Turn YouTube videos and audio or video files into searchable, exportable transcripts.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Create a signed direct-upload session for an opened audio file. App-facing only: the uploader view calls it, not the model.
Media MIME type.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http transcriptlab https://api.transcriptlab.dev/mcp
Create a signed direct-upload session for an opened audio file. App-facing only: the uploader view calls it, not the model.
| Argument | Type | Description |
|---|---|---|
| name* | string | |
| bytes* | integer | |
| content_type* | string | Media MIME type. |
{
"type": "object",
"required": [
"name",
"bytes",
"content_type"
],
"properties": {
"name": {
"type": "string",
"maxLength": 256,
"minLength": 1
},
"bytes": {
"type": "integer",
"maximum": 2000000000,
"minimum": 1
},
"content_type": {
"type": "string",
"pattern": "^(audio|video)/",
"description": "Media MIME type."
}
},
"additionalProperties": false
}List the caption languages and track types (manual vs generated) available for a YouTube video. Use when the user asks which languages or subtitles a video has, or before transcriptlab_get_transcript when they want a specific language. Free in transcript credits, but subject to the account monthly discovery limit.
| Argument | Type | Description |
|---|---|---|
| url* | string | YouTube video URL or 11-character video ID. |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"maxLength": 2048,
"minLength": 1,
"description": "YouTube video URL or 11-character video ID."
}
},
"additionalProperties": false
}Create a 10-minute signed download link (TXT, SRT, VTT, Markdown, or JSON) for a transcript the account already has, or for a transcribed upload. Call this when the user wants a file or a link to a file: hand them the returned url and say it expires in 10 minutes. Needs a signed-in connection. The launcher Download action calls it too, so a host that cannot start a download itself still gives the user the link.
| Argument | Type | Description |
|---|---|---|
| url | string | YouTube video URL or 11-character video ID. |
| lang | string | |
| format | string | |
| upload_id | string | Upload id of a transcribed file. |
{
"type": "object",
"properties": {
"url": {
"type": "string",
"maxLength": 2048,
"description": "YouTube video URL or 11-character video ID."
},
"lang": {
"type": "string",
"pattern": "^[a-z]{2,3}(-[a-z0-9]{2,8})*$"
},
"format": {
"enum": [
"text",
"srt",
"vtt",
"md",
"json"
],
"type": "string"
},
"upload_id": {
"type": "string",
"maxLength": 64,
"description": "Upload id of a transcribed file."
}
},
"additionalProperties": false
}Check whether a transcript job from transcriptlab_get_transcript has finished. Use it when that tool returned a job_id instead of a transcript. Returns status only, delivers no transcript, and spends no credits; once it reports done, read the text with transcriptlab_retrieve_transcript.
| Argument | Type | Description |
|---|---|---|
| job_id* | string | Job id returned by transcriptlab_get_transcript. |
{
"type": "object",
"required": [
"job_id"
],
"properties": {
"job_id": {
"type": "string",
"maxLength": 128,
"minLength": 1,
"description": "Job id returned by transcriptlab_get_transcript."
}
},
"additionalProperties": false
}Read the speech-to-text transcript started by transcriptlab_transcribe_file (pass upload_id) or transcriptlab_transcribe_media_url (pass media_id). Pass exactly one id. While transcription runs it returns a pending result: wait a few seconds, back off, and stop after about ten tries; if it is still pending, tell the user the job is queued instead of looping. Reading does not start new work or add charges.
| Argument | Type | Description |
|---|---|---|
| format | string | Defaults to json. |
| media_id | string | From transcriptlab_transcribe_media_url. |
| upload_id | string | From transcriptlab_transcribe_file. |
{
"type": "object",
"properties": {
"format": {
"enum": [
"json",
"text",
"srt",
"vtt"
],
"type": "string",
"description": "Defaults to json."
},
"media_id": {
"type": "string",
"maxLength": 64,
"description": "From transcriptlab_transcribe_media_url."
},
"upload_id": {
"type": "string",
"maxLength": 64,
"description": "From transcriptlab_transcribe_file."
