VocalStack

● Active

com.vocalstack/mcp

Transcribe and translate audio, video and live streams; run live broadcasts in any language.

Connect this server

One click to install, or copy the config below. Suits: Claude Desktop · Cursor.

Add to Cursor Add to VS CodeClaude Desktop / Claude Code: paste the config below.

Or add it manually — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor):

{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@vocalstack/mcp@1.5.9"
      ],
      "env": {
        "VOCALSTACK_API_KEY": "<your VOCALSTACK_API_KEY>"
      }
    }
  }
}
One line, from the terminal
Claude Code
claude mcp add --env VOCALSTACK_API_KEY='<your VOCALSTACK_API_KEY>' --transport stdio mcp -- npx -y @vocalstack/mcp@1.5.9
OpenAI Codex CLI
codex mcp add mcp --env VOCALSTACK_API_KEY='<your VOCALSTACK_API_KEY>' -- npx -y @vocalstack/mcp@1.5.9
VS Code
code --add-mcp '{"name":"mcp","type":"stdio","command":"npx","args":["-y","@vocalstack/mcp@1.5.9"],"env":{"VOCALSTACK_API_KEY":"<your VOCALSTACK_API_KEY>"}}'

Syntax from each client's docs (Claude Code: claude mcp add; Codex: codex mcp add; VS Code: code --add-mcp). Placeholders in angle brackets are values you fill in.

Environment variables
  • VOCALSTACK_API_KEYrequiredsecretAPI key from app.vocalstack.com (Developers, API keys).

A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.

Category
Media & Creative
Version
1.0.14
Registry
active
Published
11/20/2026
Listed in:Official MCP registry ↗how this is checked

Is it safe? Is it maintained?

Serverdex check: Nov 22, 2026

Looks healthy: VocalStack is maintained, open source, hosted endpoint answering without a key.

Maintained
Active
Last commit 2 days ago (Nov 20, 2026), 3 open issues.
Official registry
Active
Published as com.vocalstack/mcp in the official MCP registry, version 1.0.14.
Source
Open source, MIT
Public repository under the MIT licence, 0 stars, 0 forks.
Runs
Local package or hosted
Ships as a local package (npm) that runs on your machine, and as a hosted endpoint at api.vocalstack.com that receives what your client sends it.
Credentials
None needed to connect
The hosted endpoint completed the Serverdex initialize + tools/list handshake with no key (checked Nov 22, 2026); individual tools may still ask for one.
Owner
Unclaimed
Nobody has claimed this page yet; the data above comes from the registry, GitHub and the live check.

Facts only: last commit and licence from GitHub, the entry's status from the official registry, credentials from the live check. Not a code audit — run the security scan on the endpoint yourself and see the status history.

Live check

checked Nov 22, 2026, 10:08 UTCStatus history & uptime →
● Working129 msprotocol 2025-06-18v1.1.0tools

The endpoint answered the MCP handshake as "vocalstack" and listed 15 tools. Answering since Nov 20, 2026.

Context cost ≈ 12k tokens of tool definitions a client loads per conversation (estimate: characters ÷ 4) across 15 tools.

Tools (15)

  • create_transcription12 params

    Start transcribing a finished recording, from a public link or a file sent inline; returns a transcriptionId at once, before any text. Use: audio or video that has ended (a file, podcast episode, YouTube video or public post). A stream playing now: start_broadcast. The result: get_transcription with waitS, no polling needed. Arguments: exactly one source: url, or fileBase64 with filename (over 10 MiB: host the file and give url). startS and endS clip both what is transcribed and what is billed. spokenLanguage helps short or noisy audio; speakerLabels is fixed once created, while summary and shareLink can also be turned on later with update_transcription. Behaviour: VocalStack's servers download the link once, as a visitor who is not signed in; nothing is posted to or changed on the source site. List price: $0.20 an hour of audio, billed per second transcribed; Pay as you go bills at least 5 minutes per transcription. Each call is a new, billed transcription unless it repeats an idempotencyKey; a refused call costs nothing; summary and shareLink are free. New transcriptions an hour per account: 10 on Pay as you go, 100 on Premium. Transcriptions running at once per account: 5 on Pay as you go, 50 on Premium; more wait their turn instead of failing. Returns: transcriptionId, state (queued, fetching, transcribing, then done, failed or stopped), progress, shareUrl when shareLink is true, replayed true for a repeated key. API: POST /v1/transcriptions, documented at https://api.vocalstack.com/docs. Errors: invalid_options (neither or both of url and fileBase64, not a public http(s) link, bad base64, too large), invalid_audio (empty file), idempotency_key_reused, insufficient_credit (with topUpUrl), quota_exceeded, terms_acceptance_required (with acceptUrl: the person opens it and accepts the Terms once, then you call again), rate_limited (with retryAfterS). A source that cannot be read ends in state failed, with error.

