01 / AI-first
2026 · Live
AI Content Production Platform
Content and media production platform, bulk Excel-driven workflows for AI-generated images, video, and audio, with pause/resume job control.
- 01
Excel upload → project rows → explicit generate step
- 02
Pause and resume on bulk runs
- 03
Per-type and per-provider semaphore caps, no Redis
- 04
OpenAI, ElevenLabs, and Fal.ai for image, video, and audio
The brief
Teams generating content at volume (dozens of product images, video clips, or voiceovers per batch) typically stitch together multiple AI tools and vendors by hand, with no shared job history, no way to pause and resume a bulk run, and no protection against a provider rate-limiting or the server falling over under concurrent load.
The outcome
- 01Custom async-semaphore concurrency control replaces Redis/BullMQ/SQS, bulk jobs stay bounded with zero added infrastructure
- 02Two-layer protection (worker-level job caps + provider-level API rate caps) tuned live via environment variables, no redeploy needed
- 03Full bulk pipeline from spreadsheet to generated media: Excel upload → project → generation → pause/resume, backed by durable Postgres job state
The build
A TypeScript monorepo where an Excel upload creates project rows, and generation (image, video, and audio via OpenAI, ElevenLabs, and Fal.ai) is a separate, explicit, pausable and resumable step.
The concurrency problem is real: firing 40 generation jobs at once blows through provider rate limits and can OOM the server. It was solved without adding infrastructure. A custom semaphore bounds how many jobs run per type and per provider, configurable via env vars, with zero Redis or queue service.
Jobs persist as Postgres rows with a JSON payload. Execution can run inline in the API or in an optional dedicated worker. Generated media lands on S3 behind CloudFront.
Specs
- Platform
- Web (React SPA) + REST API
- AI providers
- OpenAI, ElevenLabs, Fal.ai, image, video, and audio generation
- Job system
- Postgres-backed job rows (JSON payload), inline API execution + optional dedicated worker process
- Storage
- AWS S3 + CloudFront
Stack
Building something in this layer?
Start an inquiryMore AI-first
All AI-first
AI Personalised Kids Video Platform
Personalised animated storytelling for children. Generative video pipelines, parent-safe workflows, and infrastructure tuned for viral traffic and repeat renders.
AI-Native Design Studio
AI-native design studio for interior designers: client project management, redesign generation, and team communication in one platform.
Industrial Intelligence
Institutional memory for heavy industry: ingest maintenance documents, build a knowledge graph of assets, people, incidents, and parts, then answer field questions with citations.