Projects
/
Nooko AI Intro
/
Brief
VID-2026-0007
Rendered
Workflow
Brief
Creative & technical brief
JSON Plan
AI-generated storyboard
Assets
Images & voice-over
Music
Background audio
Render
Export final video
History
Activity & versions
Version history:
v3 — 2026-05-17 06:23
v2 — 2026-05-17 05:42
v1 — 2026-05-17 05:41
Showing v3
Brand Kit
Use a brand kit (palette, photography style, logo)
None — generic, no brand constraint
Blaze
CalcMenu Cloud
Nooko AI
Applies the brand's visual directive to every image prompt and keeps all scenes on-brand.
Video Description
Format: vertical 9:16 Length: 12–15 seconds Style: fast, clean, modern, food-tech, professional kitchen + software interface Audio: light energetic music, optional voice-over Captions: burned into the video, because many people watch without sound Scene structure: 0–2 sec Visual: messy desk/kitchen counter with paper recipes, PDFs, phone photos, Excel sheet. Text: “Recipes everywhere?” 2–5 sec Visual: files being pulled into Nooko AI. Text: “Turn them into structured recipes.” 5–9 sec Visual: quick flashes of Nooko-style actions: create, convert, analyse, translate, edit. Text: “Create. Convert. Analyse. Translate.” 9–12 sec Visual: clean recipe card, dish image, professional layout. Text: “From idea to ready-to-use recipe.” 12–15 sec Visual: Nooko AI logo. Text: “Meet Nooko AI.” CTA: “Start free.”
This is the primary input — write as much as you need. The AI uses this to build the entire storyboard.
Product & Goal
Product / App Name
*
Feature to Promote
Goal
Call to Action
Audience & Messaging
Target Audience
Technical
Duration (seconds)
Platform
TikTok
Instagram Reels
YouTube Shorts
Facebook
LinkedIn
YouTube
Language
English
French
Spanish
German
Portuguese
Italian
Dutch
Voice (ElevenLabs)
Default (from .env)
Roger - Laid-Back, Casual, Resonant
Sarah - Mature, Reassuring, Confident
Laura - Enthusiast, Quirky Attitude
Charlie - Deep, Confident, Energetic
George - Warm, Captivating Storyteller
Callum - Husky Trickster
River - Relaxed, Neutral, Informative
Harry - Fierce Warrior
Liam - Energetic, Social Media Creator
Alice - Clear, Engaging Educator
Matilda - Knowledgable, Professional
Will - Relaxed Optimist
Jessica - Playful, Bright, Warm
Eric - Smooth, Trustworthy
Bella - Professional, Bright, Warm
Chris - Charming, Down-to-Earth
Brian - Deep, Resonant and Comforting
Daniel - Steady Broadcaster
Lily - Velvety Actress
Adam - Dominant, Firm
Bill - Wise, Mature, Balanced
Adalina - Professional & Friendly
Antonio Farina - Italian PRO Talent - Audiobook, Narration
Arthur – Social Media Conversational American Male Narrator
Brian K
Daria - The Upbeat American Gal
Arthur – American Male Narrator
Hale - Great for Commercials
David - A versatile and authentic male voice
Clément - Top Voice France - Narrative, calm, clear
Frédéric French Narration
Broadcast - Compressed
Hope - upbeat and clear
Clark Clear - Professional Voice
Hope - Professional, Clear and Natural
Joel – Inspiring American Male Narrator
Léo - French Pro Voice Artist for Narration & More
Johnny - Upbeat Professional American Male
Francesco – Warm and Expressive
Mario - Professional Voice
Mark - Casual, Relaxed and Light
Mark - Natural Conversations
Scoobie - American Male, enthusiastic, sharp, smart
Mr. Laurent — French Podcast Voice
Voce per Audiolibri & Podcast
Premium Male teacher, E-learning, Informative
Thomas - Warm TV Documentary, E-Learning & Tutorial Voice
Thomas Louis
Nate - Natural, Warm, Podcast Voice
Tone
Select…
Energetic
Professional
Playful
Inspiring
Calm
Urgent
Friendly
Pace
Select…
Fast
Medium
Slow
Visual Style
Select…
Modern
Minimalist
Bold
Cinematic
Animated
Corporate
Lifestyle
Visuals & Scenes
Media mode
Images only — simple, cheap, fastest
Mixed — LLM picks video vs image per scene
Videos only — every scene is Veo-generated
Video scenes use Google Veo 3.1 and are capped at 8s each.
Veo model (ignored if media mode = Images only)
Fast — $0.10/sec (recommended)
Standard — $0.40/sec (highest quality)
Lite — $0.05/sec (cheapest)
Number of scenes (blank = let the AI decide)
Image source (default)
AI-generated
I'll upload my own
You can still flip this per-scene on the Assets page.
Image provider (AI)
Google Nano Banana Pro (gemini-3-pro-image-preview)
OpenAI gpt-image-1
Only used when image source is AI-generated.
Animated subtitles (TikTok-style word highlight)
Uses ElevenLabs forced alignment to sync each word with the voice-over.
Music & Constraints
Music Style
Music Constraints
Optional Notes
Back to Project
Save Draft
Save & Generate Plan
Project Info
Ref No
VID-2026-0007
Status
Rendered
Created
2026-05-17 05:41
Brief versions
3
Recent Activity
Render Complete
2026-05-17 08:44
Render Started
2026-05-17 08:43
Render Queued
2026-05-17 08:43
Music Selected
2026-05-17 08:43
Assets Approved
2026-05-17 08:43
Assets Generation Complete
2026-05-17 06:35
Asset Generated
2026-05-17 06:35
Asset Generated
2026-05-17 06:35