    Show parameters
    • endSnumberTranscribe only up to this second (default: the end), at least 0.5 s after startS.
    • fileBase64stringThe whole file in standard base64 (a data: URL prefix and line breaks are accepted), at most 10 MiB decoded; for a larger file give url instead. mp3, m4a, wav,
    • filenamestringWith fileBase64 only: the file's name with its extension, also the default display name.
    • idempotencyKeystringAny unique string of visible ASCII. Retrying with the same key and the same arguments within 24 h returns the first result (with replayed true) and nothing is c
    • mimeTypestringWith fileBase64 only, optional: the file's media type when known.
    • namestringDisplay name shown in lists and on the share page. Defaults to the file name or the link.
    • shareLinkbooleanMake a public link anyone can open to read the transcript without signing in (shareUrl in the result). Off: it stays private to this account.
    • speakerLabelsstringauto labels lines once a second speaker is heard, on labels every line, off none. Recordings under a minute are never labelled.
    • spokenLanguagestringCode of the language spoken, e.g. en, ro, es. Omit to detect it (recordings that switch language are handled too); set it for better accuracy on short or noisy
    • startSnumberTranscribe only from this second (default: the start). Only the part transcribed is billed: startS 90 and endS 600 bill 8.5 minutes.
    • summarybooleanAlso write a title and summary when it is done, at no extra cost (get_transcription with format summary reads it). Never for recordings under a minute.
    • urlstringPublic http(s) link to the recording: an audio or video file, a YouTube video, or a public post on Twitch, Facebook, Instagram, Vimeo, Dailymotion, TikTok, X, S
  • get_transcription7 params

    Read or export one transcription: its status and text with timestamps and speakers, its title and summary, or the whole transcript as an SRT, WebVTT or Markdown file; as spoken or translated, at once or after waiting for it to finish. Use: after create_transcription (waitS saves polling), or any time during a live transcription for the text so far. An overview: format summary. Subtitles or a document to save: format srt, vtt or markdown. Finding a passage in many transcriptions: search_transcriptions. Behaviour: free. A wait ends as soon as the work does, and sends progress notifications when the client gives a progress token. lang needs a finished transcription; the first call in a new language can take up to a minute on a long one, later pages are quick. Page with offset = nextOffset. Returns: status (state, progress, error when failed, shareUrl when it has a public link: made with shareLink in create_transcription or update_transcription), timedOut when waitS was set, then segmentCount, partial while text is still coming, text or segments, nextOffset when more remain, and lang and translated with lang. format summary returns summary instead: state ready with title and summary (and lang when translated), pending while it is written or the transcription runs, none when none was asked for (update_transcription with summary true writes one), not_requested under a minute, unavailable when it failed. format srt, vtt or markdown returns file (fileName, contentType, content: the whole file as text, partial while it runs) instead of text. A wait that runs out with lang set returns the status only. Errors: not_found; invalid_state for lang before it is finished; invalid_options for an unsupported lang or includeWords with lang; rate_limited (with retryAfterS) when waitS is set and 4 waits are already open for this key (8 for the account), or past 600 calls a minute per API key.

    Show parameters
    • formatstringtext: one string, a line per segment as "[mm:ss] Speaker 1: words", for reading and quoting; segments: timed lines (start, end, text, speakerNumber, speakerName
    • includeWordsbooleanWith format segments and no lang: also each word with its start and end second. It makes the answer several times larger, so ask for a narrow page (e.g. limit 5
    • langstringCode of a language to read the whole text (or, with format summary, the summary) in, one of about 100 (e.g. es, de, ja): the transcription must be finished (sta
    • limitintegerMost segments in one call. When more are left the result has nextOffset.
    • offsetintegerIndex of the first segment to return (0, the start, by default). To page, pass the nextOffset the previous call returned.
    • transcriptionIdstringrequiredA transcriptionId from create_transcription, list_transcriptions, search_transcriptions or start_broadcast.
    • waitSintegerSeconds to wait for a file or link transcription to finish before answering, 0 to 60 (0, the default: answer at once). Returns as soon as it ends; timedOut true
  • list_transcriptions3 params

    List this account's transcriptions, newest first, a page at a time: files, links and live ones, including those broadcasts recorded. Use: to find a transcriptionId by when it was made or see what exists. Which tool: list_transcriptions browses by date; search_transcriptions finds what was said; get_transcription reads one whose id you have. Broadcasts: list_broadcasts. Behaviour: free. Ordered by creation time, so pages are stable: transcriptions made or deleted while paging never repeat or shift another out of its page. lifecycle archived lists the trash: deleted transcriptions, restorable for 30 days with update_transcription restore true. A cursor this tool did not give out is refused. Returns: transcriptions (transcriptionId, name, createdAt, kind file or live, state, durationS and title when known, broadcastId for a broadcast's), and nextCursor while more remain. None: an empty list. Errors: invalid_options for an unknown cursor; rate_limited (with retryAfterS) past 600 calls a minute per API key.

