MCP App Store
by KeenEthics
Transcript LOL icon

Transcript LOL MCP Server for Claude and ChatGPT

By Omnivision

Overview

Transcript LOL turns audio and video into accurate, speaker-labelled transcripts — meetings, customer calls, interviews, podcasts, lectures and more, in dozens of languages. This connector gives Claude OAuth-scoped access to your Transcript.lol workspaces so you can work with your recordings without leaving the conversation. What Claude can do with it: • Find recordings by what was said — semantic or exact search across every transcript, filtered by folder, speaker or date, with timestamps for each hit. • Read transcripts and translations — the full text, a specific time window, or SRT/VTT/JSON with timestamps. • Reuse existing AI insights — pull summaries, action items, key points and any custom prompt output already generated, or run one of your workspace's prompt templates to generate a new insight. • Start new work — submit a public audio/video URL for transcription, or request a translation into another language, then poll until it's ready. • Keep the library organised — rename recordings, create and rename folders, move recordings, and label diarized speakers with named people. Example prompts: • "Summarise yesterday's customer call and list the action items." • "Find the meeting where we discussed pricing and quote the exact wording." • "Pull the key decisions from every interview in the Q3 Research folder." • "Transcribe this podcast episode and give me the five main takeaways." Every tool runs under the connected user's own permissions: Claude only sees the workspaces and recordings that account can already access, and read-only tools are annotated so Claude can browse safely. Requires a Transcript.lol plan with API access.

How to connect

  1. Claude: Open the Transcript LOL listing in the Claude connectors directory and choose Connect. Claude listing Transcript LOL exposes 23 tools here.
  2. ChatGPT: Open the Transcript LOL listing in the ChatGPT app directory and choose Connect. ChatGPT listing Transcript LOL exposes 23 tools here.

Tools

assign_speaker

ChatGPT
Label a transcript's diarization speakerIndex (from list_transcript_speakers) with a named speaker (speakerId from list_speakers). Updates the recording's transcript and every labelled view of it.

create_folder

ChatGPT
Create a folder in a workspace to organize recordings. Optionally nest it under a parent folder. File recordings into it with move_recordings_to_folder.

create_prompt

ChatGPT
Create a new insight prompt template in a workspace — useful when a task needs an insight no existing prompt covers. Returns the new prompt's id; pass it to generate_insight to run it against a recording. The prompt is saved to the workspace's library and does NOT run automatically on future transcriptions. Check list_prompts first to avoid creating a duplicate.

create_speaker

ChatGPT
Create a new named speaker in a workspace. Use this while labelling a transcript when the person isn't already in list_speakers. Returns the new speaker's id — pass it to assign_speaker to label a diarization speakerIndex with it.

generate_insight

ChatGPT
Generate an insight for a recording by running one of the workspace's prompt templates against its transcript. Generation is asynchronous: this returns immediately with the new insight in 'QUEUED' status — poll get_insights and read the item with the returned id until its status is 'IDLE' (finished, content populated) or 'FAILED'. Discover promptIds with list_prompts. This consumes the account's AI-generation credits and may require a paid plan.

get_insights

ChatGPT
Fetch the AI-generated insights already produced for a recording — the curated summaries, action items, key points and other outputs from the workspace's insight prompts. Prefer this over re-summarizing the raw transcript yourself: it reuses the prompts the user configured and the work the product already did, into far less context. Returns each insight's prompt title, generated content, and status. Use list_prompts + generate_insight to produce an insight that doesn't exist yet.

get_recording

ChatGPT
Fetch a single recording's metadata, including its transcription status. Use this to check whether a transcript is ready before calling get_transcript. To see the recording's translations, use list_translations.

get_transcript

ChatGPT
Fetch the transcript of a completed recording. Call this when the user wants to read, summarize, quote, analyze, or answer questions about a recording or meeting. Returns readable plain text by default; use 'srt'/'vtt' for subtitles or 'json' for timestamped paragraphs. Optionally pass startTime/endTime to fetch only a time window (e.g. the minutes around a search hit) instead of the whole transcript.

