Spoken

Summary

Spoken is a podcast transcript API for AI agents and developers. One call lists every episode of a show that has a published transcript, and one call per episode returns it as clean Markdown with real speaker names and timestamps, ready to drop into notes, a knowledge base or an LLM.

Key Features

Podcast transcript API returning clean Markdown transcripts
Real speaker names identified from conversation context, with timestamps
Search shows by title, guest, or pasted Spotify or YouTube link
One free call lists every episode of a show that has a transcript
One credit per episode, whatever its length, with re-fetches never charged
New-episode endpoint to keep a podcast archive current
MCP server and OpenAPI spec for use with AI agents
Credits never expire and errors are never charged
Free demo key for trying search and a sample transcript
14-day full refund on packs if 20 credits or fewer were used

About Spoken


Shows can be found by title, guest or a pasted Spotify or YouTube link, and a dedicated endpoint lists new episodes so a scheduled poll keeps an archive current. It integrates via a plain REST API, an OpenAPI spec, or an MCP server for ChatGPT, Claude Code and other agent clients, and a free demo key lets you try search and a sample transcript without a card.


Spoken charges one credit per episode regardless of length, with packs from $15 for 100 credits to $160 for 2,000, and credits never expire. It is built for people assembling searchable podcast archives and RAG pipelines over shows they follow.

Get more likes & reach the top of search results by adding this button on your site!

Embed button preview - Light theme
Embed button preview - Dark theme
TurboType Banner

Subscribe to the AI Search Newsletter

Get top updates in AI to your inbox every weekend. It's free!