    Show parameters
    • cursorstringOmit for the first page (the newest). For the next page, pass the previous call's nextCursor unchanged, with the same lifecycle.
    • lifecyclestringWhich transcriptions: active those in use, archived those in the trash, all both.
    • limitintegerMost transcriptions in one page.
  • search_transcriptions5 params

    Find what was said across this account's transcriptions, or in one: the lines with given words or a name (mode words), or the passages that answer a question (mode meaning). Use: words when you know what was said; meaning for a question or topic, in any language. Not for browsing by date (list_transcriptions) or reading a whole transcript (get_transcription with its id). Text around a hit: get_transcription with offset. One transcription's overview: get_transcription with format summary. Arguments: query is phrased differently per mode: a few words or a name for words, a whole question for meaning. transcriptionId narrows either mode to one transcription; lang and limit go with words only, and lang changes only how hits are shown, never which lines match. Examples: {query: "budget"}; {query: "What did they decide about hiring?", mode: "meaning"}; {query: "Maria", transcriptionId, lang: "es"}. Behaviour: free; no paging. words ranks whole words first, then close spellings, then newest, and searches the query's English translation too, and finds a line once it is final, so the last seconds of a live transcription may not show yet. The trash is never searched. meaning returns up to 10 passages, closest first, and covers finished recordings only (they are indexed after they end). Searches by meaning an hour per account: 60 on Pay as you go, no limit on Premium. Returns: words: query, queryEn, hits (transcriptionId, name, mediaStart in seconds, speaker, text, score, live, recordedAt, rendered with lang). meaning: query, state (ready, or unavailable or off when it cannot run), passages (transcriptionId, name, mediaStart, mediaEnd, text, similarity 0 to 1, live), searchesLeftThisHour when capped. Cite the transcription and second. No match: an empty list. Errors: not_found for an unknown transcriptionId; invalid_options for lang or limit with mode meaning; rate_limited (with retryAfterS) past the hourly searches by meaning.

    Show parameters
    • langstringmode words only, optional language code: each hit also comes back translated into it, as rendered. It never changes what matches.
    • limitintegermode words only: most lines to return, best first. There is no next page: narrow the query or set transcriptionId.
    • modestringwords: the lines where these words or a close spelling were said ("presupuesto" also finds "budget"). meaning: the passages closest in meaning, even with none o
    • querystringrequiredmode words: words, a phrase or a name that was said. mode meaning: a question or topic in plain words; a full question works better than one keyword. Any langua
    • transcriptionIdstringSearch only this transcription (a transcriptionId from list_transcriptions or create_transcription). Omit to search the whole account.
  • update_transcription7 params

    Change a transcription: its name, its public share link, its summary, whether spoken translations use the speakers' own cloned voices, or bring it back from the trash. Use: renaming, sharing or unsharing, asking for a summary later, switching cloned voices, or restoring one deleted by mistake. Only the fields given change; give at least one. Speaker names: update_speaker. Removing it: delete_transcription. Arguments: transcriptionId (required). name 1 to 200 characters. shareLink true makes a public read-only link (or keeps the one it has), false turns every public link off. summary true writes a title and summary if it has none (a finished transcription of at least a minute). clonedVoices true needs consent true, recording that everyone speaking agreed to be cloned; false needs no consent. restore true brings a deleted transcription back first, then applies the rest (a deleted broadcast: update_broadcast with restore). Behaviour: free; calling again with the same fields changes nothing. A link turned off cannot be turned back on: shareLink true afterwards makes a new address. With cloned voices on, each speaker's translated words are read in that speaker's own voice, never anyone else's; speakers who refused, or without a usable clone, keep a stock voice; lines read after the change use it. Returns: transcriptionId, name, shareUrl (null with no public link), summary (state ready, pending, not_requested or unavailable) when asked for, clonedVoices, restored with restore. Errors: invalid_options for no field to change, a bad name, summary or restore false, or clonedVoices true without consent; invalid_state for a deleted transcription without restore true, or summary before it is finished; not_found once erased after the restore window; not_found; forbidden for a read-only key.

