AI Story Video Maker Platform
Budget / Salary₹12,500–37,500
TypeFreelance project
LocationRemote
Posted1 hour ago
I need an end-to-end solution that lets users type a topic and receive a polished video story in minutes. The core flow is: topic → AI-written story (user can choose short, medium, long) → scene breakdown → image generation with character consistency → bilingual (English & Hindi) voice-over → automatic assembly into a video with smooth transitions.
Scope
• Two client surfaces: a responsive web app plus a dedicated Android build. The codebase can be shared (e.g., React + React Native or Flutter Web + Android) as long as the UX remains consistent.
• Server side must orchestrate OpenAI (or similar) for text generation, a diffusion model for images, a TTS engine for voice-over, and a lightweight video compositor such as FFmpeg or Remotion.
• Auth (email + social) with a simple dashboard where users can replay, download, or delete past stories.
• Output: MP4 ready to download or share.
What I’d like from you
1. A concise proposal outlining the tech stack you recommend, why it fits, and any licensing considerations for the AI models.
2. A realistic timeline broken into milestones (MVP, beta, production).
3. Cost by milestone and payment terms.
4. Any previous work that shows you have handled multimedia generation or complex AI pipelines.
Acceptance criteria
• Story and voice-over available in both languages on day one.
• Scene images retain character identity throughout the video.
• A five-minute story renders in under two minutes on a mid-tier cloud instance.
• Clear, reproducible deployment scripts (Docker or similar).
I’m ready to move quickly once I see a solid plan. Let me know if any part of the scope needs clarification.
Scope
• Two client surfaces: a responsive web app plus a dedicated Android build. The codebase can be shared (e.g., React + React Native or Flutter Web + Android) as long as the UX remains consistent.
• Server side must orchestrate OpenAI (or similar) for text generation, a diffusion model for images, a TTS engine for voice-over, and a lightweight video compositor such as FFmpeg or Remotion.
• Auth (email + social) with a simple dashboard where users can replay, download, or delete past stories.
• Output: MP4 ready to download or share.
What I’d like from you
1. A concise proposal outlining the tech stack you recommend, why it fits, and any licensing considerations for the AI models.
2. A realistic timeline broken into milestones (MVP, beta, production).
3. Cost by milestone and payment terms.
4. Any previous work that shows you have handled multimedia generation or complex AI pipelines.
Acceptance criteria
• Story and voice-over available in both languages on day one.
• Scene images retain character identity throughout the video.
• A five-minute story renders in under two minutes on a mid-tier cloud instance.
• Clear, reproducible deployment scripts (Docker or similar).
I’m ready to move quickly once I see a solid plan. Let me know if any part of the scope needs clarification.
Apply on Freelancer →
Project sourced from Freelancer.com. Applications happen directly on the original platform — we never collect your data.