tl;dv

tl;dv

Let your AI read your tl;dv meeting recordings: find meetings from Google Meet, Zoom and Teams, read the AI notes, topics and full transcripts, and with your confirmation import a recording from a link.

7 дней бесплатно · без карты · EU-хостинг

Спроси tl;dv что угодно

Попробуй реальный промпт против tl;dv via AnythingMCP — Claude вызывает tools, возвращает ответ. Нажми Enter на своём сообщении, чтобы установить в Cloud.

Установить tl;dv в Cloud
tl;dv · live via MCP
Поделиться
Opus 4.7

Claude — это AI, он может ошибаться. Проверяйте ответы.

Настройка за 2 минуты

  1. 1Запусти free trial на cloud.anythingmcp.com.
  2. 2Нажми tl;dv в коннектор-сторе. Вставь учётные данные.
  3. 3Выпусти MCP API ключ и направьте AI-клиент на MCP URL.
Установить tl;dv сейчас

Гиды по tl;dv

Пошаговая настройка для основных AI-клиентов.

Настройка tl;dv

Прямо из определения коннектора: где взять учётные данные, какие права им нужны и с каким API работает этот адаптер. Предоставлено автором коннектора на английском языке.

tl;dv

This connector reads tl;dv, the meeting recorder for Google Meet, Zoom and Microsoft Teams, through the tl;dv public API (https://pasta.tldv.io, version v1alpha1) with a personal API key: recorded meetings, tl;dv's AI notes and topics, and the full transcripts. It can also import a recording from a link.

Setup (about 2 minutes)

  1. Sign in to tl;dv and open Settings, Personal settings, API keys (https://tldv.io/app/settings/personal-settings/api-keys).
  2. Generate a key and paste it into TLDV_API_KEY. It is sent in the x-api-key header and only to tl;dv.
  3. Check the setup with tldv_list_meetings.

Which meetings the API can reach: the key acts as its user, and tl;dv only exports meetings whose organizer (the person who sent the calendar invite) has a paid plan (Pro, Business or Enterprise). A meeting the user can see in the app but that was organised by someone on the free plan is not exported, even when it was shared: it is missing from the list or answers 403.

Recordings and transcripts are personal data. They hold what colleagues, customers and other participants said, with their names and email addresses. Only fetch what the user's question needs, prefer the AI notes over the full transcript, and do not copy transcripts to other systems unless the user asks for it.

How to work

  1. Find meetings: tldv_list_meetings with a search word (query), a date range (from, to), meeting_type internal or external, or only_participated. The answer has page, pages and total; ask for the next page while it is below pages.
  2. tldv_get_meeting for one meeting's details, tldv_get_notes for the AI notes and topics.
  3. tldv_get_transcript for what was said, 700 lines at a time as [start second, speaker, text]; when totalLines is above 700, tldv_get_transcript_more gives lines 701 to 1400. tl;dv has no further paging.
  4. tldv_import_meeting brings in a recording from a public link and creates a new meeting: confirm the link and the name with the user first. Use dry_run to test.

Errors

  • 401 AuthorizationRequiredError or UnauthorizedError: the key is missing, wrong or revoked; generate a new one.
  • 403: the meeting's organizer has no paid plan, or the user may not export it.
  • 404 NotFoundError: wrong meeting id, or no transcript or notes yet.
  • 400: a parameter has the wrong format; the message names it (meeting ids are 24 hexadecimal characters).

Out of scope here: downloading the recording file (the API answers with a redirect to the file itself), uploading a file in parts, and webhooks (MeetingReady and TranscriptReady are set up in tl;dv's settings, not through this API).

Твой AI в двух кликах от tl;dv.

Установи коннектор, вставь учётные данные, спроси AI. 7 дней бесплатно, без карты.