Te whakarite: Kiriata whakarewatanga tauira ahua Ora 2

Pātai mai ki ahau mō: te ingoa o taku hua, he tono kotahi te rārangi, taku tohu, 3 ki te 6 ngā whakaahua mata o te hua, 40+ ngā whakaahua o āna mahi (ngā whakaahua rānei), ngā tae me te momotuhi o taku waitohu, he kī API ElevenLabs me te ID reo, me te ara kore utu me te maturuturunga mārama (te kōnae oro me te tohu wā maturuturunga). Mēnā ka pekehia e au tētahi mea, whakamahia ēnei taunoa: "Ora 2", "he tauira whakaahua i hangaia mō te reka", ngā whakaahua kore utu mai i Unsplash me Pixabay, Geist, waituhi #111214, te reo Samara X (19STyYD15bswVz51nqLf) i runga i te eleven_v4, me Pixabay "Cascade Breathe" (129.83 BPM, maturuturunga i te 75.39s).

<script>
Tuhia he reo ā-ringa e 9 ngā rārangi i tēnei whakatakotoranga, ā, urutauhia ia rārangi ki taku hua:
"Ko [ingoa] tēnei. He [kāwai]... i hangaia mō [uara]. [Kupumahi] i roto i NGĀ momo kāhua KATOA. Hoatu he [whakauru] - ā, ka... mārama noa iho. Ka nui ake tō whakamahinga, ka PAI AKE. Whakatikatikahia tōna [tautuhinga]. Tōna [tautuhinga]. Tōna [tautuhinga]. Ia [putanga] - kia rite ki tāu i whakaaro ai. [Ingoa]. Kei waho inaianei."
Whakamahia ngā tohu kare ā-roto kia iti: [mārire] i ngā rārangi marino, me [hihiri] i te rārangi [Werb]. Kaua e tohu i te tīmatanga, engari me mutu ki te ira poto.
</script>

Waea tika atu ki te API ElevenLabs mā te whakamahi i taku kī, me te kore he MCP. Waihangahia kia 4 ngā tangohanga tuhinga-katoa i te kotahi haerenga, ā, tukua ahau kia whiriwhiri. Ki te kore e tika te tangi o tētahi rārangi, whakahoutia taua rārangi kia 4 ngā wā ka honoa te putanga pai rawa atu ki taku tangohanga.
Whakapotoa ngā okiokinga neke atu i te 0.28 hēkona ki te 0.2 hēkona, kātahi ka nekehia ia kīanga ki te 85% o te huarahi ki te taumata waenga, me te whakatika i te whakanui i ngā wā okiokinga anake.
Mō ngā wā kupu, wehea te pānui i ngā wā okioki o te 100ms, neke atu rānei, tuhia motuhaketia ia wāhanga ki a Whisper, ā, whakaritea tōna kupu tuatahi ki te tīmatanga inehia. Mā te tukunga kotahi a Whisper ka taea te whakanoho i ngā kupu ki muri i te hawhe hēkona.

He kiriata whakarewatanga tapawhā 22-hēkona te roa, 1440x1440 i te 60fps, he momo whakarewatanga taiwhanga AI: he kānawehi mā, he momotuhi kotahi, he mangumangu pango, he whakaahua tūturu, me ngā taitara i patohia kupu-i-te-kupu i te wā tonu e kōrerotia ana.
Ka whakamahia e ia mana whakahaere (pae tohu, papa tautuhinga, pire taitara) he karāhe wai: pania te tirohanga i muri, pikohia taua tirohanga ki te taha pērā i te karāhe matotoru, kātahi ka tāpirihia he kanapa o runga, he awhi kanapa me te atarangi hiki ngawari. Ka ngaro te karāhe i te mā noa, nō reira tāpirihia he aura pastel puhoi i roto i ngā tae o taku waitohu, he horoi pōuri rānei o te whakaahua i muri.
Ko tā te mea i whakanuia ngā momo kupu i roto i te rerekētanga o ngā tae o taku waitohu, me te kanapa ngoikore i muri.
Ngā ture nekehanga: kia neke tonu te kāmera (pēhia mai i te 1.0 ki te 1.04 mō ia whakaaturanga; ina neke te ihirangi ki te whakaaturanga e whai ake nei, tīmata i te whakanui i te wāhi i mutu ai te whakaaturanga o mua). Kāore he mea e puta tonu mai: whakamahia ngā memeha ngāwari o te 0.3 hēkona pea. Hurihia ngā whakaahua i ngā nota 16, me te pāwhiri kotahi mō ia. Taungahia ngā huringa whakaaturanga i te tīmatanga o te rerenga kōrero, ā, whakaritea te maturuturunga o te puoro ki te rārangi [Verb]. Kaua e whakaatu i ngā ira katoa ki te mata.
Kua āraia: ngā miramira pouaka-kōwhiringa, ngā pao-pāwhiri, ngā uira mā, te 3D, ngā tauira.

