Podcast Transcripts for AI Agents | spoken.md

Your agent can browse the web, read docs, and write code — but it can't listen to podcasts.

Give your agent any podcast episode as Markdown — with real speaker names, not "Speaker 1." One API call. No subscription.

Try it now — search for any episode or use API key pt_demo with any endpoint. No signup needed.

Building a podcast summarizer, search engine, or research tool? This is the API you were looking for.

Works with Claude, ChatGPT, Cursor, Windsurf, LangChain — any agent that can make an HTTP call.

$0.10 per transcript. Your first transcript in under 30 seconds.

Skip the transcription pipeline

Download audio → Convert format → Run Whisper → Bolt on diarization → Chunk for LLM → Manage storage

You started building a podcast tool — and became a database administrator.

spoken.md replaces that entire pipeline with one API call. You get speaker-labeled Markdown with real names — ready for your LLM's context window.

Real speaker names, not "Speaker 1"

Figuring out who is speaking is harder than transcribing the words. Most tools punt on this — you get "Speaker 1" and "Speaker 2" and a manual cleanup step.

Whisper + diarization

Speaker 1 (0:00)
Welcome to the podcast, where we discuss science and science-based tools for everyday life.

Speaker 2 (0:45)
Thank you for having me. Sleep is one of those things where small changes can have outsized effects.

Spoken

**Andrew Huberman** (0:00)
Welcome to the podcast, where we discuss science and science-based tools for everyday life.

**Matt Walker** (0:45)
Thank you for having me. Sleep is one of those things where small changes can have outsized effects.

No post-processing, no lookup table, no manual correction.

How it works

Two API calls. Search by text or paste a URL from Spotify, YouTube, or any podcast app — then fetch the full transcript.

# 1. Search for an episode
curl -H "x-api-key: pt_demo" \
  https://spoken.md/search?q=huberman+sleep

# 2. Get the transcript
curl -H "x-api-key: pt_demo" \
  https://spoken.md/transcripts/1000651996090

Response is text/markdown with speaker names and credit info in headers:

**Andrew Huberman** (0:00)
Welcome to the Huberman Lab podcast,
where we discuss science and science-based
tools for everyday life. Today my guest is
Dr. Matt Walker, professor of neuroscience
at UC Berkeley and author of Why We Sleep.

**Matt Walker** (0:45)
Thank you for having me, Andrew. Sleep is
one of those things where small changes to
your routine can have outsized effects on
both mental and physical health.

...

Agent integration

# Agent skill (Claude Code, Cursor, Windsurf, etc.)
npx skills add https://spoken.md

# OpenAPI spec — works with any agent framework
https://spoken.md/.well-known/openapi.json

# llms.txt — automatic LLM discovery
https://spoken.md/llms.txt

Pricing

Starter

$15 / 100

$0.15 per transcript

Standard Best value

$50 / 500

$0.10 per transcript save 33%

Volume

$160 / 2,000

$0.08 per transcript save 47%

Credits never expire. Errors are never charged. If it doesn't work, you don't pay.

Each transcript replaces ~$1 of Whisper + diarization compute. No subscription, no overage charges, no annual commitment.

Already have a key? Top up here — or your agent can do it automatically via the API.

Built for agents

OpenAPI spec for automatic tool integration
Structured error codes (error.code) for programmatic handling
Credit-tracking headers (X-Credits-Remaining, X-Credits-Charged) in every response
llms.txt and Agent skill for agent discovery — install with npx skills add https://spoken.md

FAQ

What podcasts are supported?

spoken.md works with any podcast episode. Search by text or paste a URL from Spotify, YouTube, or any podcast app to find episodes.

How are speaker names detected?

Speakers are automatically identified by their real names when possible. When names aren't mentioned in the episode, labels like "Host" or "Guest" are used instead.

What format does the transcript come in?

Transcripts are returned as clean Markdown. Each speaker turn includes the speaker's name in bold and a timestamp, with natural paragraph breaks. The format is optimized for LLM context windows — no timing artifacts or proprietary markup.

Can I use this with my AI agent?

Yes — see the "Built for agents" section above for integration options.

Is there a free trial?

Yes. Use the demo key pt_demo with any endpoint — no signup or payment needed. The demo key returns a full transcript for a sample episode so you can evaluate the format and quality before purchasing.

How do I get more transcripts?

Paste your API key in the top-up form above, or let your agent handle it — the API response includes a top-up link when credits run out.

How much does it cost?

Transcripts start at $0.15 each (100-pack for $15), with volume discounts: 500 for $50 ($0.10 each) or 2,000 for $160 ($0.08 each). Returning customers get lower top-up rates. Errors (404, 502) are never charged. No subscription — credits never expire.

Popular podcasts

Browse transcripts from popular shows:

Example transcripts by podcast →

See Pricing

From $0.08/transcript. No subscription, no expiry. Try with pt_demo first.