CoHost AI Studio
Nothing publishes until it clears the gate.
One instrumented pipeline replaces the five-to-eight-tool relay independent producers run today. An episode publishes only after it clears a measured quality bar.
Who it helps: Built for independent podcast producers and studio operators. Fewer listener-facing episodes go out with avoidable technical defects, because publishing waits on the quality checks.
At a glance
- languages
- Python 3.11, TypeScript / React 19, Rust (Tauri)
- pipeline
- 23-step DAG, 4 profile variants
- quality gate
- 11 programmatic scorers + 5 LLM evals
- tests
- pytest suite gates every publish
- history
- built Feb to May 2026 (15 weeks)
- repo
- Private
The problem
Independent podcast producers run every episode through five to eight disconnected tools, with a manual handoff at each step and no signal when a bad master or a thin transcript slips through to publish.
How it’s built
-
A DAG pipeline with idempotency and fault isolation
Twenty-three steps run as a topologically sorted DAG on a thread pool. Each step has an idempotency predicate, so partial runs resume cleanly, and per-step cascade behavior isolates a failure (a stitch timeout does not block show-notes generation). The graph is validated for cycles at build time, before the first episode runs.
-
An instrumented quality gate, not a vibe check
Eleven steps are scored against programmatic metrics: LUFS delta for audio mastering, word confidence and speaker resolution for transcripts, artifact completeness for video. A weighted composite plus a per-step hard-fail threshold feeds straight into the publish decision; below the bar, the pipeline halts before distribution.
-
LLM evals layered over deterministic scores
Five content-heavy steps add opt-in LLM evaluation via OpenRouter, each returning a criterion, score, and reasoning that merge into the scorecard alongside the programmatic metrics. Fast deterministic checks always run; the slower qualitative ones are opt-in.
By the numbers
- steps in the podcast pipeline
- 23
- programmatic scorers plus LLM evals
- 11 + 5
- from first commit to a working gated pipeline
- 15 wks
- pipeline profile variants from one 23-step DAG
- 4
Where this stands today
Live, pre-launch. Four of five P0 launch criteria are validated; YouTube OAuth and multi-show isolation remain open. Functional and test-validated for single-show local operation.