The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
🎙️ I just built an AI Podcast Video Workflow on @Morphic
that turns ONE image into a full cinematic podcast video automatically.
Here's what it does:
✅ Generates your podcast scene
✅ Creates cinematic B-roll cutaways
✅ Lip-syncs your character to your voice
✅ Alternates camera angles automatically
✅ Adds background music & sound effects
No camera. No studio. No editing skills.
Just one image. One script. One click. 🚀
#MorphicWorkflowChallenge @Morphic
was building this and now see it here, but my is a little different
ohh really!
Nice!
Thank You!
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
AI-Powered Motion Graphics & Video Creation
A creative video project exploring how AI-assisted workflows can transform ideas into engaging visual experiences.
Created using Claude AI (Opus 5.5), this project combines AI-assisted generation, dynamic animation, and a modern visual style to create content designed for digital platforms and social media.
Project Highlights
AI-assisted video creation and creative direction
Motion graphics and dynamic visual elements
Visual and engaging scene composition
Content designed for digital marketing and social media
Tools: Claude AI (Opus 5.5), AI-assisted creative workflow.
My Focus: Exploring new ways to combine artificial intelligence and visual creativity to produce engaging, high-quality video content for brands, businesses, and digital creators.
This project is part of my exploration of AI-powered video production and creative visual communication.
Automating viral shorts: Turning 60-minute raw video feeds into cut-and-captioned reels programmatically 🎬⚡
Most content agencies still spend 4+ hours per video manually scrubbing timelines, finding hooks, and syncing subtitle keyframes.
Currently deploying an automated multi-modal clipping engine combining computer vision, audio processing, and programmatic rendering:
Audio-Visual Hook Detection: Runs Whisper for high-precision word-level timestamps and audio frequency analysis to pinpoint emotional peaks, loud reactions, and punchlines.
Auto-Reframing (Face Tracking): Uses OpenCV / MediaPipe face tracking to dynamically crop 16:9 widescreen video into vertical 9:16, keeping speakers centered across active camera cuts.
Programmatic FFmpeg Rendering: Bypasses sluggish UI video editors by chaining headless FFmpeg commands for seamless transitions, auto-zooms, and b-roll overlays.
Dynamic Kinetic Captions: Generates styled, word-by-word animated subtitles directly baked into video layers at 60 FPS.
Turning raw customer webinars and podcasts into 10 ready-to-post short-form clips in under 3 minutes per run.
Pipeline architecture and rendering speed benchmarks below! 👇
#VideoAutomation #FFmpeg #Python #ComputerVision #ContentOps #GenerativeAI #BuildInPublic
This video is made entirely using AI. from storyboarding to prompting and then post-production everything was handled by me.
What do Y'all think about the output?
Nice shot