Spoken
Podcast transcripts as clean Markdown with real speaker names — via the Spoken API.
사용해야 할까요
품질 및 안전성
도구 정의와 프로토콜 준수에 대한 자동 분석을 기반으로 합니다.
컨텍스트 비용
이는 서버의 도구가 모델의 컨텍스트에 로드될 때마다 소비되는 대략적인 토큰 수입니다. 수치가 높을수록 다른 작업에 사용할 수 있는 주의가 줄어듭니다.
설치
원클릭 설치
`claude_desktop_config.json` 파일에 다음을 추가하세요:
{
"mcpServers": {
"spoken": {
"command": "npx",
"args": [
"spoken-mcp"
]
}
}
}실행 가능한 패키지
0.4.3stdio원격 엔드포인트
https://spoken.md/mcpstreamable-http할 수 있는 일
도구 목록
도구 (8)
🟢search_podcasts(query)
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.
입력 스키마
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"description": "Free text (e.g. 'huberman sleep') or a pasted episode URL."
}
},
"required": [
"query"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}출력 스키마
{
"type": "object",
"properties": {
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Episode id; pass it to get_transcript."
},
"title": {
"type": "string"
},
"date": {
"type": "string",
"description": "Release date, ISO 8601."
},
"podcast_id": {
"type": "string",
"description": "Show id; pass it to list_episodes or follow_podcast."
},
"podcast": {
"type": "string",
"description": "Show name."
}
},
"required": [
"id",
"title",
"date",
"podcast_id",
"podcast"
],
"additionalProperties": false
}
}
},
"required": [
"results"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_transcript(episode_id)
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.
입력 스키마
{
"type": "object",
"properties": {
"episode_id": {
"type": "string",
"minLength": 1,
"description": "Episode id returned by search_podcasts."
}
},
"required": [
"episode_id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢list_episodes(podcast_id)
List a podcast's entire back-catalog (every episode, newest first). Pass a podcast_id from a search_podcasts result. Returns each episode's id, title, and date — fetch any with get_transcript. Use this to transcribe a whole show. Does not consume credits itself; transcribing the returned episodes costs 1 credit each (repeat fetches are free), so make sure the key has enough credits before looping.
입력 스키마
{
"type": "object",
"properties": {
"podcast_id": {
"type": "string",
"minLength": 1,
"description": "Show id (the podcast_id field from a search_podcasts result)."
}
},
"required": [
"podcast_id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}출력 스키마
{
"type": "object",
"properties": {
"podcast_id": {
"type": "string",
"description": "Show id; pass it to list_episodes or follow_podcast."
},
"podcast": {
"type": "string",
"description": "Show name."
},
"count": {
"type": "number",
"description": "Episodes listed; fetching all of them costs up to this many credits."
},
"episodes": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Episode id; pass it to get_transcript."
},
"title": {
"type": "string"
},
"date": {
"type": "string",
"description": "Release date, ISO 8601."
}
},
"required": [
"id",
"title",
"date"
],
"additionalProperties": false
}
}
},
"required": [
"podcast_id",
"podcast",
"count",
"episodes"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_balance
Check the current Spoken credit balance, account email, and recent usage for the configured API key. Does not consume credits.
입력 스키마
{
"type": "object",
"properties": {},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}출력 스키마
{
"type": "object",
"properties": {
"credits": {
"type": "number",
"description": "Credits remaining; one is spent per first fetch of an episode."
},
"email": {
"description": "Account email, when one is attached to the key.",
"type": "string"
},
"usage": {
"type": "object",
"properties": {
"total": {
"type": "number",
"description": "Episodes fetched with this key."
},
"recent": {
"type": "array",
"items": {
"type": "object",
"properties": {
"episodeId": {
"type": "string"
},
"accessedAt": {
"type": "string"
}
},
"required": [
"episodeId",
"accessedAt"
],
"additionalProperties": false
},
"description": "The 50 most recent fetches."
}
},
"required": [
"total",
"recent"
],
"additionalProperties": false
}
},
"required": [
"credits",
"usage"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢list_following
The shows this key is kept current on. Every charged fetch makes its show a follow: the five most-fetched shows from the last 180 days are followed automatically (source 'fetch'), and up to 25 more can be declared with follow_podcast (source 'explicit'). Muted shows are listed separately. Use list_new_episodes to see what is new on them. Does not consume credits; the demo key has nothing to follow with.
입력 스키마
{
"type": "object",
"properties": {},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}출력 스키마
{
"type": "object",
"properties": {
"following": {
"type": "array",
"items": {
"type": "object",
"properties": {
"podcast_id": {
"type": "string",
"description": "Show id; pass it to list_episodes or follow_podcast."
},
"podcast": {
"type": "string",
"description": "Show name."
