TranscriptLab is an MCP server published by dev.transcriptlab, hosted at api.transcriptlab.dev. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 20 tools, including transcriptlab_get_transcript, transcriptlab_retrieve_transcript, transcriptlab_discover_captions, transcriptlab_search_transcript, transcriptlab_get_job_status.
Turn YouTube videos and audio or video files into searchable, exportable transcripts.
Nothing else in the archive shares these values.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
Get a YouTube transcript. Use when the user gives a YouTube link or video ID and wants the transcript. Default engine=captions reads existing YouTube captions; engine=stt is opt-in speech-to-text (slower, billed per audio minute — 1 credit/min standard, 10 credits/min with speaker labels). Never switch to engine=stt silently: only pass engine=stt when the user explicitly opts in or asks to transcribe the audio. 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. When the source is an attached file or a direct media link, use transcriptlab_transcribe_file or transcriptlab_transcribe_media_url.
| Parameter | 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. |
| tier | string | Speech model tier for engine=stt; normal bills 1 credit/min, premium bills 10 credits/min and supports speaker labels. Defaults to auto. |
| type | string | Caption track type; defaults to any. |
| engine | string | captions (default) reads YouTube caption tracks; stt transcribes the audio (opt-in only, billed per audio minute). |
| format | string | Output format; defaults to json. |
| cleanup | boolean | Strip filler words and stray timestamps from the transcript text. |
| diarize | boolean | Label speakers in the transcript. Requires engine=stt; implies tier=premium. |
| metadata | boolean | Include video metadata when available; defaults to true. |
| speakers | string | Rename diarization labels for engine=stt, e.g. "Speaker 1=Host,Speaker 2=Guest". |
| translate | string | Translate captions to this language when available. |
{
"name": "transcriptlab_get_transcript",
"title": "Get YouTube transcript",
"description": "Get a YouTube transcript. Use when the user gives a YouTube link or video ID and wants the transcript. Default engine=captions reads existing YouTube captions; engine=stt is opt-in speech-to-text (slower, billed per audio minute — 1 credit/min standard, 10 credits/min with speaker labels). Never switch to engine=stt silently: only pass engine=stt when the user explicitly opts in or asks to transcribe the audio. 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. When the source is an attached file or a direct media link, use transcriptlab_transcribe_file or transcriptlab_transcribe_media_url.",
"inputSchema": {
"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})*$",
"description": "Caption language. Omit it to get the video's own language (recommended); set it only to request a specific language."
},
"tier": {
"enum": [
"normal",
"premium",
"auto"
],
"type": "string",
"description": "Speech model tier for engine=stt; normal bills 1 credit/min, premium bills 10 credits/min and supports speaker labels. Defaults to auto."
},
"type": {
"enum": [
"any",
"manual",
"generated"
],
"type": "string",
"description": "Caption track type; defaults to any."
},
"engine": {
"enum": [
"captions",
"stt"
],
"type": "string",
"description": "captions (default) reads YouTube caption tracks; stt transcribes the audio (opt-in only, billed per audio minute)."
},
"format": {
"enum": [
"json",
"text",
"srt",
"vtt"
],
"type": "string",
"description": "Output format; defaults to json."
},
"cleanup": {
"type": "boolean",
"description": "Strip filler words and stray timestamps from the transcript text."
},
"diarize": {
"type": "boolean",
"description": "Label speakers in the transcript. Requires engine=stt; implies tier=premium."
},
"metadata": {
"type": "boolean",
"description": "Include video metadata when available; defaults to true."
},
"speakers": {
"type": "string",
"maxLength": 2048,
"description": "Rename diarization labels for engine=stt, e.g. \"Speaker 1=Host,Speaker 2=Guest\"."
