tl;dv
Read tl;dv meeting recordings, transcripts and AI notes, and import external recordings, over the tl;dv Public API (v1alpha1, alpha).
About
tl;dv ships in the w6w first-party pack. It declares 5 actions, 3 health checks, and the host runs its code in a sandbox that never sees the credential.
- App id
io.w6w.tldv- Version
- 0.1.1
- Author
- w6w
- Licence
- MIT
- Categories
- AI & Machine Learning · Productivity · Video & Streaming
Overview
tl;dv brings AI meeting recordings into a workflow — listing and searching meetings, reading full transcripts and AI-generated notes, and importing recordings captured outside tl;dv’s own bots. Meeting actions list and filter meetings by participation, date range or type, and read a specific meeting’s details, while transcript and notes actions return the AI-generated output only once tl;dv has finished processing a call.
Programmatic API access follows the plan of whichever person organized the meeting, not the plan of whoever generated the API key — so a workflow’s visibility into a given meeting depends on who called it, which is worth knowing when a query returns fewer meetings than expected in the tl;dv web app. The import action lets a workflow bring an externally-recorded meeting into tl;dv as a background job, checked afterward through the meeting list rather than returned synchronously.
This app is built on tl;dv’s own labeled “alpha” API, and covers meetings, transcripts, notes and import rather than tl;dv’s separate webhook-driven integrations, which are a different kind of surface entirely.
Build with tl;dv
Three routes to the same 5 actions. The Workflow tab is generated from tl;dv's own manifest and carries its real ids, so it is copy-pasteable; the Code and CLI examples are the same call for any action on any app, so every app-specific value in them is a blank you fill in.
A workflow step names the app and the action, and the editor fills in the
connection when you pick one. This is the Step shape from the
workflow spec, carrying tl;dv's real ids.
{
"manifestVersion": "2",
"name": "tldv-example",
"steps": [
{
"id": "meeting-get",
"uses": {
"app": "io.w6w.tldv",
"action": "meeting-get",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"meetingId": "<meetingId>"
}
}
]
}Here are some of the things you can do
-
Get Meeting
readmeeting-get -
Import Meeting
performmeeting-import -
List Meetings
searchmeeting-list -
Get Notes
readnotes-get -
Get Transcript
readtranscript-get
Every app-specific value here is a blank you have to fill in. An
app action is reached through the connection that authenticates it, so the
address is a connection id, not the app id — and connections belong to your account,
so a public page cannot know yours. Create one for tl;dv, then fill in
the three blanks: conn_YOUR_CONNECTION_ID, the action key, and the
parameters that action declares. The call itself is real — the shape is transcribed
from the studio's own snippet builder, which prints the same kind of blanks — but
nothing in it is specific to tl;dv. The Workflow tab is where this app's
real ids are.
npm install @w6w/sdkyarn add @w6w/sdkpnpm add @w6w/sdkdeno add npm:@w6w/sdkimport { W6wClient, isActionRun } from "@w6w/sdk";
// Reads W6W_BASE_URL and W6W_TOKEN from the environment when omitted.
const client = new W6wClient();
const envelope = await client.run({
urn: "conn_YOUR_CONNECTION_ID",
action: "meeting-get",
payload: {
meetingId: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value);npm install -g @w6w/cliw6w run conn_YOUR_CONNECTION_ID --action meeting-get --payload '{"meetingId":"<value>"}'Give an AI agent tl;dv — without giving it tl;dv's credentials. One MCP endpoint exposes every app, function and workflow the caller is entitled to, as tools it can discover and run. Access is granted per team while we onboard.
One tool call{
"name": "w6w_invoke",
"arguments": {
"ref": "app:io.w6w.tldv#meeting-get",
"input": {
"meetingId": "<meetingId>"
}
}
}
Every tool names its target with a single ref. The
app: form above doesn't name a connection at all — the
host resolves which of the caller's tl;dv connections to sign
with, and refuses rather than guesses when the answer is ambiguous.
What the agent gets
Credentials it can't read
The token is attached host-side, at the moment of the call. It is never a tool argument, never in the model's context, and never in a transcript — so a prompt injection has nothing to exfiltrate.
A tool surface scoped to the caller
Tools are derived per end user from what that person has actually connected and is entitled to — not one shared bot identity carrying the union of everyone's access.
A durable workflow in one call
Multi-step work runs on the workflow engine and returns a run handle the agent can poll — retries, branching and state survive the conversation that started them.
Health-aware discovery
tl;dv's declared health checks are on the surface too, so an agent can tell "the vendor is down" from "your credential expired" before it burns a retry on either.
The MCP surface is part of the hosted platform. tl;dv itself is MIT, and the runtime that executes it is source-available (FSL).
Health checks
tl;dv declares its own checks, so its health is a property of the app rather than something the host guesses at.
tl;dv platform status
Component status from tldv.instatus.com. The verdict follows the `Public API` component alone — the surface every action here calls; the WebApp, recorder bots, webhooks and AI-notes components are reported for attribution but never move it.
API reachability
Unauthenticated GET of /v1alpha1/health, tl;dv's own dedicated health route. A 200 with {"status":"ok"} is the pass. Credential validity is the derived auth:api-key check's job.