},
"source": {
"type": "string",
"enum": [
"fetch",
"explicit"
],
"description": "'fetch': followed automatically from fetches. 'explicit': declared with follow_podcast."
},
"fetch_count": {
"type": "number",
"description": "Episodes of this show fetched."
},
"last_fetched_at": {
"type": "string"
},
"newest_fetched_id": {
"description": "Newest episode fetched; list_new_episodes lists what came after it.",
"type": "string"
}
},
"required": [
"podcast_id",
"podcast",
"source",
"fetch_count"
],
"additionalProperties": false
}
},
"muted": {
"type": "array",
"items": {
"type": "object",
"properties": {
"podcast_id": {
"type": "string",
"description": "Show id; pass it to list_episodes or follow_podcast."
},
"podcast": {
"type": "string",
"description": "Show name."
}
},
"required": [
"podcast_id",
"podcast"
],
"additionalProperties": false
}
},
"limits": {
"type": "object",
"properties": {
"explicit": {
"type": "number",
"description": "Most shows that can be declared with follow_podcast."
},
"inferred": {
"type": "number",
"description": "Shows followed automatically from fetches."
},
"inferred_window_days": {
"type": "number"
}
},
"required": [
"explicit",
"inferred",
"inferred_window_days"
],
"additionalProperties": false
}
},
"required": [
"following",
"muted",
"limits"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🔴follow_podcast(podcast_id)
Declare a follow for a show, or clear a mute. Pass a podcast_id from search_podcasts. A declared follow stays until unfollow_podcast, regardless of fetch activity, and does not use one of the five automatic slots. For a show never fetched, what counts as new starts from its newest episode now. Does not consume credits.
입력 스키마
{
"type": "object",
"properties": {
"podcast_id": {
"type": "string",
"minLength": 1,
"description": "Show id (the podcast_id field from a search_podcasts result)."
}
},
"required": [
"podcast_id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}출력 스키마
{
"type": "object",
"properties": {
"podcast_id": {
"type": "string",
"description": "Show id; pass it to list_episodes or follow_podcast."
},
"podcast": {
"type": "string",
"description": "Show name."
},
"state": {
"type": "string",
"enum": [
"following",
"muted"
]
}
},
"required": [
"podcast_id",
"podcast",
"state"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟡unfollow_podcast(podcast_id)
Mute a show: it leaves the followed list and later fetches do not re-add it. follow_podcast reverses it. Pass a podcast_id from list_following. Does not consume credits.
입력 스키마
{
"type": "object",
"properties": {
"podcast_id": {
"type": "string",
"minLength": 1,
"description": "Show id, from list_following or search_podcasts."
}
},
"required": [
"podcast_id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}출력 스키마
{
"type": "object",
"properties": {
"podcast_id": {
"type": "string",
"description": "Show id; pass it to list_episodes or follow_podcast."
},
"podcast": {
"type": "string",
"description": "Show name."
},
"state": {
"type": "string",
"enum": [
"following",
"muted"
]
}
},
"required": [
"podcast_id",
"podcast",
"state"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢list_new_episodes
What is new on the shows this key follows: for each show, the episodes released in the last 90 days that are newer than the newest one already fetched from it (up to 10 per show), each with a transcript_url. Episodes with no transcript are left out. Fetch any with get_transcript (1 credit each on first fetch); a fetch raises that show's floor, so the next call lists only what came after. Refreshed hourly, so a show followed moments ago may be empty until its first poll. Does not consume credits.
입력 스키마
{
"type": "object",
"properties": {},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}출력 스키마
{
"type": "object",
"properties": {
"as_of": {
"type": "string",
"description": "When the list was read, ISO 8601."
},
"count": {
"type": "number",
"description": "New episodes across all followed shows."
},
"shows": {
"type": "array",
"items": {
"type": "object",
"properties": {
"podcast_id": {
"type": "string",
"description": "Show id; pass it to list_episodes or follow_podcast."
},
"podcast": {
"type": "string",
"description": "Show name."
},
"source": {
"type": "string",
"enum": [
"fetch",
"explicit"
],
"description": "'fetch': followed automatically from fetches. 'explicit': declared with follow_podcast."
},
"episodes": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Episode id; pass it to get_transcript."
},
"title": {
"type": "string"
},
"date": {
"type": "string",
"description": "Release date, ISO 8601."
},
"transcript_url": {
"type": "string"
}
},
"required": [
"id",
"title",
"date",
"transcript_url"
],
"additionalProperties": false
}
}
},
"required": [
"podcast_id",
"podcast",
"source",
"episodes"
],
"additionalProperties": false
}
}
},
"required": [
"as_of",
"count",
"shows"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}커뮤니티
증거