}
},
"additionalProperties": false
}Get a YouTube transcript from existing captions. Use when the user gives a YouTube link or video ID and wants the transcript. Returns the transcript, or a job id when the request outlives the synchronous window: if a job comes back, poll transcriptlab_get_job_status, then read the text with transcriptlab_retrieve_transcript. The first delivery of each transcript variant can spend credits; later deliveries of that variant are free. Captions only: when the user asks which caption tracks exist use transcriptlab_discover_captions; when the video has no captions, or the source is an attached file or a direct media link, use transcriptlab_transcribe_file or transcriptlab_transcribe_media_url.
| Argument | Type | Description |
|---|---|---|
| url* | string | YouTube video URL or 11-character video ID. |
| also | array | Additional formats to include in a JSON response. |
| lang | string | Caption language. Omit it to get the video's own language (recommended); set it only to request a specific language. |
| type | string | Caption track type; defaults to any. |
| format | string | Output format; defaults to json. |
| cleanup | boolean | Strip filler words and stray timestamps from the caption text. |
| metadata | boolean | Include video metadata when available; defaults to true. |
Read the account plan, remaining credits, and current-period usage. Use when the user asks about cost, balance, or limits, or before a credit-spending request.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}Return per-video results for a batch or channel job. App-facing only. Page with the returned cursor.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| cursor | string | |
| job_id* | string |
{
"type": "object",
"required": [
"job_id"
],
"properties": {
"limit": {
"type": "integer",
"maximum": 100,
"minimum": 1
},
"cursor": {
"type": "string"
},
"job_id": {
"type": "string",
"maxLength": 64,
"minLength": 1
}
},
"additionalProperties": false
}List YouTube videos whose transcripts were already delivered to this account, most recent first. Use it to find or reopen an earlier transcript. It fetches nothing and delivers no transcript. When more results exist, page with the returned cursor.
| Argument | Type | Description |
|---|---|---|
| limit | integer | Page size; defaults to the server default. |
| cursor | string | Opaque cursor returned by the previous page. |
| search | string | Optional video ID or title filter. |
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"maximum": 100,
"minimum": 1,
"description": "Page size; defaults to the server default."
},
"cursor": {
"type": "string",
"maxLength": 2048,
"description": "Opaque cursor returned by the previous page."
},
"search": {
"type": "string",
"maxLength": 64,
"description": "Optional video ID or title filter."
}
},
"additionalProperties": false
}Composer at-mention search over the account’s transcript library, used to build the @TranscriptLab picker. App-facing only: the host calls it, it returns resource links rather than transcript text, and the model should not call it.
| Argument | Type | Description |
|---|---|---|
| query | string | Typeahead text; may be empty. |
{
"type": "object",
"properties": {
"query": {
"type": "string",
"maxLength": 64,
"description": "Typeahead text; may be empty."
}
},
"additionalProperties": false
}Open the TranscriptLab launcher view, where the user can work with transcripts visually and send one into the chat with "Discuss in chat". Use tab "upload" when a file needs the uploader: the user wants to pick a local audio or video file, the attached file is too large or could not be read by transcriptlab_transcribe_file, or that upload failed. Use "library" to reopen earlier transcripts, and "link" (the default) to paste a YouTube link. Also offer it when the user wants a transcript but has given no link or file.
| Argument | Type | Description |
|---|---|---|
| tab | string | Which launcher tab to show first; defaults to link. |
{
"type": "object",
"properties": {
"tab": {
"enum": [
"link",
"upload",
"library"
],
"type": "string",
"description": "Which launcher tab to show first; defaults to link."
}
},
"additionalProperties": false
}Entry point the host invokes when the user opens an audio or video file with this plugin: opens the uploader view and starts speech-to-text. You do not call this directly; for a file attached to the conversation use transcriptlab_transcribe_file.
| Argument | Type | Description |
|---|---|---|
| file* | object | Host-provided handle for the opened file. |
| diarize | boolean | Label speakers; defaults to false. Implies tier=premium and 10 credits per audio minute. |
{
"type": "object",
"required": [
"file"
],
"properties": {
"file": {
"type": "object",
"required": [
"name",
"resourceUri"
],
"properties": {
"name": {
"type": "string"
},
"resourceUri": {
"type": "string"
}
},
"description": "Host-provided handle for the opened file."
},
"diarize": {
"type": "boolean",
"description": "Label speakers; defaults to false. Implies tier=premium and 10 credits per audio minute."
