Create edited videos with AI-generated scripts and your voice
AI-scripted, voice-cloned short-form video without timeline editing—Mac voice clone only.

Automated comedy podcast pipeline with multi-agent writers' room and verification gates.
Podcast creators, content producers, AI automation enthusiasts
Synthesia (video generation pipeline) · Descript (audio/podcast editing automation) · Obviously AI (automated business intelligence)
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.
AI-scripted, voice-cloned short-form video without timeline editing—Mac voice clone only.
Yet another AI podcast generator when several free alternatives already exist.
HN-to-podcast pipeline, but Spotify already has HN discussion podcasts.
Sentry-to-PR pipeline writes failing tests first, then fixes the bug.
TDD-first auto-fix approach writes failing tests before generating patches, not just patching blindly.
Private podcast feed for couples beats ephemeral WhatsApp voice notes.