},
"translate": {
"type": "string",
"pattern": "^[a-z]{2,3}(-[a-z0-9]{2,8})*$",
"description": "Translate captions to this language when available."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Get YouTube transcript",
"readOnlyHint": false,
"openWorldHint": true,
"destructiveHint": 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. Pass the same engine/tier/diarize used for the original fetch so the read selects the matching artifact. Reading an already delivered variant is free; a never-before-delivered variant can spend credits like the original request.
| Parameter | 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. |
| tier | string | Speech tier for engine=stt; must match the original fetch. |
| type | string | one of ["any","manual","generated"] |
| engine | string | Selects the captions or speech-to-text artifact; must match the original fetch. |
| format | string | one of ["json","text","srt","vtt"] |
| cleanup | boolean | |
| diarize | boolean | Must match the original fetch; implies tier=premium for engine=stt. |
| metadata |
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.
| Parameter | Type | Description |
|---|---|---|
| url * | string | YouTube video URL or 11-character video ID. |
{
"name": "transcriptlab_discover_captions",
"title": "Discover caption tracks",
"description": "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.",
"inputSchema": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"maxLength": 2048,
"minLength": 1,
"description": "YouTube video URL or 11-character video ID."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Discover caption tracks",
"readOnlyHint": true,
"openWorldHint": true,
"destructiveHint": 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.
| Parameter | 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. |
| tier | string | Speech tier for engine=stt; must match the tier the transcript was fetched with (auto resolves to whichever artifact exists). |
| type | string | one of ["any","manual","generated"] |
| flags | string | Optional regular expression flags. |
| terms | array | Required in keyword mode. |
| engine | string | Search the captions artifact by default; engine=stt searches the speech-to-text transcript instead — use it when the video was transcribed with engine=stt. |
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.
| Parameter | Type | Description |
|---|---|---|
| job_id * | string | Job id returned by transcriptlab_get_transcript. |
{
"name": "transcriptlab_get_job_status",
"title": "Check transcript job",
"description": "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.",
"inputSchema": {
"type": "object",
"required": [
"job_id"
],
"properties": {
"job_id": {
"type": "string",
"maxLength": 128,
"minLength": 1,
"description": "Job id returned by transcriptlab_get_transcript."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Check transcript job",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Read the account plan, remaining credits, and current-period usage, plus upgrade options. Use when the user asks about cost, balance, or limits, or before a credit-spending request.
No parameters.
{
"name": "transcriptlab_get_usage",
"title": "Check TranscriptLab usage",
"description": "Read the account plan, remaining credits, and current-period usage, plus upgrade options. Use when the user asks about cost, balance, or limits, or before a credit-spending request.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"annotations": {
"title": "Check TranscriptLab usage",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Create a hosted Dodo checkout link bound to the user's connected TranscriptLab account (no website sign-in required). Use when the user runs out of credits (insufficient_credits), asks to upgrade, or wants to buy more credits. Choose starter ($3.99/mo for 1,000 monthly credits) or credit_pack ($4.99 one-time for 1,000 non-expiring credits). Always show the returned checkout_url verbatim as a clickable link.
| Parameter | Type | Description |
|---|---|---|
| offer * | string | starter ($3.99/mo for 1,000 monthly credits) or credit_pack ($4.99 one-time for 1,000 non-expiring credits). |
{
"name": "transcriptlab_create_checkout_link",
"title": "Create a checkout link to add credits",
"description": "Create a hosted Dodo checkout link bound to the user's connected TranscriptLab account (no website sign-in required). Use when the user runs out of credits (insufficient_credits), asks to upgrade, or wants to buy more credits. Choose starter ($3.99/mo for 1,000 monthly credits) or credit_pack ($4.99 one-time for 1,000 non-expiring credits). Always show the returned checkout_url verbatim as a clickable link.",
"inputSchema": {
"type": "object",
"required": [
"offer"
],
"properties": {
"offer": {
"enum": [
"starter",
"credit_pack"
],
"type": "string",
"description": "starter ($3.99/mo for 1,000 monthly credits) or credit_pack ($4.99 one-time for 1,000 non-expiring credits)."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Create a checkout link to add credits",
"readOnlyHint": false,
"openWorldHint": true,
"destructiveHint": 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.
