n8n workflow from audio to video for youtube , fb , tiktok video.
Budget: $12 – $30 SGD
I need a fully automated AI-powered video generation system that runs on my own server using Docker + n8n, and uses FREE / OPEN-SOURCE AI models (NO paid APIs for video generation).
The system must:
• Accept input through a single secure web page (with login)
• Generate dynamic 9:16 videos with movement (not static images)
• Add burned-in subtitles from the transcript I provide
• Sync video with my 2–5 minute audio
• Upload automatically to YouTube Shorts
• Save video & captions for TikTok and Facebook Reels
• Include a dashboard where I can see all processed videos
I DO NOT want to open n8n manually.
Everything must be done through the web page.
FULL TECHNICAL REQUIREMENTS
1. Secure Web Form (Primary User Interface)
A professionally designed, clean, modern UI/UX webpage with:
Fields:
• Audio upload (MP3/WAV, 2–5 minutes storytelling)
• Transcript (text area)
• YouTube Title
• YouTube Description
• YouTube Tags
• TikTok Caption
• TikTok Hashtags
• Facebook Reels Caption
• Video Style Selector (cinematic / historical / epic / calm / etc.) Form Functionality:
• Once submitted → send data to n8n Webhook
• Must include:
o Validation o Progress indication (optional) o Mobile and desktop responsive design Security Requirements:
• Login system (username + password)
• Only I can access this page
• No public access
• Dev can use any safe authentication method:
o Basic Auth o JWT
o Simple database user o Encrypted .env credentials
2. Video Results Dashboard
A second page showing all videos processed:
Fields displayed:
• Job ID
• Title
• Date submitted
• Status (queued / processing / completed / failed)
• Final video download link
• Subtitle file (optional)
• YouTube upload result
• TikTok & Reels caption (easy copy/paste) Features:
• Clean, modern UI/UX
• Search & filter (optional)
• Pagination (optional)
• Auth-protected (same login)
3. n8n Automation Workflow
The workflow inside n8n must include:
A) INPUT
• Receive data from Web Form (via Webhook node)
• Store metadata (title, captions, transcript, etc.)
B) OPEN-SOURCE AI VIDEO GENERATION
(Free, no paid API)
Must support open-source models such as:
• Stable Diffusion (image generation)
• AnimateDiff (motion animation)
• Stable Video Diffusion
• ModelScope Text2Video System must generate:
• Dynamic AI visuals
• With motion (camera movement / animation)
• Not static image slideshow
If the model only produces images, apply:
• FFmpeg motion
• Ken Burns effect
• Parallax
• Smooth zoom-in/out
• Pan left/right
• Subtle movement
(YouTube must NOT detect static content.)
C) VIDEO + AUDIO COMBINATION Use FFmpeg to:
• Merge AI-generated video with original audio
• Ensure perfect timing sync
• Adjust durations
• Create transitions
• Output in 1080×1920 (9:16 vertical)
D) SUBTITLE GENERATION
From the transcript I provide:
• Auto timing generation (AI/algorithm-based segmentation)
• Burn-in subtitles using FFmpeg
• Subtitle style:
o Bold o White text o Black outline o Shadow
o Positioned above safe zone E) YOUTUBE SHORTS AUTO UPLOAD
Using YouTube Data API v3:
• Upload final MP4
• Title → from form
• Description → from form
• Tags → from form
• Set category: Shorts
• Set visibility (Public/Unlisted)
• Create OAuth credentials for future automatic uploads F) SAVE FINAL RESULTS System must:
• Save video file in local storage / cloud
• Save metadata for dashboard
• Provide link for:
o Final video o Subtitles o TikTok caption o Reels caption o AI visual info
G) NOTIFICATIONS (Optional)
Send a Telegram/Discord message on:
• Processing started
• Video completed
• Video failed
4. SERVER REQUIREMENTS
Developer must set up the entire system on my server.
Tools to install (server-side):
• Docker
• Docker Compose
• n8n (Docker container)
• FFmpeg
• Stable Diffusion / AnimateDiff / SVD / ModelScope (via local API or container)
• Reverse proxy (NGINX / Traefik)
• SSL (optional)
• Node.js/Vercel/Next.js deployment for Web Form (optional) Deployment rules:
• Everything must run inside Docker
• No manual dependency that breaks on future server changes
• System must be portable
• All API keys stored in .env
5. DOCUMENTATION REQUIREMENTS (COMPLETE)
The developer MUST provide detailed documentation including: Docker Installation n8n Setup
FFmpeg Setup
Open-Source AI Model Setup
How to change AI model in future
YouTube API setup & token refresh
Web Form deployment guide
How to change login credentials
Dashboard modification guide
Environment variables list
How to migrate to a new server
How to restart/update n8n
How to update Docker images
Troubleshooting guide
Full workflow explanation
This ensures the system can run even if moved to a new server 1–3 years later.