}
},
"additionalProperties": false
}Read the transcript of a file uploaded through the uploader view. A pending transcription reports 202; retry shortly. App-facing only.
| Argument | Type | Description |
|---|---|---|
| format | string | |
| upload_id* | string |
{
"type": "object",
"required": [
"upload_id"
],
"properties": {
"format": {
"enum": [
"json",
"text",
"srt",
"vtt"
],
"type": "string"
},
"upload_id": {
"type": "string",
"maxLength": 64,
"minLength": 1
}
},
"additionalProperties": false
}Read a YouTube transcript that is already published for this account, without starting a new fetch. Use it after transcriptlab_get_job_status reports a job done, or to re-open a variant that was delivered before. For a first request use transcriptlab_get_transcript instead. Reading an already delivered variant is free; a never-before-delivered variant can spend credits like the original request.
| Argument | Type | Description |
|---|---|---|
| url* | string | YouTube video URL or 11-character video ID. |
| lang | string | Caption language. Omit it to get the video's own language (recommended); set it only to request a specific language. |
| type | string | |
| format | string | |
| cleanup | boolean | |
| metadata | boolean | |
| translate | string | Translation target, if requested for the original fetch. |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"maxLength": 2048,
"minLength": 1,
"description": "YouTube video URL or 11-character video ID."
},
"lang": {
"type": "string",
"pattern": "^[a-z]{2,3}(-[a-z0-9]{2,8})*$",
"description": "Caption language. Omit it to get the video's own language (recommended); set it only to request a specific language."
},
"type": {
"enum": [
"any",
"manual",
"generated"
],
"type": "string"
},
"format": {
"enum": [
"json",
"text",
"srt",
"vtt"
],
"type": "string"
},
"cleanup": {
"type": "boolean"
},
"metadata": {
"type": "boolean"
},
"translate": {
"type": "string",
"pattern": "^[a-z]{2,3}(-[a-z0-9]{2,8})*$",
"description": "Translation target, if requested for the original fetch."
}
},
"additionalProperties": false
}Search, quote, or slice a transcript already delivered to this account. Use for "find the part where...", keyword or regex lookup, or paginating a long transcript into chunks. It never starts a fetch and never charges transcript credits, so it only works on a video already cached here: deliver it first with transcriptlab_get_transcript if it is not. mode chooses the behavior: keyword matches terms, regex matches a pattern, chunk returns sequential sections.
| Argument | Type | Description |
|---|---|---|
| url* | string | YouTube video URL or 11-character video ID. |
| lang | string | |
| mode* | string | keyword matches terms, regex matches pattern, chunk returns sequential sections. |
| type | string | |
| flags | string | Optional regular expression flags. |
| terms | array | Required in keyword mode. |
| pattern | string | Required in regex mode. |
| translate | string |
Finalize a signed upload and start speech-to-text on it. App-facing only: the uploader view calls it once the file is uploaded. Spends credits per audio minute.
| Argument | Type | Description |
|---|---|---|
| tier | string | Speech model tier; defaults to auto (normal when available). |
| diarize | boolean | Label speakers; defaults to false. Implies tier=premium. |
| upload_id* | string |
{
"type": "object",
"required": [
"upload_id"
],
"properties": {
"tier": {
"enum": [
"normal",
"premium",
"auto"
],
"type": "string",
"description": "Speech model tier; defaults to auto (normal when available)."
},
"diarize": {
"type": "boolean",
"description": "Label speakers; defaults to false. Implies tier=premium."
},
"upload_id": {
"type": "string",
"maxLength": 64,
"minLength": 1
}
},
"additionalProperties": false
}Queue a list of YouTube URLs as one batch job and return its job id. App-facing only. The plan caps how many URLs one job accepts.
| Argument | Type | Description |
|---|---|---|
| urls* | array | YouTube URLs to transcribe. |
{
"type": "object",
"required": [
"urls"
],
"properties": {
"urls": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 500,
"minItems": 1,
"description": "YouTube URLs to transcribe."
}
},
"additionalProperties": false
}Transcribe an audio or video file the user attached to this conversation, using speech-to-text (mp3, m4a, wav, mp4, webm and similar). Use it for an attached media file; YouTube links use transcriptlab_get_transcript instead. Spends credits per audio minute. Attachments up to 300 MB work here; larger files (up to 2 GB) use the launcher upload view. Stores the file, starts transcription, and returns an upload_id: poll transcriptlab_get_speech_transcript with it, waiting a few seconds between tries and stopping after about ten. Do not call this again for the same file. If it fails or the file is too large, call transcriptlab_open with tab "upload".
| Argument | Type | Description |
|---|---|---|
| file* | object | The attached media file. |
| tier | string | Speech model tier; defaults to auto (normal when available). |
| diarize | boolean | Label speakers; defaults to false. Implies tier=premium. |
{
"type": "object",
"required": [
"file"
],
"properties": {
"file": {
"type": "object",
"required": [
"download_url",
"file_id"
],
"properties": {
"file_id": {
"type": "string",
"maxLength": 256
},
"file_name": {
"type": "string",
"maxLength": 512
},
"mime_type": {
"type": "string",
"maxLength": 256
},
"download_url": {
"type": "string",
"maxLength": 4096
}
},
"description": "The attached media file.",
"additionalProperties": false
},
"tier": {
"enum": [
"normal",
"premium",
"auto"
],
"type": "string",
"description": "Speech model tier; defaults to auto (normal when available)."