| Parameter | 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. |
{
"name": "transcriptlab_list_transcripts",
"title": "List transcript library",
"description": "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.",
"inputSchema": {
"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
},
"annotations": {
"title": "List transcript library",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": 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.
| Parameter | Type | Description |
|---|---|---|
| query | string | Typeahead text; may be empty. |
{
"name": "transcriptlab_mentions",
"title": "Transcript library",
"description": "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.",
"inputSchema": {
"type": "object",
"properties": {
"query": {
"type": "string",
"maxLength": 64,
"description": "Typeahead text; may be empty."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Transcript library",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": 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.
| Parameter | 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. |
{
"name": "transcriptlab_open_audio",
"title": "Transcribe an audio file",
"description": "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.",
"inputSchema": {
"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
},
"annotations": {
"title": "Transcribe an audio file",
"readOnlyHint": false,
"openWorldHint": true,
"destructiveHint": false
}
}Create a signed direct-upload session for an opened audio file. App-facing only: the uploader view calls it, not the model.
| Parameter | Type | Description |
|---|---|---|
| name * | string | |
| bytes * | integer | |
| content_type * | string | Media MIME type. |
{
"name": "transcriptlab_begin_audio_upload",
"title": "Begin audio upload",
"description": "Create a signed direct-upload session for an opened audio file. App-facing only: the uploader view calls it, not the model.",
"inputSchema": {
"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
},
"annotations": {
"title": "Begin audio upload",
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}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.
| Parameter | 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 |
{
"name": "transcriptlab_start_audio_transcription",
"title": "Transcribe uploaded audio",
"description": "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.",
"inputSchema": {
"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
},
"annotations": {
"title": "Transcribe uploaded audio",
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Read the transcript of a file uploaded through the uploader view. A pending transcription reports 202; retry shortly. App-facing only.
| Parameter | Type | Description |
|---|---|---|
| format | string | one of ["json","text","srt","vtt"] |
| upload_id * | string |
{
"name": "transcriptlab_read_audio_transcript",
"title": "Read uploaded-audio transcript",
"description": "Read the transcript of a file uploaded through the uploader view. A pending transcription reports 202; retry shortly. App-facing only.",
"inputSchema": {
"type": "object",
"required": [
"upload_id"
],
"properties": {
"format": {
"enum": [
"json",
"text",
"srt",
"vtt"
],
"type": "string"
},
"upload_id": {
"type": "string",
"maxLength": 64,
"minLength": 1
}
},
"additionalProperties": false
},
"annotations": {
"title": "Read uploaded-audio transcript",
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": 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.
| Parameter | Type | Description |
|---|---|---|
| tab | string | Which launcher tab to show first; defaults to link. |
{
"name": "transcriptlab_open",
"title": "Open TranscriptLab",
"description": "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.",
"inputSchema": {
"type": "object",
"properties": {
"tab": {
"enum": [
"link",
"upload",
"library"
],
"type": "string",
"description": "Which launcher tab to show first; defaults to link."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Open TranscriptLab",
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": 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".
| Parameter | 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. |
{
"name": "transcriptlab_transcribe_file",
"title": "Transcribe an attached audio or video file",
"description": "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\".",
"inputSchema": {
"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
},
"annotations": {
"title": "Transcribe an attached audio or video file",
"readOnlyHint": false,
"openWorldHint": true,
"destructiveHint": 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.
| Parameter | 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. |
{
"name": "transcriptlab_transcribe_media_url",
"title": "Transcribe a direct media link",
"description": "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.",
"inputSchema": {
"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
},
"annotations": {
"title": "Transcribe a direct media link",
"readOnlyHint": false,
"openWorldHint": true,
"destructiveHint": 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.
