Hi Product Hunt. Spoken is an API for people who follow a few podcasts closely and want the episodes as text they can search, quote and hand to an LLM. Two calls do the job: one lists every episode of a show that has a transcript, one returns an episode as Markdown with the speakers named and timestamped. There is a bash loop on every show page that pulls a whole back catalog; 215 episodes of Acquired come to $32. What it is not: a speech-to-text service. It serves transcripts of published episodes, so you pay per episode rather than per minute of audio, and a show that publishes no transcript is one Spoken cannot serve. Search yours first; every result it shows is fetchable. There is a free demo key (pt_demo) that returns one full episode without signing up, an MCP server (npx spoken-mcp) and a Python client (pip install spoken-md). We would rather have your honest take on the positioning than an upvote: is "your shows, as text" the right first sentence, or does "podcast transcript API" say it faster? We will be in and out through the day and will answer everything.

Spoken.md

Podcast transcripts as Markdown, with real speaker names

Podcast transcripts as Markdown, with real speaker names