},
"diarize": {
"type": "boolean",
"description": "Label speakers; defaults to false. Implies tier=premium."
}
},
"additionalProperties": false
}Transcribe a public https link to an audio or video file with speech-to-text. Use it for a direct media URL (ending in .mp3, .m4a, .wav, .mp4, .webm and similar); not for YouTube or other web pages, which use transcriptlab_get_transcript. Spends credits per audio minute. Returns a media_id: poll transcriptlab_get_speech_transcript with it, waiting a few seconds between tries and stopping after about ten.
| Argument | Type | Description |
|---|---|---|
| url* | string | Public https URL of an audio or video file. |
| tier | string | Speech model tier; defaults to auto (normal when available). |
| diarize | boolean | Label speakers; defaults to false. Implies tier=premium. |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"maxLength": 2048,
"minLength": 1,
"description": "Public https URL of an audio or video file."
},
"tier": {
"enum": [
"normal",
"premium",
"auto"
],
"type": "string",
"description": "Speech model tier; defaults to auto (normal when available)."
},
"diarize": {
"type": "boolean",
"description": "Label speakers; defaults to false. Implies tier=premium."
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 17, 2026.
| translate | string | Translate captions to this language when available. |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"maxLength": 2048,
"minLength": 1,
"description": "YouTube video URL or 11-character video ID."
},
"also": {
"type": "array",
"items": {
"enum": [
"srt",
"vtt",
"text"
],
"type": "string"
},
"maxItems": 3,
"description": "Additional formats to include in a JSON response."
},
"lang": {
"type": "string",
"pattern": "^[a-z]{2,3}(-[a-z0-9]{2,8})*$",
"description": "Caption language. Omit it to get the video's own language (recommended); set it only to request a specific language."
},
"type": {
"enum": [
"any",
"manual",
"generated"
],
"type": "string",
"description": "Caption track type; defaults to any."
},
"format": {
"enum": [
"json",
"text",
"srt",
"vtt"
],
"type": "string",
"description": "Output format; defaults to json."
},
"cleanup": {
"type": "boolean",
"description": "Strip filler words and stray timestamps from the caption text."
},
"metadata": {
"type": "boolean",
"description": "Include video metadata when available; defaults to true."
},
"translate": {
"type": "string",
"pattern": "^[a-z]{2,3}(-[a-z0-9]{2,8})*$",
"description": "Translate captions to this language when available."
}
},
"additionalProperties": false
}| max_tokens | integer |
| context_chars | integer |
| target_tokens | integer |
| case_sensitive | boolean |
| overlap_snippets | integer |
{
"type": "object",
"required": [
"url",
"mode"
],
"properties": {
"url": {
"type": "string",
"maxLength": 2048,
"minLength": 1,
"description": "YouTube video URL or 11-character video ID."
},
"lang": {
"type": "string",
"pattern": "^[a-z]{2,3}(-[a-z0-9]{2,8})*$"
},
"mode": {
"enum": [
"keyword",
"regex",
"chunk"
],
"type": "string",
"description": "keyword matches terms, regex matches pattern, chunk returns sequential sections."
},
"type": {
"enum": [
"any",
"manual",
"generated"
],
"type": "string"
},
"flags": {
"type": "string",
"maxLength": 8,
"description": "Optional regular expression flags."
},
"terms": {
"type": "array",
"items": {
"type": "string",
"maxLength": 200
},
"maxItems": 50,
"description": "Required in keyword mode."
},
"pattern": {
"type": "string",
"maxLength": 512,
"description": "Required in regex mode."
},
"translate": {
"type": "string",
"pattern": "^[a-z]{2,3}(-[a-z0-9]{2,8})*$"
},
"max_tokens": {
"type": "integer",
"maximum": 4096,
"minimum": 1
},
"context_chars": {
"type": "integer",
"maximum": 1000,
"minimum": 0
},
"target_tokens": {
"type": "integer",
"maximum": 4096,
"minimum": 1
},
"case_sensitive": {
"type": "boolean"
},
"overlap_snippets": {
"type": "integer",
"maximum": 20,
"minimum": 0
}
},
"additionalProperties": false
}