> ## Documentation Index
> Fetch the complete documentation index at: https://docs.audivo.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Overview

> Podcast transcripts by API — search a show, price the episodes, confirm, read.

Audivo turns a public podcast episode into a clean, timed, provenance-carrying
transcript over an HTTP API, and exposes the same operations to AI agents as
a remote MCP server.

## How a request flows

1. **Find** a show by name, or take a category chart.
2. **Price** the episodes you want. A quote reserves nothing and tells you the
   most it can cost.
3. **Confirm** the quote. Cached episodes are delivered at once; the rest
   become jobs in one group.
4. **Read** each transcript as JSON, plain text, SRT, VTT or Markdown.

Credits are the unit of spend: one credit per audio minute, rounded up per
episode. A quote states an estimate and a ceiling; a job settles at the
measured audio or the ceiling, whichever is lower, and never above.

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Search, quote, confirm and read one episode with curl.
  </Card>

  <Card title="Authentication" icon="key" href="/authentication">
    API keys, the one header every call sends, and what a 401 looks like.
  </Card>

  <Card title="Errors" icon="triangle-exclamation" href="/errors">
    Every error code, what it means, and whether to retry.
  </Card>

  <Card title="MCP server" icon="robot" href="/mcp">
    Set up Codex, Claude Code, Cursor, and other clients with your API key.
  </Card>
</CardGroup>