    Show parameters
    • clonedVoicesbooleantrue: translations of each speaker's own words are read aloud in that speaker's own cloned voice (needs consent true); false: stock voices.
    • consentbooleanMust be true with clonedVoices true: confirms everyone speaking in it agreed to have their voice cloned. Recorded with your account and the time. Not needed to
    • namestringNew display name, shown in lists and on the share page; trimmed, 1 to 200 characters.
    • restorebooleantrue: bring it back from the trash (after delete_transcription, within the restore window) with everything it had; other fields given apply after. false is not
    • shareLinkbooleantrue: make a public link anyone can open to read the transcript without signing in (an existing one is kept; shareUrl in the result). false: every public link o
    • summarybooleantrue: write a title and summary now if it has none (free; the transcription must be finished and at least a minute long). Read it with get_transcription format
    • transcriptionIdstringrequiredA transcriptionId from create_transcription, list_transcriptions, search_transcriptions or start_broadcast.
  • delete_transcription1 param

    Move a transcription to the trash, with its recordings, transcript, translations and summary; its share links stop working. Use: to remove one; undo with update_transcription restore true (list_transcriptions with lifecycle archived lists the trash). Saved speakers stay (delete_speaker). A broadcast itself: delete_broadcast. Arguments: transcriptionId only: the transcriptionId field returned by create_transcription, list_transcriptions, search_transcriptions or start_broadcast, a 36-character UUID, upper or lower case. Not a name (look it up with search_transcriptions), a broadcastId or a speakerId (not_found), nor the code in a share link (invalid_options: it must be a UUID). Behaviour: free; a soft delete kept 30 days, then erased for good. At once its share links answer not found, voices reading its translations stop, and it leaves list_transcriptions and search_transcriptions; restoring brings back the same links. A file still being transcribed is stopped and keeps its text so far, billed only for that; restoring does not resume it. A live one must be stopped first (update_broadcast with onAir false on its broadcast). One already in the trash is left as it is, so a retry is safe. Needs a key or token with the write scope; a read-only one is refused before anything changes. Gives rate_limited (with retryAfterS) past 600 calls a minute per API key. Returns: transcriptionId, name, deleted, deletedAt, restorableUntil. Errors: invalid_state while recording live or when locked; not_found; forbidden for a read-only key.

    Show parameters
    • transcriptionIdstringrequiredA transcriptionId from list_transcriptions or create_transcription.
  • list_speakers

    List the speakers this account has saved: people recognised by name in every new transcription. Use: to see who is known, before saving someone (update_speaker with save), or to find a speakerId for update_speaker or delete_speaker. Names inside one transcription come from get_transcription. Behaviour: free; no paging. Returns: speakers, newest first, each with id, name, gender when known, cloned (their voice was cloned, with consent, to read translations of their own words) and, when cloned, voiceReady. None saved: an empty list.

  • update_speaker7 params

    Name or save a speaker, with two kinds of target: a person in one transcription (transcriptionId + speaker number: name them instead of "Speaker N", and with save true create a saved speaker so later transcriptions recognise them; this is the create-a-speaker tool, there is no separate one), or a saved speaker (speakerId: rename, switch their cloned voice on or off, everywhere they are recognised). Use: labelling who spoke here; remembering a person across transcriptions (save true); correcting a saved speaker's name or turning their cloned voice on with their consent. Who is saved: list_speakers. Forgetting someone: delete_speaker. Arguments: give exactly one target: transcriptionId with speaker (the number in "Speaker 2" from get_transcription, not a name or an id) and name, plus save and consent; or speakerId (from list_speakers) with name, clonedVoice or both. A name in a transcription is cut to 80 characters and an empty one undoes it; a saved speaker's, or one with save, is 1 to 60. clonedVoice true needs consent true. Examples: {transcriptionId, speaker: 2, name: "Maria Lopez"}; {transcriptionId, speaker: 2, name: "Maria Lopez", save: true}; {speakerId, clonedVoice: true, consent: true}. Behaviour: free; calling again replaces the name and saves no one twice. In a transcription it applies to that person in every recording of it, and listeners following live see it at once; their speaker number never changes. save keeps their voice fingerprint (and, with consent, clones their voice from their speech here, voiceState training then ready); the person must have spoken, and a live transcription can still be running. clonedVoice true clones a saved speaker from their stored sample if they have no clone yet; false keeps the clone, unused (delete_speaker erases it). Nothing else about the person changes. Returns: transcriptionId, speaker, name (null when cleared), and with save speakerId, saved (false when they were already saved), consent, cloned and voiceState; or,

