A’ stèidheachadh: Film cur air bhog modail ìomhaigh Ora 2

Faighnich dhomh: ainm mo thoraidh, tairgse aon-loidhne, mo shuaicheantas, 3 gu 6 dealbhan-sgrìn den toradh, còrr is 40 ìomhaigh den rud a chruthaicheas e (no dealbhan dheth), dathan is cruth-clò mo bhrand, iuchair API ElevenLabs agus ID gutha, a bharrachd air trac gun rìoghalachd le leigeil sìos soilleir (am faidhle claisneachd agus stampa-ama an leigeil sìos). Ma leumas mi rud sam bith, cleachd na roghainnean bunaiteach seo: "Ora 2", "modail ìomhaigh air a dhèanamh airson blas", ìomhaighean an-asgaidh bho Unsplash agus Pixabay, Geist, inc #111214, a’ ghuth Samara X (19STyYD15bswVz51nqLf) air eleven_v4, agus Pixabay "Cascade Breathe" (129.83 BPM, leigeil sìos aig 75.39s).

<script>
Sgrìobh guth-thairis 9-loidhne san fhòrmat seo agus atharraich gach loidhne a rèir mo thoradh:
"Seo [ainm]. Roinn-seòrsa [roinn]... air a thogail airson [luach]. [Gnìomhair] ann an stoidhle SAM BITH. Thoir [cuir a-steach] dha - agus bidh e dìreach... a’ tuigsinn. Mar as motha a chleachdas tu e, ’s ann as fheàrr a gheibh e. Atharraich a [suidheachadh]. A [suidheachadh]. A [suidheachadh]. Gach [toradh] - dìreach mar a bha thu ga fhaicinn. [Ainm]. Ri fhaighinn a-nis."
Cleachd tagaichean faireachdainn gu gann: [gu socair] air na loidhnichean sàmhach agus [air bhioran] air an loidhne [Gnìomhair]. Na cuir tag air an toiseach, agus crìochnaich e le stad-phuing shìmplidh.
</script>

Cuir fòn gu API ElevenLabs gu dìreach a’ cleachdadh an iuchair agam, às aonais MCP. Gin 4 gabhail làn-sgriobt ann an aon phas agus leig dhomh taghadh. Mura h-eil loidhne a’ fuaimeachadh ceart, ath-ghin dìreach an loidhne sin 4 tursan agus cuir an dreach as fheàrr a-steach don ghabhail agam.
Giorraich stadan nas fhaide na 0.28 s gu 0.2 s, an uairsin thoir gach abairt 85% den t-slighe a dh’ionnsaigh an ìre mheadhanaich, ag atharrachadh a’ bhuannachd a-mhàin rè stadan.
Airson amannan fhaclan, roinn an leughadh aig stadan de 100ms no nas fhaide, sgrìobh gach earrann air leth le Whisper, agus co-thaobhadh a’ chiad fhacal aige ris an toiseach tomhaiste. Faodaidh aon phas Whisper faclan a chuir suas ri leth diog fadalach.

Film cur air bhog ceàrnagach 22-diog, 1440x1440 aig 60fps, ann an stoidhle cur air bhog obair-lann AI: canabhas geal, aon chruth-clò, inc dubh, fìor ìomhaighean, agus fo-thiotalan air an taipeadh facal air fhacal aig an dearbh àm a thathar gan labhairt.
Bidh gach smachd (bàr-stiùiridh, pannal roghainnean, clàr-sgrìobhaidh) a’ cleachdadh glainne leaghaidh: cuir reothadh air an t-sealladh air a chùlaibh, lùb an sealladh sin air an oir mar ghlainne thiugh, an uairsin cuir deàrrsadh àrd, oir shoilleir agus sgàil bog ris. Bidh glainne a’ dol à sealladh air geal lom, mar sin cuir aura pastel slaodach ann an dathan mo bhrand no nighe doilleir den dealbh air a chùlaibh.
Chuir am fear cuideam air seòrsachan fhaclan ann an caisead de dhhathan mo bhrand, le deàrrsadh lag air a chùlaibh.
Riaghailtean gluasaid: cùm a’ chamara a’ gluasad (brùth bho 1.0 gu 1.04 gach sealladh; nuair a ghluaiseas susbaint chun ath shealladh, tòisich aig an zoom far an do chrìochnaich an sealladh roimhe). Chan eil dad a’ nochdadh sa bhad: cleachd seargadh socair de co-dhiù 0.3 diogan. Atharraich ìomhaighean air notaichean 16mh, le cliog airson gach fear. Tionndaidh atharrachaidhean seallaidh air tìr nuair a thòisicheas abairtean, agus co-thaobhadh an ceòl a’ leigeil sìos leis an loidhne [Gnìomhair]. Na seall stadan slàn air an sgrion.
Toirmisgte: prìomh thachartasan bogsa-taghaidh, slams le buille-snap, lasraichean geala, 3D, teamplaidean.

