Spoken is answering right now. Last checked 8 min ago. 105 installs a week from npm. It exposes 8 tools. Last commit 6 Oct 2026.
Podcast transcripts as clean Markdown with real speaker names — via the Spoken API.
Installs per day
peak 370 · avg 33 · +18% w/w
a month agotoday
Uptime history
35 days of history · worst day 99%
35 days agonow
100.0%
Uptime 24h
91 of 91 checks
8
Tools
read from the server
351 ms
Response time
average over 24h
105
Installs / week
npm and PyPI
What changed 5
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 6 October 2026. No other catalogue keeps this.
6 Oct
3 tools changed the parameters they ask for
get_balance, list_following, list_new_episodes
6 Oct
a tool changed version2 times that day
and 1 more, back to 6 October 2026
Nothing serious here today
Today is the operative word: we check Spoken every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 8 min ago.
run in your terminal
claude mcp add spoken --transport http https://spoken.md/mcpSettings → Connectors → Add custom connector, then paste this address
https://spoken.md/mcp~/.codex/config.toml
[mcp_servers.spoken]
url = "https://spoken.md/mcp".cursor/mcp.json
{
"mcpServers": {
"spoken": {
"url": "https://spoken.md/mcp"
}
}
}.vscode/mcp.json
{
"servers": {
"spoken": {
"type": "http",
"url": "https://spoken.md/mcp"
}
}
}Available tools 8
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
balance
get_balance
Check the current Spoken credit balance, account email, and recent usage for the configured API key. Does not consume credits.
episodes
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 returned episodes costs 1 credit each (repeat fetches are free), so make sure the key has enough credits before looping.
follow
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 newest episode now. Does not consume credits.
following
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 separately. Use list_new_episodes to see what is new on them. Does not consume credits; the demo key has nothing to follow with.
new
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 (1 credit each on first fetch); a fetch raises that show's floor, so the next call lists only what came after. Refreshed hourly, so a show followed moments ago may be empty until its first poll. Does not consume credits.
podcasts
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-catalog. Does not consume credits.
transcript
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.
unfollow
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.
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://spoken.md/mcp | streamable-http | answering | 186 ms | 8 min ago |
Alternatives to Spoken
same job, measured the same wayWhispifys
by whispifys
Your Microsoft Teams call transcripts, with real speaker names: search, read, ask.
F
Fetch Extract
by cedrickouma
MCP server (stdio): fetch web pages as clean readable markdown via the AgentForge API
Podcast Transcript Scraper
by fernandoguiraud16-coder
Transcribe any podcast by name or RSS feed to text and SRT, with speaker labels.
SummarizeVideo.ai
by summarizevideo
Summarize public video URLs into Markdown notes and read their transcripts.
Whispernotes
by mazzzystar
Search, read, and create speech-to-text transcripts on-device with the Whisper Notes Mac app.
Promptready MCP
by hydrojwh
Convert PDF/CSV to Markdown with AI-powered OCR via the PromptReady cloud API.
UK Data: Web reader
by co-reliness
Read any web page as clean markdown or text with title, description and links
YouTube Transcripts, original language (Apify)
by rwb3n
YouTube transcripts in the original spoken language, via Apify. Pay per transcript; failures free.
Spoken — questions
Answers built from our own checks of this server.
What can Spoken do?
It exposes 8 tools, read directly from the server on our last check. Among them: follow_podcast, get_balance, get_transcript, list_episodes, list_following, list_new_episodes and 2 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README.
How MCP servers expose tools in the first place →
Is Spoken working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 351 ms. The bar chart above shows every period we have measured.
How do I connect Spoken?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Spoken need an API key?
No. Spoken completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 8 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Spoken?
It answers our handshake in 351 ms on average, which is faster than 39% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.
How many people use Spoken?
The npm package spoken-mcp was installed 105 times in the last week. Week over week that is +18%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Spoken open source?
The code is open source: it is published under the MIT licence, written in Python and 5 stars on GitHub. The licence covers the code in the repository, not the hosted service at spoken.md, which runs on its operator's own terms.