E whitu ngā whakaaturanga, i whakaritea ki te reo:

1. "Ko [ingoa] tēnei": ka puta ake he kohinga whakaahua o aku whakaahua i te wā e patohia ana te ingoa ki te rahi, kātahi ka tukuna ki te rārangi kāwai.
2. "i hangaia mō te [uara]": ka whiti ngā uira mata-katoa o aku whakaahua pai rawa atu i ngā nota 16 ki roto i te maturuturunga iho, me te rārangi i patohia ki te mā i runga ake.
3. Te taka: ka patohia he tohu poto e te pae tohu karāhe. Ka huri te momo o te kāri hua i ia nota 16, ka huri te maramara pango ki ia ingoa hou i runga ake i te rārangi iti.
4. "Whakaaturia he papa āhua": E iwa ngā whakaahua ka rere ki roto i tētahi matawhata 3x3, kātahi ka porowhitahia te hua ina patohia te "Ka whiwhi koe" ki te mata.
5. "Ka nui ake tō whakamahinga, ka pai ake": patohia kia rua ngā rārangi, me te kupu kua whakanuia i roto i te rōnaki.
6. Ngā tautuhinga: whakaaturia he panera karāhe me ngā reti e toru, e neke ana ia mea i a ia e whakaingoa ana. Nekehia te tae o te ahua, hurihia he purapura hou ki te 16, kātahi ka hurihia hei pānui. Nekehia he tae pōuriuri ki muri i te karāhe kia rite ki te wā kotahi.
7. "Ngā [putanga] katoa, kia rite ki tāu e kite nei": 120 ngā whakaahua i pūhia ki waho mai i waenganui i muri i tētahi pire taitara karāhe, kātahi ka honoa mai ki roto i taku waitohu i te wā e patohia ana te ingoa. Whakatakotoria te "Out now" ki raro, ka pupuri mō te 2 hēkona.

Whakakapia te pae tohu, ngā hua me ngā reti ki ngā tāuru, ngā putanga me ngā tautuhinga tuturu o taku hua.

Whakatakotoria te waiata kia tau te maturuturunga ki te rārangi [Verb], ka herea te whatunga patu ki reira.
Āraia te puoro i raro i te reo mā te whakamahi i tētahi mekameka taha-toru (ngā iti 30%, ngā waenga 85%, te hau 55%; te pupuri 0.3s, te titiro whakamua 50ms, te tuku 0.5s). Kātahi ka whakatikatika i ngā waenga o ia rerenga kōrero kia eke te reo ki te 9 dB i runga ake i te puoro i waenga i te 300 Hz me te 4 kHz.
Whakamahia kia kotahi te Mixkit SFX kua tikiakehia mō ia huihuinga, kia tū ai i runga i tōna tihi inehia: he pāwhiri mō ia huringa whakaahua, he tangi kī mō ia reta kua patohia, he taunga ngawari ki te kupu kua whakanuia, he whoosh, me te pānga ki te maturuturunga me te tohu. Tapahia ia mea huri noa i tōna tihi (he maha ngā ara ake he 4 hēkona). Whakangaromia te puoro i te taha o te pihi dB i raro i te kāri mutunga. Whakanuia te oro ki te -14 LUFS.

1. Kotahi te kānawehi HTML. He mahi tūturu ia anga o te wā i roto i te seek(t), ā, ko ia taitara me ia tapahi e whai ana i te kupu ripanga.
2. Karāhe: hopukina te kānawehi i muri i te āhua, whakapōuriuria kia 14px te whānui mō te tinana, tuhia he tārua pōuriuri kua whakanuia kia 1.06x i roto i te whitiki 12px i te taha, kātahi ka tāpirihia te miraka, te kanapa, te awhi me te atarangi.
3. Tāruatia ki Playwright i te 60fps mā te whakamahi i ngā anga iti e waru mō te neke-pōuri, kātahi ka whakakōwaea ki ffmpeg.
4. I mua i te whakaatu mai i tētahi mea ki ahau, hangaia he pepa whakapā mō ngā whakaahua, matawaihia ngā rerekētanga o te anga mō ngā pakū o te anga kotahi (ko ngā oma o te nota 16 anake ka peke), ā, tirohia te ōwehenga reo-ki-puoro mō ia rerenga kōrero.

Ka taea e te whakatuwheratanga [mahana] te tangi hāhā, engari ka taea e te [whakahihiri] te ahua rūpahu. Ko te pouaka miramira i muri i te kupu he rite ki te kōwhiringa tuhinga Windows. Ki te tautuhi anō te kāmera ki te 1.0 i te wā e whakawhiti ana, ka pakū te whakanui. Ko te memeha 0.05s he rite ki te pakū-ake inamata.

Pātai mai ki ahau mō ngā whakaurunga, tuhia te tuhinga, tukuna mai kia 4 ngā tango reo hei whiriwhiri māu, kātahi ka whakakitea mai kia 8 ngā whakaahua i mua i te whakaahuatanga katoa.

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.

I tangohia te tono mai i pou @rossaxbt.