    Show parameters
    • clonedVoicebooleanWith speakerId only: true reads translations of this person's own words in their own cloned voice (needs consent true; cloned from their stored sample if not ye
    • consentbooleantrue only when this person agreed to have their voice cloned: needed with clonedVoice true, and with save it clones them too, from their own speech in this tran
    • namestringThe name to show instead of "Speaker N", trimmed: up to 80 characters in one transcription (an empty string clears it back to "Speaker N"), 1 to 60 for a saved
    • savebooleanWith transcriptionId and speaker only: true also saves this person to the account's saved speakers, so later transcriptions recognise and name them; their own s
    • speakerintegerWith transcriptionId: the N of "Speaker N" in get_transcription's text, or speakerNumber in its segments; it stays the same after naming.
    • speakerIdstringInstead of transcriptionId and speaker: a saved speaker's id (id in list_speakers, or speakerId from update_speaker with save), changed everywhere they are reco
    • transcriptionIdstringWith speaker: the transcription the speaker is in (from create_transcription, list_transcriptions, search_transcriptions or start_broadcast). Leave out with spe
  • delete_speaker1 param

    Delete a saved speaker for good: their name, fingerprint, stored sample and any cloned voice are erased at once and cannot be restored. Use: the person should no longer be recognised, or asked for their voice to be removed. A name inside one transcription: update_speaker. Arguments: speakerId only: the id field from list_speakers, or the speakerId update_speaker returned with save. A speaker number such as 2 (from "Speaker 2") or a transcriptionId is wrong here; to unname someone in one transcription, use update_speaker with an empty name instead. Example: {speakerId: "0190f0e0-7c1a-7d3e-9b2a-5f4e3d2c1b0a"}. Behaviour: free; the erasure is complete before the call returns, with no trash and no undo. Transcripts keep every line they spoke and their speaker numbers; lines that showed the saved name show "Speaker N" again. From then on new and running transcriptions no longer recognise them, and translations of their words read aloud use a stock voice instead of their clone. The id is never reused: saving the same person again (update_speaker with save) gives a new speakerId and needs their consent again to clone. A repeat call answers not_found and changes nothing. Gives rate_limited (with retryAfterS) past 600 calls a minute per API key. Returns: speakerId, deleted true. Errors: not_found for an unknown or already deleted id, or one of another account; forbidden for a read-only key.

    Show parameters
    • speakerIdstringrequiredA saved speaker's id: id in list_speakers, or speakerId from update_speaker with save.
  • list_broadcasts1 param

    List this account's broadcasts with their status. A broadcast is a public link where listeners follow a live transcription in their own language. Use: to find a broadcastId, or see which are on air right now. For one broadcast's recorded transcriptions and streams, call get_broadcast with its id; for what was said, get_transcription with a transcriptionId (broadcasts' recordings are also in list_transcriptions). Arguments: lifecycle only, and it is optional: active (the default) for broadcasts in use, archived for those in the trash (deleted within the restore window, restorable with update_broadcast restore true), all for both. Examples: {} lists the active ones; {lifecycle: "archived"} shows what can still be restored. Behaviour: free and read-only; most recently updated first, up to 500 per lifecycle in one call, with no paging: with more than 500 in that lifecycle, the 500 most recently updated come back, and an older one is still reachable by id with get_broadcast. rate_limited (with retryAfterS) past 600 calls a minute per API key. Returns: broadcasts (broadcastId, name, link, access, onAir, listenersNow, lastRecordedAt once it has recorded, archived for one in the trash; while on air transcriptionId, state, onAirSince). None: an empty list. Errors: invalid_options for an unknown lifecycle.

    Show parameters
    • lifecyclestringWhich broadcasts: active those in use, archived those in the trash, all both.
  • get_broadcast1 param

    Get one broadcast in detail: its status, link and settings, the transcriptions it has recorded, and the streams it has used. Use: before a run to check its settings and link, during one to see listeners and the live transcriptionId, after to find what it recorded. All broadcasts: list_broadcasts. The text: get_transcription with a transcriptionId from here. Arguments: broadcastId only: the broadcastId field from list_broadcasts or start_broadcast, a 36-character UUID, upper or lower case. A broadcast in the trash is returned too (archived true, restorable with update_broadcast restore true). Not a transcriptionId (not_found), and not the short code at the end of the link listeners open (invalid_options: it must be a UUID). Example: {broadcastId: "0190f0e0-7c1a-7d3e-9b2a-5f4e3d2c1b0a"}. Behaviour: free and read-only; listenersNow is counted at the moment of the call. Gives rate_limited (with retryAfterS) past 600 calls a minute per API key. Returns: broadcastId, name, link, access, onAir, listenersNow, lastRecordedAt; while on air transcriptionId, state, onAirSince; transcriptions (up to 20, newest first: transcriptionId, name, recording, lastRecordedAt) and streams (name, url). Errors: not_found for an unknown broadcastId (or one erased after the restore window); invalid_options for something that is not a UUID.

