfuil fuaim cheart ar líne, athghin an líne sin amháin 4 huaire agus splais an leagan is fearr isteach i mo thógáil.
Giorraigh sosanna níos faide ná 0.28s go 0.2s, ansin tabhair gach frása 85% den bhealach i dtreo an mheánleibhéil, ag coigeartú an ghnóthachan le linn sosanna amháin.
I gcás uainiú focal, scoilt an léamh ag sosanna 100ms nó níos faide, trascríobh gach cuid ar leithligh le Whisper, agus ailínigh a chéad fhocal leis an tús tomhaiste. Is féidir le pas amháin le Whisper focail a chur suas le leathshoicind déanach.

Scannán seolta cearnach 22 soicind, 1440x1440 ag 60fps, i stíl lainseála saotharlainne AI: chanbhás bán, cló amháin, dúch dubh, fíoríomhánna, agus fotheidil clóscríofa focal ar fhocal ag an am beacht a labhraítear iad.
Úsáideann gach rialú (barra leideanna, painéal socruithe, táibléad fotheideal) gloine leachtach: cuir oighriú ar an radharc taobh thiar de, lúb an radharc sin feadh an imeall cosúil le gloine thiubh, ansin cuir snasta uachtarach, imeall geal agus scáth bog ardaithe leis. Imíonn gloine ar bán simplí, mar sin cuir aura mall pastel i ndathanna mo bhranda nó níochán doiléir den ghrianghraf taobh thiar de.
Chuir an ceann béim ar chineálacha focal i ngrádán de dathanna mo bhranda, le gliondar lag taobh thiar de.
Rialacha gluaiseachta: coinnigh an ceamara ag imeacht (brúigh ó 1.0 go 1.04 in aghaidh an radhairc; nuair a bhogann an t-ábhar go dtí an chéad radharc eile, tosaigh ag an súmáil san áit ar chríochnaigh an radharc roimhe sin). Ní fheictear aon rud láithreach: bain úsáid as céimnithe maolaithe de 0.3s ar a laghad. Athraigh íomhánna ar nótaí 16ú, le cliceáil do gach ceann. Cuir athruithe radhairc i dtír nuair a thosaíonn frása, agus ailínigh an titim ceoil leis an líne [Briathar]. Ná taispeáin lánstadanna ar an scáileán.
Toirmiscthe: buaicphointí bosca roghnúcháin, slamanna buille-snapáilte, splancanna bána, 3T, teimpléid.

Seacht radharc, uainiú leis an nguth:

1. "Is é seo [ainm]": tagann colláis de mo chuid íomhánna amach de réir mar a chlóscríobhtar an t-ainm i bhformáid mhór, agus ansin tugtar bealach don líne catagóire.
2. "déanta do [luach]": lascáin lán-scáileáin de mo chuid íomhánna is fearr a chuireann nótaí 16ú isteach sa titim, agus an líne clóscríofa i mbán os a gcionn.
3. An titim: clóscríobhann barra leid gloine leid ghearr. Athraíonn stíl an chárta toraidh gach 16ú nóta, agus rollaíonn sliseanna stíl dhubh chuig gach ainm nua os cionn stiall mionsamhlacha.
4. "Taispeáin clár giúmar dó": eitlíonn 9 n-íomhá isteach i ngreille 3x3, ansin cuir ciorcal timpeall an toraidh agus "Faigheann sé thú" clóscríobhtar ar an scáileán.
5. "Dá mhéad a úsáideann tú é, is amhlaidh is fearr a éiríonn sé": clóscríobh dhá líne, leis an bhfocal béimithe sa ghrádán.
6. Na socruithe: taispeáin painéal gloine le 3 sleamhnán, gach ceann acu ag bogadh de réir mar a thugann sí ainm air. Athraigh dath na híomhá, rolladh síolta nua ar 16ú, ansin déan póstaer de. Bog nigh doiléir dá dathanna taobh thiar den ghloine i sioncrón.
7. "Gach [aschur], díreach mar a fheiceann tú é": pléasc 120 de mo chuid íomhánna amach ón lár taobh thiar de phíobán fotheideal gloine, ansin tabhair le chéile iad i mo lógó de réir mar a chlóscríobhann an t-ainm. Cuir "Amach anois" faoi agus coinnigh ar feadh 2 shoicind.

Cuir ionchur, aschur agus socruithe fíor mo tháirge in ionad an bharra leideanna, na dtorthaí agus na sleamhnán.

Socraigh an t-amhrán sa chaoi is go dtitfidh an braon ar an líne [Briathar], agus ancaire an eangach buille ansin.
Lig don cheol dul faoin nguth le slabhra taobh 3-bhanda (na híseal-tonnta 30%, na meán-tonnta 85%, an t-aer 55%; coinnigh ar feadh 0.3s, féach chun tosaigh ar feadh 50ms, scaoileadh ar feadh 0.5s). Ansin coigeartaigh meán-tonnta gach frása go dtí go suíonn an guth thart ar 9 dB os cionn an cheoil idir 300 Hz agus 4 kHz.
Bain úsáid as SFX Mixkit amháin íoslódáilte in aghaidh an imeachta, suite de réir a bhuaic tomhaiste: cliceáil do gach athrú íomhá, fuaim eochrach do gach litir chlóscríofa, tuirlingt bhog ar an bhfocal atá béimnithe, fuaim na bhfuaimeanna, agus tionchair ar an titim agus ar an lógó. Bailear gach ceann timpeall a bhuaic (maireann go leor ardaitheoirí 4 shoicind). Céimnigh an ceol feadh cuar dB faoin gcárta deiridh. Ardghnáth go -14 LUFS.

1. Canbhás HTML amháin. Is feidhm íon ama laistigh de seek(t) gach fráma, agus leanann gach fotheideal agus gearradh an tábla focal.
2. Gloine: gabh an chanbhás taobh thiar den chruth, doiléir é thart ar 14px don chorp, tarraing cóip atá beagán doiléir agus formhéadaithe thart ar 1.06x i mbanda 12px feadh an imeall, ansin cuir an bainne, an snasta, an imeall agus an scáth leis.
3. Rindreáil le Playwright ag 60fps ag baint úsáide as 8 bhfofhráma doiléire gluaisne, ansin ionchódaigh le ffmpeg.
4. Sula dtaispeánann tú aon rud dom, déan bileog teagmhála de na grianghraif, scanadh na difríochtaí fráma le haghaidh popanna aonfhráma (ní fhéadfaidh ach na ritheanna 16ú nóta léim), agus seiceáil an cóimheas gutha-le-ceol do gach frása.

Is féidir go mbeadh fuaim chogarnach ar oscailt [te], ach is féidir go mbeadh cuma bhréige ar [sceitimíneach]. Breathnaíonn bosca aibhsithe taobh thiar de fhocal cosúil le roghnú téacs Windows. Má athshocraíonn an ceamara go 1.0 le linn láimhseála, stopann an súmáil. Breathnaíonn céimniú 0.05s cosúil le pop-in láithreach.

Iarr na hionchuir orm, scríobh an script, seol 4 ghlacadh gutha chugam le roghnú astu, ansin taispeáin 8 ngrianghraf dom roimh an rindreáil iomlán.

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.

Leid tógtha ó post @rossaxbt.