| Parameter | Type | Description |
|---|---|---|
| format | string | Defaults to json. |
| media_id | string | From transcriptlab_transcribe_media_url. |
| upload_id | string | From transcriptlab_transcribe_file. |
{
"name": "transcriptlab_get_speech_transcript",
"title": "Read a speech-to-text transcript",
"description": "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.",
"inputSchema": {
"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
},
"annotations": {
"title": "Read a speech-to-text transcript",
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": 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.
| Parameter | Type | Description |
|---|---|---|
| url | string | YouTube video URL or 11-character video ID. |
| lang | string | |
| tier | string | Speech tier for engine=stt; auto resolves to whichever artifact exists. |
| engine | string | Download the speech-to-text transcript for a video fetched with engine=stt. |
| format | string | one of ["text","srt","vtt","md","json"] |
| diarize | boolean | Must match the original fetch; requires engine=stt. |
| upload_id | string | Upload id of a transcribed file. |
{
"name": "transcriptlab_export_link",
"title": "Create a download link",
"description": "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.",
"inputSchema": {
"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})*$"
},
"tier": {
"enum": [
"normal",
"premium",
"auto"
],
"type": "string",
"description": "Speech tier for engine=stt; auto resolves to whichever artifact exists."
},
"engine": {
"enum": [
"captions",
"stt"
],
"type": "string",
"description": "Download the speech-to-text transcript for a video fetched with engine=stt."
},
"format": {
"enum": [
"text",
"srt",
"vtt",
"md",
"json"
],
"type": "string"
},
"diarize": {
"type": "boolean",
"description": "Must match the original fetch; requires engine=stt."
},
"upload_id": {
"type": "string",
"maxLength": 64,
"description": "Upload id of a transcribed file."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Create a download link",
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": 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.
| Parameter | Type | Description |
|---|---|---|
| urls * | array | YouTube URLs to transcribe. |
{
"name": "transcriptlab_submit_batch",
"title": "Submit a batch transcript job",
"description": "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.",
"inputSchema": {
"type": "object",
"required": [
"urls"
],
"properties": {
"urls": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 500,
"minItems": 1,
"description": "YouTube URLs to transcribe."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Submit a batch transcript job",
"readOnlyHint": false,
"openWorldHint": true,
"destructiveHint": false
}
}Return per-video results for a batch or channel job. App-facing only. Page with the returned cursor.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | |
| cursor | string | |
| job_id * | string |
{
"name": "transcriptlab_list_job_items",
"title": "List job items",
"description": "Return per-video results for a batch or channel job. App-facing only. Page with the returned cursor.",
"inputSchema": {
"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
},
"annotations": {
"title": "List job items",
"readOnlyHint": true,
"openWorldHint": true,
"destructiveHint": false
}
}Use transcript retrieval only when the user asks for a transcript. First delivery of a transcript variant may use credits. Caption discovery, cached transcript search, job status, usage, and library listing do not deliver transcripts. Offer transcriptlab_open when the user wants to transcribe but has not given a link or file yet. YouTube links use transcriptlab_get_transcript with engine="captions" by default; engine="stt" (speech-to-text, billed per audio minute) is opt-in only — if captions are unavailable, tell the user and ask whether to retry with engine="stt" rather than switching silently. Speech-to-text also works on user-supplied media: when the user attaches an audio or video file, call transcriptlab_transcribe_file; for a direct link to a media file (not YouTube), call transcriptlab_transcribe_media_url; then poll transcriptlab_get_speech_transcript with the returned id. If a file cannot be transcribed that way (too large, unreadable, or the user would rather pick it from disk), call transcriptlab_open with tab "upload" to show the upload view. If credits run low or a call fails with insufficient_credits, offer Starter ($3.99/month for 1,000 credits) or Credit pack ($4.99 one-time for 1,000 non-expiring credits) and call transcriptlab_create_checkout_link to give the user a direct checkout link.
Names, descriptions and schemas were written by the server and are shown as data.
Pattern matches on what the server declares. They show what it says it can do, not what it does.