Seachd seallaidhean, air an clàradh leis a’ ghuth:

1. “Is e seo [ainm]”: nochdaidh cruinneag de na h-ìomhaighean agam fhad ’s a tha an t-ainm a’ taipeadh ann am meud mòr, agus an uairsin thig loidhne na roinne-seòrsa.
2. "air a dhèanamh airson [luach]": bidh lasraichean làn-sgrìn de na h-ìomhaighean as fheàrr agam a’ tionndadh air notaichean 16mh a-steach don tuiteam, leis an loidhne air a taipeadh ann an geal thairis orra.
3. An boinne: bidh bàr-brosnachaidh glainne a’ taipeadh brosnachaidh ghoirid. Bidh stoidhle cairt nan toraidhean ag atharrachadh a h-uile 16mh nota, agus bidh sliseag stoidhle dubh a’ roiligeadh gu gach ainm ùr os cionn stiall mion-dhealbhan.
4. “Seall bòrd-mothachaidh dha”: bidh 9 ìomhaighean ag itealaich a-steach do ghriod 3x3, an uairsin cuir cearcall timcheall air an toradh fhad ’s a tha “Gheibh e thu” a’ taipeadh air an sgrion.
5. “Mar as motha a chleachdas tu e, ’s ann as fheàrr a bhios e”: sgrìobh dà loidhne, leis an fhacal le cuideam anns a’ chlaonadh.
6. Na roghainnean: seall pannal glainne le 3 sleamhnagan, gach fear a’ gluasad mar a dh’ainmicheas i e. Gluais dath na h-ìomhaigh, rol sìol ùra air 16mh, agus an uairsin tionndaidh e gu postair. Gluais nighe doilleir de na dathan aige air cùl a’ ghlainne ann an sioncronachadh.
7. "A h-uile [toradh], dìreach mar a chì thu e": cuir 120 de na h-ìomhaighean agam a-mach bhon mheadhan air cùl clàr-sgrìobhaidh glainne, an uairsin thoir iad còmhla gus am bi iad nam suaicheantas fhad ‘s a tha an t-ainm a’ taipeadh. Cuir "A-mach a-nis" fodha agus cum sìos airson 2 dhiog.

Cuir fìor chur-a-steach, toraidhean agus roghainnean an toraidh agam an àite a’ bhàr-brosnachaidh, nan toraidhean agus nan sleamhnagan.

Suidhich an t-òran gus am bi am boinne a’ tuiteam air an loidhne [Verb], agus cuir a’ ghriod buille an sin.
Cuir an ceòl fon ghuth le slabhraidh-taobh 3-bhanna (ìosalan 30%, meadhanan 85%, èadhar 55%; cumail 0.3s, coimhead air adhart 50ms, leigeil ma sgaoil 0.5s). An uairsin atharraich meadhan gach abairt gus am bi an guth mu 9 dB os cionn a’ chiùil eadar 300 Hz agus 4 kHz.
Cleachd aon Mixkit SFX a chaidh a luchdachadh sìos gach tachartas, suidhichte leis a’ mhullach aige a chaidh a thomhas: cliog airson gach atharrachadh ìomhaigh, fuaim iuchrach airson gach litir a chaidh a thaidhpeadh, tighinn air tìr bog air an fhacal a tha air a chomharrachadh, fuaim “shoosh”, agus buaidhean air an tuiteam agus an suaicheantas. Gearr gach fear timcheall air a mhullach (ma tha mòran de na risers 4 diogan). Searg a’ cheòl air feadh lùb dB fon chairt crìochnachaidh. Àrd-norm gu -14 LUFS.

1. Aon chanabhas HTML. Tha gach frèam na ghnìomh fìor-ghlan de ùine taobh a-staigh seek(t), agus tha gach fo-thiotal agus gearradh a’ leantainn clàr nam faclan.
2. Glainne: glac an canabhas air cùl a’ chruth, doilleirich e mu 14px airson a’ chuirp, tarraing leth-bhreac beagan doilleir air a mheudachadh mu 1.06x ann am còmhlan 12px air an oir, an uairsin cuir ris a’ bhainne, an deàrrsadh, an oir agus an sgàil.
3. Dèan reindreachadh le Playwright aig 60fps a’ cleachdadh 8 fo-fhrèamaichean doilleir-gluasaid, agus an uairsin còdaich le ffmpeg.
4. Mus seall thu dad dhomh, dèan duilleag-conaltraidh de dhealbhan fhathast, sgan eadar-dhealachaidhean frèam airson pops aon-fhrèam (chan fhaod ach na ruithean 16mh-nota leum), agus thoir sùil air a’ cho-mheas guth-ri-ceòl airson gach abairt.

Faodaidh fosgladh [blàth] a bhith coltach ri feadalaich, ach faodaidh [air bhioran] a bhith coltach ri meallta. Tha bogsa comharrachaidh air cùl facal coltach ri taghadh teacsa Windows. Ma thèid an camara ath-shuidheachadh gu 1.0 rè làimhseachadh, bidh an zoom a’ snaidheadh. Tha seargadh 0.05s coltach ri pop-in sa bhad.

Iarr orm na cuir-a-steach, sgrìobh an sgriobt, cuir thugam 4 dealbhan gutha airson taghadh, agus an uairsin seall dhomh 8 dealbhan mus tèid an làn-riochdachadh.

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.

Brosnachadh air a thoirt bho post @rossaxbt.