Spoken
About
Fetch published podcast transcripts as clean Markdown with real speaker names — search episodes and pull transcripts via the Spoken API.
Details
- Author
- spokenmd
- Categories
- Search, Other, Media
Jump to
Setup
Install Spoken in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/spokenmd/spoken
Follow the installation instructions in the repository README, then restart your MCP client.
Spoken — podcast transcripts as clean Markdown, built for AI agents
It's a transcriptretrievalAPI, not a speech-to-text service: it works on already-published podcasts, so you skip uploading audio, running diarization, and mapping anonymous speaker labels by hand. For published shows that's typically5–10× cheaperthan running the audio through a transcription service.
- 🎙️Real speaker names, resolved automatically
- 📄Clean Markdownwith timestamps, tuned for LLM context windows and RAG chunking
- 🔎Searchby text query or paste a Spotify/YouTube URL
- 💳Pay-per-use credits— no subscription, failed calls never charged, repeat fetches free
- 🤖Agent-native— ships with anAgent Skill,agents.md,llms.txt, and anOpenAPI spec
Get a key atspoken.md— or try it free with the demo keypt_demo(search works fully; transcripts limited to the demo episode).
# 1. Find an episode (by text, or paste a Spotify/YouTube URL) curl -s 'https://spoken.md/search?q=huberman+sleep' \ -H 'x-api-key: pt_demo' # 2. Fetch the transcript as Markdown curl -s 'https://spoken.md/transcripts/1000651996090' \ -H 'x-api-key: pt_demo'
The transcript comes back as Markdown with named speakers and timestamps:
John Smith (0:00) Welcome to the show. Today we're talking about... Jane Doe (0:15) Thanks for having me.
Auth is thex-api-keyheader. Responses includeX-Credits-RemainingandX-Credits-Charged. Seeagents.mdfor the full error table and response shapes.
- examples/podcast_summarizer.py— fetch a transcript and summarize it
- examples/rag_pipeline.py— chunk a transcript for a vector store / RAG
- examples/quickstart.sh— search → transcript in two curl calls
This repo includesspoken-mcp, aModel Context Protocolserver that exposes Spoken to MCP-compatible agents (Claude Desktop, Cursor, Cline, …). It provides four tools:
Add it to your MCP client config (e.g. Claude Desktop'sclaude_desktop_config.json):
{ "mcpServers": { "spoken": { "command": "npx", "args": ["-y", "spoken-mcp"], "env": { "SPOKEN_API_KEY": "pt_your_key" } } } }
SPOKEN_API_KEYdefaults topt_demo(search works fully; transcripts limited to the demo episode). Get a real key atspoken.md.
npm install && npm run build SPOKEN_API_KEY=pt_your_key node dist/index.js
Spoken is designed to be called by agents. Point your agent at theAgent Skill(also served athttps://spoken.md/.well-known/skills/spoken-md/SKILL.md), or hand itagents.md. TheOpenAPI specmakes it easy to wrap as a tool for any function-calling or MCP-compatible client (Claude, GPT, Cursor).
Pay-per-use credits, no subscription. New keys: 100 for $15, 500 for $50, 2,000 for $160. Machine-readable atspoken.md/pricing.md.
- Website & docs:https://spoken.md
- Agent instructions:https://spoken.md/agents.md
- OpenAPI spec:https://spoken.md/.well-known/openapi.json
- LLM-friendly overview:https://spoken.md/llms.txt
Spoken is built and maintained atspoken.md.
Search global news using natural language. Webz.io News Search API returns the most relevant articles and content, with filters for source, country, language, date, sentiment, and category.
Add audio search to via MCP - Search any audio in seconds
Search and discover audio content from Freesound.org for video editing and content creation.
Search, download, and extract information from YouTube music videos.
MCP server for AI music catalog — search, stream, and browse 1M+ AI-generated tracks
A Model Context Protocol (MCP) server that enables AI applications to search and download audio resources from the Freesound platform via natural language commands.
A soundboard MCP server with millions of meme sounds from myinstants.com — search, play, and browse categories. npx myinstants-mcp to get started.
Search a real music catalogue from your assistant, get 30-second previews you can play, and add songs straight to your Apple Music playlists.
Music metadata search: 90M+ tracks, ISRC/ISWC, cross-platform IDs
A Model Context Protocol (MCP) server that enables AI applications to search for YouTube music videos and manage playlists using the official YouTube Data API v3.
Semantic search over 9 free-license stock photo sources. Hosted remote server with OAuth — no API key to paste.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