    Show parameters
    • broadcastIdstringrequiredThe broadcast's id.
  • start_broadcast6 params

    Start a broadcast: live transcription and translation of a stream playing now, on a public link listeners open in their own language. Also the tool that creates a broadcast (without a stream: set up ahead, off air). Use: when the event is live now, or beforehand to get the link to share. A recording that has ended, even a past live stream's file: create_transcription. Reading it while it runs: get_transcription. Arguments: streamUrl must be live when called; the same streamUrl on the same broadcast reuses its stream. Without streamUrl (and without broadcastId) it only sets up a new broadcast, off air and free: its link can be shared and configured with update_broadcast before the event. broadcastId (from list_broadcasts or get_broadcast) reruns an existing broadcast on its old link, and then name is ignored; without it a new broadcast is made, named name or the stream's host. spokenLanguage is a code like en (omit to detect). spokenTranslations true adds audio of each translation. List price: $0.60 an hour while it runs, billed per second; Pay as you go bills at least 5 minutes per transcription. Listeners and translations are free. Transcriptions running at once per account: 5 on Pay as you go, 50 on Premium; past that a start is refused with quota_exceeded. Behaviour: not idempotent, as annotated: every call with streamUrl starts a new billed run (set up only: free, nothing runs), and without broadcastId makes a new broadcast with a new link. To make a retry safe after a timeout, pass idempotencyKey: the same key and arguments within 24 h return the first run (replayed true) and bill nothing more. VocalStack's servers pull the stream as a visitor who is not signed in; nothing is posted to or changed at the source. Listeners on the link see each line within seconds of it being said, translated into the language they pick, with no account; the text is kept as a transcription. A run lasts until update_broadcast with onAir false or the stream ends, and billing stops a

    Show parameters
    • broadcastIdstringOptional: run it on this existing broadcast (from list_broadcasts), so its listeners' link stays the same. Omit to make a new broadcast with a new link.
    • idempotencyKeystringAny unique string of visible ASCII. Retrying with the same key and the same arguments within 24 h returns the first result (with replayed true) and nothing is s
    • namestringName of a new broadcast, shown to listeners. Defaults to the stream's host. Ignored with broadcastId.
    • spokenLanguagestringCode of the language spoken, e.g. en, es. Omit to detect it.
    • spokenTranslationsbooleanAlso read each translation aloud, so listeners can hear it in their language as well as read it. Listening stays free.
    • streamUrlstringhttp(s) address of a stream playing now: a YouTube live, an internet radio station, an HLS (.m3u8) or Icecast stream. Omit it (and broadcastId) to only set up a
  • update_broadcast10 params

    Change a broadcast: end its live run (onAir false), or its settings: its name, who can listen (public, or private behind a listener code VocalStack makes), the language spoken, and whether translations are read aloud, in stock or the speakers' own cloned voices; or bring it back from the trash. Use: to end the event when it is over (onAir false), or before or between runs to change settings; settings apply from the next start_broadcast, the name and access at once. Only the fields given change; give at least one. Starting a run: start_broadcast; removing the broadcast and its link: delete_broadcast. Arguments: broadcastId (required); the rest are independent and optional, except that newListenerCode goes only with a private broadcast and clonedVoices only with spokenTranslations on, needing consent true. No code is ever passed in: VocalStack makes it, so it never sits in the model's arguments. restore true brings a deleted broadcast back first, then applies the rest. Examples: {broadcastId, onAir: false} (ends the run); {broadcastId, access: "private"} (returns listenerCode); {broadcastId, newListenerCode: true}; {broadcastId, spokenTranslations: true, clonedVoices: true, consent: true}; {broadcastId, restore: true}. Behaviour: the link and broadcastId never change; no call here makes a new address (for one: delete_broadcast, then start_broadcast without broadcastId). Changing access or the listener code signs out every current listener at once, even on air: their page asks for the link again (and the code when private), and they miss the lines spoken until they are back; the transcript is kept. Making it public again lets anyone with the link in, with no sign-in. The name shows to listeners at once; language and voice settings never touch a run in progress. Ending a run (onAir false) is free and final for that run: billing stops at that moment, listeners see the broadcast is over, and the transcript is kept (get_transcription reads it and its summary once done); it

