use case
Ship show notes without the transcription slog.
Drop an episode. Get Markdown your agent can turn into chapter markers, pull-quote cards, SEO-ready show notes, and full accessibility transcripts.
the problem
Why this is a pain.
You just finished recording a 72-minute episode. Your cohost already closed the laptop. You still need show notes, a title that doesn't feel generic, three pull-quote images for social, timestamped chapters for YouTube, and a plain-text transcript for accessibility. That's four hours of work on top of editing, and it's work you hate.
Transcription services give you text. They don't give you the downstream artifacts — the pull quotes, the chapter breakdown, the show-note bullets tuned for your audience. Your agent can do all of that, if it has the transcript in a shape it can work with.
the workflow
How Frenchie handles it.
- 1
Drop the exported episode audio into your agent.
- 2
Your agent calls transcribe_to_markdown via Frenchie. Long-form audio chunks automatically — a 90-minute episode lands clean.
- 3
Ask your agent to generate the show-note outputs you need: chapters with timestamps, three pull quotes, a hook intro, and the full accessibility transcript.
- 4
Publish. The raw transcript lives in your workspace as an .md file your next episode's agent can reference for running threads.
example
What it looks like in practice.
Your prompt
/transcribe ./episodes/ep-041-final-mix.mp3 Give me: (1) a 3-sentence episode hook, (2) 8 chapter markers with timestamps, (3) 3 pull quotes from the guest, (4) five candidate episode titles.
Agent response
Transcribed 72-minute episode. Outputs below. **Hook**: Why platform engineers should stop building internal dev portals from scratch and start treating their platform as a product with real users. Our guest has built platforms at three unicorns and has opinions. **Chapters**: - 0:00 — Cold open - 2:14 — How the guest got into platform work - 9:40 — The internal-dev-portal mistake - 18:22 — Treating platform as a product - 31:05 — Metrics that matter vs vanity metrics - 44:18 — Hiring for platform teams - 58:30 — Common failure modes - 1:06:12 — Book and tool recommendations **Pull quotes**: 1. "Nobody uses your platform because they love you. They use it because their deadline is tomorrow." 2. "A platform team without product management is just an infra team with more meetings." 3. "The best measure of a platform is how much of it your users forgot is even there." **Title candidates**: - Your Platform Is a Product (Whether You Like It or Not) - Stop Building Developer Portals From Scratch - The Invisible Platform - Platform Engineering, Minus the Myth - What Your Platform Team Isn't Telling You
What lands in your workspace
$frenchie transcribe customer-call.mp3
# Transcript [00:00:12] Alex Welcome — let's walk through what shipped last week. [00:00:48] Sam Auth milestone landed Monday, dashboard rewrite went out Thursday. [00:01:24] Alex Any blockers heading into next sprint?
tips
Things worth knowing.
- A 60-minute episode is 120 credits = $1.20. An episode a week is roughly $62 a year — less than a single month of most podcast-production SaaS.
- Frenchie doesn't detect chapter breaks on its own. Your agent does that from the transcript — it works because agents are good at narrative boundaries once they can read the words.
- For podcasts with heavy cross-talk, your agent's pull-quote quality improves if you prompt for quotes from a specific speaker by context clues ("the guest", "the second voice").
questions
Common questions.
Can I transcribe episodes with multiple hosts?
Yes. Frenchie returns a single transcript — your agent can usually guess speaker boundaries from content. For strict speaker labels, use a dedicated transcription API and feed its output into your agent instead.
What about episodes with music and sound effects?
Transcribes the spoken content and ignores non-speech audio. If you have a stinger or sound effect mid-dialogue, it won't show up in the transcript, which is usually what you want.
How long does a 90-minute episode take to transcribe?
Roughly 8-10 minutes of processing. The job runs async — your agent can keep generating show notes for earlier episodes while the new one processes.
Can I automate this with a script?
Yes — either via the MCP tool (if your scheduler runs in an MCP-compatible agent) or via the HTTP endpoint at mcp.getfrenchie.dev. Cron the export, drop the file, your agent does the rest.
Try it with a real recording of yours.
100 free credits on signup. No card. Drop an audio or video file from your own workflow and see the transcript your agent gets back.