6. DEVELOPER SKILLS REQUIRED
The developer must be strong in:
• n8n workflow automation
• Docker DevOps
• FFmpeg scripting
• AI open-source model integration
• Web development (UI/UX, login, backend)
• API integration (webhooks, YouTube API)
• Server management
• Security best practices
7. DELIVERABLES
• Fully working production-ready system
• Web form (secure)
• Dashboard
• n8n automation
• Open-source AI video engine
• Subtitles generator
• YouTube uploader
• Documentation
• Testing + debugging
• Post-install support (optional)
The system must:
• Accept input through a single secure web page (with login)
• Generate dynamic 9:16 videos with movement (not static images)
• Add burned-in subtitles from the transcript I provide
• Sync video with my 2–5 minute audio
• Upload automatically to YouTube Shorts
• Save video & captions for TikTok and Facebook Reels
• Include a dashboard where I can see all processed videos
I DO NOT want to open n8n manually.
Everything must be done through the web page.
FULL TECHNICAL REQUIREMENTS
1. Secure Web Form (Primary User Interface)
A professionally designed, clean, modern UI/UX webpage with:
Fields:
• Audio upload (MP3/WAV, 2–5 minutes storytelling)
• Transcript (text area)
• YouTube Title
• YouTube Description
• YouTube Tags
• TikTok Caption
• TikTok Hashtags
• Facebook Reels Caption
• Video Style Selector (cinematic / historical / epic / calm / etc.) Form Functionality:
• Once submitted → send data to n8n Webhook
• Must include:
o Validation o Progress indication (optional) o Mobile and desktop responsive design Security Requirements:
• Login system (username + password)
• Only I can access this page
• No public access
• Dev can use any safe authentication method:
o Basic Auth o JWT
o Simple database user o Encrypted .env credentials
2. Video Results Dashboard
A second page showing all videos processed:
Fields displayed:
• Job ID
• Title
• Date submitted
• Status (queued / processing / completed / failed)
• Final video download link
• Subtitle file (optional)
• YouTube upload result
• TikTok & Reels caption (easy copy/paste) Features:
• Clean, modern UI/UX
• Search & filter (optional)
• Pagination (optional)
• Auth-protected (same login)
3. n8n Automation Workflow
The workflow inside n8n must include:
A) INPUT
• Receive data from Web Form (via Webhook node)
• Store metadata (title, captions, transcript, etc.)
B) OPEN-SOURCE AI VIDEO GENERATION
(Free, no paid API)
Must support open-source models such as:
• Stable Diffusion (image generation)
• AnimateDiff (motion animation)
• Stable Video Diffusion
• ModelScope Text2Video System must generate:
• Dynamic AI visuals
• With motion (camera movement / animation)
• Not static image slideshow
If the model only produces images, apply:
• FFmpeg motion
• Ken Burns effect
• Parallax
• Smooth zoom-in/out
• Pan left/right
• Subtle movement
(YouTube must NOT detect static content.)
C) VIDEO + AUDIO COMBINATION Use FFmpeg to:
• Merge AI-generated video with original audio
• Ensure perfect timing sync
• Adjust durations
• Create transitions
• Output in 1080×1920 (9:16 vertical)
D) SUBTITLE GENERATION
From the transcript I provide:
• Auto timing generation (AI/algorithm-based segmentation)
• Burn-in subtitles using FFmpeg
• Subtitle style:
o Bold o White text o Black outline o Shadow
o Positioned above safe zone E) YOUTUBE SHORTS AUTO UPLOAD
Using YouTube Data API v3:
• Upload final MP4
• Title → from form
• Description → from form
• Tags → from form
• Set category: Shorts
• Set visibility (Public/Unlisted)
• Create OAuth credentials for future automatic uploads F) SAVE FINAL RESULTS System must:
• Save video file in local storage / cloud
• Save metadata for dashboard
• Provide link for:
o Final video o Subtitles o TikTok caption o Reels caption o AI visual info
G) NOTIFICATIONS (Optional)
Send a Telegram/Discord message on:
• Processing started
• Video completed
• Video failed
4. SERVER REQUIREMENTS
Developer must set up the entire system on my server.
Tools to install (server-side):
• Docker
• Docker Compose
• n8n (Docker container)
• FFmpeg
• Stable Diffusion / AnimateDiff / SVD / ModelScope (via local API or container)
• Reverse proxy (NGINX / Traefik)
• SSL (optional)
• Node.js/Vercel/Next.js deployment for Web Form (optional) Deployment rules:
• Everything must run inside Docker
• No manual dependency that breaks on future server changes
• System must be portable
• All API keys stored in .env
5. DOCUMENTATION REQUIREMENTS (COMPLETE)
The developer MUST provide detailed documentation including: Docker Installation n8n Setup
FFmpeg Setup
Open-Source AI Model Setup
How to change AI model in future
YouTube API setup & token refresh
Web Form deployment guide
How to change login credentials
Dashboard modification guide
Environment variables list
How to migrate to a new server
How to restart/update n8n
How to update Docker images
Troubleshooting guide
Full workflow explanation
This ensures the system can run even if moved to a new server 1–3 years later.
6. DEVELOPER SKILLS REQUIRED
The developer must be strong in:
• n8n workflow automation
• Docker DevOps
• FFmpeg scripting
• AI open-source model integration
• Web development (UI/UX, login, backend)
• API integration (webhooks, YouTube API)
• Server management
• Security best practices
7. DELIVERABLES
• Fully working production-ready system
• Web form (secure)
• Dashboard
• n8n automation
• Open-source AI video engine
• Subtitles generator
• YouTube uploader
• Documentation
• Testing + debugging
• Post-install support (optional)