    Show parameters
    • accessstringpublic: anyone with the link can follow it; private: listeners must enter the broadcast's listener code, which VocalStack makes the first time it goes private a
    • broadcastIdstringrequiredA broadcastId from list_broadcasts or start_broadcast.
    • clonedVoicesbooleanWith spokenTranslations: true reads each speaker's translated words in that speaker's own cloned voice (needs consent true); false: stock voices.
    • consentbooleanMust be true with clonedVoices true: confirms everyone speaking on it agreed to have their voice cloned. Recorded with your account and the time. Not needed to
    • namestringNew name shown to listeners; trimmed, 1 to 120 characters.
    • newListenerCodebooleantrue: VocalStack makes a new listener code for a private broadcast and returns it once as listenerCode, signing out every current listener (share the new one wi
    • onAirbooleanfalse: end the live run now, which stops its billing; the transcript is kept and the link stays for the next start_broadcast. Already off air: nothing changes.
    • restorebooleantrue: bring it back from the trash (after delete_broadcast, within the restore window) with its link, settings and recorded transcriptions; other fields given a
    • spokenLanguagestringCode of the language spoken (e.g. en, es), or auto to detect it. Applies from the next start_broadcast.
    • spokenTranslationsbooleantrue: each translation is also read aloud, so listeners can hear it in their language; false: text only. Applies from the next start_broadcast. Listening stays
  • delete_broadcast1 param

    Move a broadcast to the trash: its public link and stream addresses stop working for listeners. Use: a broadcast that will not run again. For 30 days update_broadcast with restore true brings it back with the same link (list_broadcasts with lifecycle archived lists the trash); after that the broadcast is erased for good. Ending a live run: update_broadcast with onAir false. Arguments: broadcastId only, from list_broadcasts or start_broadcast, upper or lower case. A transcriptionId is not_found (delete_transcription removes a recording); the short code in the link is invalid_options. Example: {broadcastId: "0190f0e0-7c1a-7d3e-9b2a-5f4e3d2c1b0a"}. Behaviour: free, and a soft delete: nothing is erased for 30 days, and one already in the trash is left as it is, so a retry is safe. At once every connected listener is signed out. A broadcast on air is refused: end its run first (update_broadcast with onAir false). The transcriptions it recorded are not deleted: while it is in the trash they leave list_transcriptions and search_transcriptions, get_transcription still reads them by id, and delete_transcription deletes one. Restoring (update_broadcast with restore true) brings back the same link and broadcastId, its settings and its transcriptions; listeners get back in by opening the link again (with the same listener code when private). Gives rate_limited (with retryAfterS) past 600 calls a minute per API key. Returns: broadcastId, name, deleted true, deletedAt, restorableUntil. Errors: invalid_state while on air; not_found for an unknown broadcastId; invalid_options for something that is not a UUID; forbidden for a read-only key.

    Show parameters
    • broadcastIdstringrequiredA broadcastId from list_broadcasts or start_broadcast, of a broadcast that is not on air.
  • Check the account's credit and usage: the balance left, the plan, whether a new file or live transcription would start now (and what would refuse it), and this period's limits. Use: before a long or live transcription, after an insufficient_credit or quota_exceeded error, or to tell the user what they have left. Prices per minute are in create_transcription and start_broadcast; adding credit happens at topUpUrl, in a browser. Arguments: none. Behaviour: free and read-only; nothing is cached, each call reads the account as it is at that moment, including a live run still being billed. Calling it changes nothing and spends nothing. Gives rate_limited (with retryAfterS) past 600 calls a minute per API key. Returns: billingEnabled; plan (id, name, kind) or null; balance in US dollars (negative while a plan lets a running transcription continue below zero); canStart and startBlock (no_credit or hourly_limit, null when it starts) for a file; canStartLive and startBlockLive (also concurrency) for a live one; running, concurrentLimit, createdLastHour and createLimit (null means unlimited); period (start, end); monthlyCredit when a plan grants one; usageCap (amount, period, used, resetsAt) when this API key has a spending cap; topUpUrl; for a signed-in person termsAccepted, and while false acceptUrl: a page where they accept the Terms of Service and Privacy Policy themselves, once, before their first transcription. Errors: rate_limited (with retryAfterS); forbidden for a token without the read scope.

Checked by Serverdex with a plain initialize + tools/list call to api.vocalstack.com/v1/mcp, no credentials, about once a day. A failed check is never a removal.

On GitHub

read Nov 21, 2026
Stars
0
Forks
0
Last push
Nov 20, 2026
License
MIT

JavaScriptlive-captionsmcpmcp-servermodel-context-protocolspeech-to-texttranscriptiontranslationvocalstack

From the README

@vocalstack/mcp VocalStack's MCP server. It runs on your machine (stdio) and works with VocalStack's public API using your API key, so any MCP client can transcribe, translate, search and summarize audio and video, and run live broadcasts that listeners follow in their own language. API key Create a key at app.vocalstack.com under Developers → API keys, and pass it as VOCALSTACKAPIKEY. Without a key the server still starts and lists its tools, but every tool call asks you to set one. Only transcription is billed, per second of audio. Reading, searching, summaries, translations and listeners are free. Setup Requires Node.js 20 or later. Claude Desktop Add this to claudedesktopconfig.json (Settings → Developer → Edit Config), then restart Claude Desktop: Cursor Add the same block to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (one project). Windsurf Add the same block to ~/.codeium/windsurf/mcp_config.json, then refresh the MCP servers in Windsurf's settings. Claude Code Hosted alternative Clients that support remote MCP servers can use VocalStack's hosted endpoint instead, with no install and no API key: add https://api.vocalstack.com/v1/mcp and sign in with your VocalStack account when the client asks.…

Read the full README on GitHub →

Remotes

  • streamable-httphttps://api.vocalstack.com/v1/mcp

The most-starred Media & Creative servers in the index, with their live-check result.

