# Spoken Muse connector

From musedirectory.ai, the independent directory of Meta Muse connectors. Not affiliated with Meta.

## Spoken

Search and read podcast transcripts as clean Markdown with speaker names and timestamps.

- Record: https://musedirectory.ai/connector/spoken
- Category: Research & Data
- Developer: Spoken (https://spoken.md)
- Muse status: Extra setup. Not in Muse's Connectors list yet. Muse can still use it: its page gives you a request to paste into Muse.
- Health: Working, 520ms, checked 2026-10-29T09:30:53Z
- Endpoint: https://spoken.md/mcp
- Auth: No account needed; Pricing: unknown
- Screening: Screened, no issues found (2026-10-28T20:21:30Z)
- Source: Found in the official MCP Registry (io.github.spokenmd/spoken) https://registry.modelcontextprotocol.io/v0/servers?search=io.github.spokenmd%2Fspoken

Spoken converts podcast episodes into searchable, readable transcripts with real speaker names and timestamps. Search by topic or paste an episode URL from Spotify or YouTube, then fetch full transcripts. Requires an API key and uses a credit system (1 credit per first fetch).

Example request: "Find and read the transcript from a Huberman Lab episode about sleep."

How to connect: Not in Muse's Connectors list yet, but Muse can still use it. Paste this into Muse: "Use Spoken to help me. It is a free service with an MCP server at https://spoken.md/mcp. It does not need an API key. Ask me before you share anything with it." Muse asks before it shares anything with the app's site. Meta does not review apps used this way, so only use ones you trust. We tested this in the Muse app on September 24, 2026: Muse used an app's link directly this way and returned a live answer.

Tools:
- search_podcasts: 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-cata
- get_transcript: 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_episodes: 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 
- get_balance: Check the current Spoken credit balance, account email, and recent usage for the configured API key. Does not consume credits.
- list_following: The shows this key is kept current on. Every charged fetch makes its show a follow: the five most-fetched shows from the last 180 days are followed automatically (source 'fetch'), and up to 25 more can be declared with follow_podcast (source 'explicit'). Muted shows are listed se
- follow_podcast: Declare a follow for a show, or clear a mute. Pass a podcast_id from search_podcasts. A declared follow stays until unfollow_podcast, regardless of fetch activity, and does not use one of the five automatic slots. For a show never fetched, what counts as new starts from its newes
- unfollow_podcast: Mute a show: it leaves the followed list and later fetches do not re-add it. follow_podcast reverses it. Pass a podcast_id from list_following. Does not consume credits.
- list_new_episodes: What is new on the shows this key follows: for each show, the episodes released in the last 90 days that are newer than the newest one already fetched from it (up to 10 per show), each with a transcript_url. Episodes with no transcript are left out. Fetch any with get_transcript 

Screening checks:
- MCP handshake: pass (Answered in 1501ms)
- Domain against threat feeds (Cloudflare security DNS): pass (spoken.md not flagged)
- Published packages against the OSV malicious-package database: pass (No malicious-package advisories)
- Hidden instructions or invisible characters in tool text: pass (8 tools read, nothing found)
- Inputs asking for passwords, card numbers or seed phrases: pass (None found)
- Domain and redirects: pass (No redirects off the domain)
- AI review of purpose and tool behavior: pass (No concerns)