Show HN: I built a pipeline that generates a comedy podcast end-to-end with AI
open.spotify.comThe pipeline takes a trending topic and produces a fully rendered ~22 min comedy podcast episode with three AI characters (PRODUCER, CRITIC, DUMBASS). Everything is automated: premise ideation, research, outline generation, script writing with a writers' room (punch-up passes, verification gates), voice synthesis via ElevenLabs, music bed mixing, and publishing to Spotify.
Stack: Temporal for durable workflow orchestration, Gemini for script generation, gollem (https://github.com/fugue-labs/gollem) agents with structured outputs and automatic validation, Postgres + Apache AGE for graph queries, Qdrant for vector search, ElevenLabs for multi-voice dialogue synthesis.
Each episode goes through ~10 beats, each independently written and verified for grounding. There's a verifier gate that checks factual claims, forbidden phrases, and character voice consistency before anything gets rendered. The whole thing runs with a single slash command and takes about 2 hours end-to-end.
24 episodes in so far. This one's about a character who uses AI to write a book in a weekend and declares himself a literary genius.
No comments yet.