Description
Summary We're looking for a developer to build a lean, working Proof-of-Concept of an automated pipeline that ingests podcast episode audio, generates a clean transcript with speaker diarization and timestamps, and uses an open-source NotebookLM alternative (Notex or Open Notebook) to automatically produce a suite of repurposed content assets — show notes, episode summaries, social media posts, blog drafts, and pull quotes. The goal is to validate the end-to-end workflow on 2–3 sample episodes, not to build a full production platform yet. We want to see the plumbing work cleanly before investing in scale. Envisioned stack: n8n for orchestration, a speech-to-text API (Deepgram, AssemblyAI, or Whisper), a lightweight DB (Supabase or PostgreSQL), and an open-source NotebookLM alternative as the content generation engine. The whole system should be self-hostable via Docker. We're open to the developer's recommendations on the best tools and tradeoffs. Deliverables include a working n8n workflow, Docker-compose setup, a short README, demonstration on 2–3 sample episodes we provide, and a brief written recommendation on Notex vs. Open Notebook for scaling this pipeline to ~500 episodes/year. Required skills: n8n (or similar orchestration), speech-to-text APIs, Docker / self-hosted deployments, hands-on experience with NotebookLM alternatives or RAG-based content engines, LLM prompt engineering for structured output, and PostgreSQL / Supabase basics. Nice to have: Prior podcast or media-tech automation work, pgvector / RAG experience, structured output via JSON schema or function calling, and experience scaling automation pipelines. To apply, please include: a short overview of your automation / AI pipeline background, specific experience with n8n + STT APIs + open-source NotebookLM alternatives, links to GitHub or prior workflows, a 2–3 sentence note on whether you'd recommend Notex or Open Notebook for this use case and why, and your estimated turnaround time. This is a fixed-budget POC (~$100). If the workflow is clean, reliable, and well-documented, we plan to expand it into a full production build (client portal, human-in-the-loop editor, admin dashboard, scaling to 500+ episodes/year) with a significantly larger budget.