None yet. Changes appear after a server's second daily check.
| boolean |
| speakers | string | Speaker label renames; must match the original fetch. |
| translate | string | Translation target, if requested for the original fetch. |
{
"name": "transcriptlab_retrieve_transcript",
"title": "Retrieve completed transcript",
"description": "Read a YouTube transcript that is already published for this account, without starting a new fetch. Use it after transcriptlab_get_job_status reports a job done, or to re-open a variant that was delivered before. For a first request use transcriptlab_get_transcript instead. Pass the same engine/tier/diarize used for the original fetch so the read selects the matching artifact. Reading an already delivered variant is free; a never-before-delivered variant can spend credits like the original request.",
"inputSchema": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"maxLength": 2048,
"minLength": 1,
"description": "YouTube video URL or 11-character video ID."
},
"lang": {
"type": "string",
"pattern": "^[a-z]{2,3}(-[a-z0-9]{2,8})*$",
"description": "Caption language. Omit it to get the video's own language (recommended); set it only to request a specific language."
},
"tier": {
"enum": [
"normal",
"premium",
"auto"
],
"type": "string",
"description": "Speech tier for engine=stt; must match the original fetch."
},
"type": {
"enum": [
"any",
"manual",
"generated"
],
"type": "string"
},
"engine": {
"enum": [
"captions",
"stt"
],
"type": "string",
"description": "Selects the captions or speech-to-text artifact; must match the original fetch."
},
"format": {
"enum": [
"json",
"text",
"srt",
"vtt"
],
"type": "string"
},
"cleanup": {
"type": "boolean"
},
"diarize": {
"type": "boolean",
"description": "Must match the original fetch; implies tier=premium for engine=stt."
},
"metadata": {
"type": "boolean"
},
"speakers": {
"type": "string",
"maxLength": 2048,
"description": "Speaker label renames; must match the original fetch."
},
"translate": {
"type": "string",
"pattern": "^[a-z]{2,3}(-[a-z0-9]{2,8})*$",
"description": "Translation target, if requested for the original fetch."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Retrieve completed transcript",
"readOnlyHint": false,
"openWorldHint": true,
"destructiveHint": false
}
}| diarize | boolean | Must match the original fetch; requires engine=stt. |
| pattern | string | Required in regex mode. |
| translate | string |
| max_tokens | integer |
| context_chars | integer |
| target_tokens | integer |
| case_sensitive | boolean |
| overlap_snippets | integer |
{
"name": "transcriptlab_search_transcript",
"title": "Search a cached transcript",
"description": "Search, quote, or slice a transcript already delivered to this account. Use for \"find the part where...\", keyword or regex lookup, or paginating a long transcript into chunks. It never starts a fetch and never charges transcript credits, so it only works on a video already cached here: deliver it first with transcriptlab_get_transcript if it is not. mode chooses the behavior: keyword matches terms, regex matches a pattern, chunk returns sequential sections.",
"inputSchema": {
"type": "object",
"required": [
"url",
"mode"
],
"properties": {
"url": {
"type": "string",
"maxLength": 2048,
"minLength": 1,
"description": "YouTube video URL or 11-character video ID."
},
"lang": {
"type": "string",
"pattern": "^[a-z]{2,3}(-[a-z0-9]{2,8})*$"
},
"mode": {
"enum": [
"keyword",
"regex",
"chunk"
],
"type": "string",
"description": "keyword matches terms, regex matches pattern, chunk returns sequential sections."
},
"tier": {
"enum": [
"normal",
"premium",
"auto"
],
"type": "string",
"description": "Speech tier for engine=stt; must match the tier the transcript was fetched with (auto resolves to whichever artifact exists)."
},
"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."
},
"engine": {
"enum": [
"captions",
"stt"
],
"type": "string",
"description": "Search the captions artifact by default; engine=stt searches the speech-to-text transcript instead — use it when the video was transcribed with engine=stt."
},
"diarize": {
"type": "boolean",
"description": "Must match the original fetch; requires engine=stt."
},
"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
},
"annotations": {
"title": "Search a cached transcript",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}