AI/SaaS / Maintained
AI Podcast & Audio Newsletter Factory
Fully automated n8n pipeline that runs every morning: ranks top AI stories from RSS feeds, writes a two-host podcast script with GPT-4o in JSON mode, synthesizes each speaker through ElevenLabs with per-persona voice tuning, stitches the audio in-memory, and publishes the episode to Cloudflare R2 and Slack.
Role
Designer and engineer (solo)
Disciplines
AI Integration / Backend Systems
Status
Maintained
System overview
Cron-triggered n8n workflow with multi-source RSS ingestion, keyword + recency scoring, a single GPT-4o call using JSON mode (response_format: json_object) for a structured [{speaker, text}] script, per-persona ElevenLabs synthesis (two deliberately differentiated voice profiles), Buffer.concat MP3 stitching in a Code node with no filesystem or ffmpeg dependency, Cloudflare R2 upload, and a Slack episode announcement. Error sub-workflow handles every failure path.
Validation and results
Fully autonomous daily audio pipeline with two differentiated voice personas, guaranteed-parseable JSON LLM output, binary audio handling without filesystem access, and per-execution cost tracking.