get_translation

ChatGPT
Fetch a translated transcript, in the same formats as get_transcript ('text' by default, or 'json'/'srt'/'vtt'). Get the translationId from list_translations; the translation must have finished (status 'COMPLETE'). Optionally pass startTime/endTime to fetch only a time window. This returns the translation only — use get_transcript for the original-language transcript.

list_folders

ChatGPT
List the folders in a workspace (id, name, parentFolderId). Use this to discover folderIds for the folderIds filter on list_recordings or search_recordings.

list_prompts

ChatGPT
List the insight prompt templates available in a workspace (id, title, and whether it auto-generates when a recording finishes transcribing). Pass a prompt's id to generate_insight to run that template against a recording.

list_recordings

ChatGPT
List recordings in a workspace, most recent first. Use this to browse a workspace and find recordingIds. Supports cursor pagination via the returned next_cursor / prev_cursor.

list_speakers

ChatGPT
List the named speakers in a workspace (id, name, role). Use this to resolve a person's name to a speakerId for the speakerIds filter on search_recordings.

list_transcript_speakers

ChatGPT
List the distinct speakers a recording's transcript was diarized into, by speakerIndex, with each one's current assignment (assignedSpeakerName is null when unassigned), how many words they spoke, and a sample of their words. Use this to work out who each speakerIndex is, then label them with assign_speaker.

list_translations

ChatGPT
List the translations of a recording's transcript (id, language, status). Use this to discover which languages a transcript has been translated into; pass a translation's id to get_translation to read it, or request a new language with translate_recording.

list_workspaces

ChatGPT
List the transcript.lol workspaces (spaces) the authenticated user can access. Call this first to obtain the workspaceId required by the other tools.

move_recordings_to_folder

ChatGPT
File one or more recordings into a folder. Omit folderId to move them out of any folder, back to the workspace root. Discover folders with list_folders, or create one with create_folder.

rename_folder

ChatGPT
Rename a folder.

rename_recording

ChatGPT
Change a recording's title.

search_recordings

ChatGPT
Search the transcripts in a workspace to find a recording or moment by what was said (e.g. "the call where we discussed pricing"). Defaults to semantic search (finds results by meaning, even when the exact words differ); pass mode:"exact" for literal keyword matching. Optionally narrow by folder, speaker, or date. Returns matching snippets with their recording, start/end timestamps (in seconds), and speaker names.

transcribe_url

ChatGPT
Submit a public audio/video URL (e.g. a podcast, MP3, or video link) to be transcribed in a workspace. Transcription runs asynchronously — poll get_recording for its status, then call get_transcript once complete. This consumes the account's transcription allowance and may require a paid plan.

translate_recording

ChatGPT
Request a translation of a recording's transcript into another language. The recording must have finished transcribing. Translation runs asynchronously — this returns immediately with the translation in a pending status; poll list_translations until its status is 'COMPLETE', then read it with get_translation. This consumes the account's translation allowance and may require a paid plan.

unassign_speaker

ChatGPT
Remove the named-speaker assignment from a transcript's diarization speakerIndex, reverting it to the generic "Speaker N" label.

assign_speaker

Claude

create_folder

Claude

create_prompt

Claude

create_speaker

Claude

generate_insight

Claude

get_insights

Claude

get_recording

Claude

get_transcript

Claude

get_translation

Claude

list_folders

Claude

list_prompts

Claude

list_recordings

Claude

list_speakers

Claude

list_transcript_speakers

Claude

list_translations

Claude

list_workspaces

Claude

move_recordings_to_folder

Claude

rename_folder

Claude

rename_recording

Claude

search_recordings

Claude

transcribe_url

Claude

translate_recording

Claude

unassign_speaker

Claude

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/transcript-lol"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/transcript-lol)