ServerStarsLast pushLive check
HyperFrames by HeyGen87,943Nov 2026Needs sign-in
HyperFrames by HeyGen86,475Nov 2026Needs sign-in
Pascal 3D Editor25,651Nov 2026Needs sign-in
screenpipe22,421Nov 2026Local / not checked
FunASR21,097Nov 2026Local / not checked

VocalStack: questions people ask

Is VocalStack a remote or a local MCP server?
According to its entry in the official MCP registry, VocalStack ships as a hosted endpoint (streamable-http) that your client connects to by URL and as a local package (npm) that your client starts on your machine. Use the hosted endpoint when your client supports Streamable HTTP; use the package when you want it to run locally.
Does VocalStack need an API key?
Its hosted endpoint completed the Serverdex live check — an MCP initialize + tools/list call — with no credentials on Nov 22, 2026. Individual tools may still ask for a key when called.
Is VocalStack safe to use?
Looks healthy: VocalStack is maintained, open source, hosted endpoint answering without a key. In detail — maintained: Active; official registry: Active; source: Open source, MIT; runs: Local package or hosted; credentials: None needed to connect. Serverdex check of Nov 22, 2026. This is a reading of the repository, the registry entry and the live check, not a code audit; run the Serverdex security scan on the endpoint before trusting it with real data.
Is VocalStack still maintained?
Active: the repository's last commit 2 days ago. Last push Nov 20, 2026, 0 GitHub stars, MIT licence. Read from GitHub on Nov 21, 2026.
What tools does VocalStack expose?
15 tools as listed by the server itself during the live check, including create_transcription, get_transcription, list_transcriptions, search_transcriptions, update_transcription. The full list with parameters is in the Live check section above.
How do I add VocalStack to Claude, Cursor or VS Code?
Copy the config in "Connect this server" into your client's MCP config file (claude_desktop_config.json, ~/.cursor/mcp.json or .vscode/mcp.json), or use the one-click Add to Cursor / Add to VS Code buttons and the one-line commands for Claude Code and Codex; then restart the client.
Browse all Media & Creative →

Add the badge to your site

Show visitors that VocalStack is listed here — it’s also the link we check for a free listing.

VocalStack — listed on Serverdex

HTML — for your website

<a href="https://serverdex.io/server/com-vocalstack-mcp?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="VocalStack — listed on Serverdex" width="123" height="40" loading="lazy"></a>

Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.

Markdown — for your README

[![VocalStack — listed on Serverdex](https://serverdex.io/brand/badge.svg)](https://serverdex.io/server/com-vocalstack-mcp?utm_source=badge)

Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.

Add to CursorAdd to VS CodeOpen in Claude Code

Install buttons — for your README

[![Add to Cursor](https://serverdex.io/brand/install-cursor.svg)](https://serverdex.io/install/cursor/com-vocalstack-mcp) [![Add to VS Code](https://serverdex.io/brand/install-vscode.svg)](https://serverdex.io/install/vscode/com-vocalstack-mcp) [![Open in Claude Code](https://serverdex.io/brand/install-claude-code.svg)](https://serverdex.io/install/claude-code/com-vocalstack-mcp)

One click opens Cursor or VS Code with this server's config prefilled; the Claude Code button lands on the one-line command. The links point at Serverdex, so when your config changes the buttons keep working.

Install buttons — HTML for your docs

<a href="https://serverdex.io/install/cursor/com-vocalstack-mcp"><img src="https://serverdex.io/brand/install-cursor.svg" alt="Add to Cursor — via Serverdex" width="140" height="28"></a>
<a href="https://serverdex.io/install/vscode/com-vocalstack-mcp"><img src="https://serverdex.io/brand/install-vscode.svg" alt="Add to VS Code — via Serverdex" width="147" height="28"></a>
<a href="https://serverdex.io/install/claude-code/com-vocalstack-mcp"><img src="https://serverdex.io/brand/install-claude-code.svg" alt="Open in Claude Code — via Serverdex" width="180" height="28"></a>

Same buttons as plain links for a docs page or website.

Prefer a live badge with the score, stars and live check? Score badge (links to a page that explains the number and back to this listing).