広告掲載
MCP.so
ログイン

Spoken MCP Server

@roberttomko

リポジトリホームページ

基本情報

カテゴリ

メディアとデザイン

ライセンス

MIT

トランスポート

stdio

作者

roberttomko

投稿者

roberttomko

Spoken MCP Server について

Podcast transcript API — turn any published podcast into clean Markdown with real speaker names. Built for AI agents.

#podcast#transcript#transcription#markdown#ai-agents#rag#llm#speech-to-text#api#developer-tools

Spoken MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "spoken": {
      "command": "npx",
      "args": [
        "-y",
        "spoken-mcp"
      ],
      "env": {
        "SPOKEN_API_KEY": "pt_demo"
      }
    }
  }
}

Spoken MCP Server のツール

4

Search published podcast episodes by text query, or paste an episode URL (Spotify, YouTube, etc.). Returns matching episodes with their id, title, podcast, podcast_id, and date. Use the id with get_transcript, or the podcast_id with list_episodes to get the show's whole back-catalog. Does not consume credits.

Fetch a podcast episode's transcript as clean Markdown with real speaker names and timestamps. Pass an episode id from search_podcasts. Costs 1 credit on the first fetch of an episode; repeat fetches are free and errors are never charged.

List a podcast's entire back-catalog (every episode, newest first). Pass a podcast_id from a search_podcasts result. Returns each episode's id, title, and date — fetch any with get_transcript. Use this to transcribe a whole show. Does not consume credits itself; transcribing the returned episodes costs 1 credit each (repeat fetches are free), so make sure the key has enough credits before looping.

Check the current Spoken credit balance, account email, and recent usage for the configured API key. Does not consume credits.

概要

What is Spoken?

Spoken is a transcript API that turns any published podcast into clean Markdown with real speaker names, not “Speaker 1.” It retrieves named, timestamped text via a single API call, designed for LLMs, RAG pipelines, summarizers, and search. It’s a retrieval service for already-published shows, typically 5–10× cheaper than running audio through a transcription service.

How to use Spoken?

Install and configure the MCP server via npx -y spoken-mcp or from source, setting the SPOKEN_API_KEY environment variable. Add the server to your MCP client config (e.g., Claude Desktop’s claude_desktop_config.json) to expose tools like search_podcasts, list_episodes, get_transcript, and get_balance. Alternatively, use the HTTP API directly via curl with an x-api-key header.

Key features of Spoken

  • Real speaker names resolved automatically
  • Clean Markdown with timestamps tuned for LLMs
  • Search by text query or paste Spotify/YouTube URL
  • Pay-per-use credits with no subscription
  • Repeat fetches are free after first charge
  • Agent-native with MCP server and OpenAPI spec

Use cases of Spoken

  • Fetch a podcast transcript and summarize it with an LLM
  • Chunk transcripts for a vector store or RAG pipeline
  • Search for episodes by topic or podcast name
  • Integrate as a tool in MCP-compatible agents (Claude, Cursor, Cline)

よくある質問

1

How does authentication work?

Authentication is via the `x-api-key` header. A demo key (`pt_demo`) is available for testing (search works fully; transcripts limited to a demo episode).

2

Is there a free tier or demo?

Yes, you can use `pt_demo` as the API key to try search and get one transcript from the demo episode. Full access requires a paid key from spoken.md.

3

What does it cost?

Spoken uses pay-per-use credits: 100 for $15, 500 for $50, 2,000 for $160. Failed calls are never charged, and repeated fetches of the same transcript are free after the first request.

4

Can I use it with any podcast?

Spoken works on already-published podcasts. You can find episodes by text search or by pasting a Spotify or YouTube URL. It does not process uploaded audio.

5

What happens if I run out of credits?

The API returns credit balance info in the `X-Credits-Remaining` header. You can top up or buy a new key via Stripe endpoints (`/buy`, `/top-up`).

コメント

「メディアとデザイン」の他のコンテンツ

Blaze

Blaze

Plan, create and schedule social media content from your AI assistant. Blaze makes on-brand posts, carousels and short videos, writes blog posts and newsletters, and schedules them to Instagram, TikTok, YouTube, LinkedIn

InstantClips

InstantStudioAI

InstantClips turns an e-commerce product into short-form vertical video for TikTok, Instagram Reels and Stories. Import a product from its page URL or photos, generate on-brand video ads, and manage brands/products throu

EveryGen AI MCP Server

EveryGen AI

EveryGen AI MCP Server lets AI assistants create videos, images, voiceovers, music and complete multi-shot films. Connect your EveryGen AI account, describe what you want, review the credit quote and approve the creation

GOJI

GOJI Agency

A remote MCP server from GOJI, a full-service digital agency in Melbourne, Australia. Nine tools over published material: a 104-term plain-English glossary, a 14-chapter guide to AI visibility, seven long-form guides inc

diggercamp

Tommaso Savorana (ti es)

diggercamp finds independent music by how it sounds. Paste any Bandcamp, YouTube or SoundCloud link and get the closest sonic matches from 4M+ independent tracks — matched by rhythm, timbre, key and energy, not genre tag

広告掲載