First-party app
Otter.ai

Otter.ai

Read Otter.ai channels, conversations, transcripts, action items, insights and outlines, download meeting audio, and import calls from a URL — over Otter's Enterprise Public API.

stable AI & Machine LearningProductivityVideo & Streaming

About

Otter.ai ships in the w6w first-party pack. It declares 7 actions, 2 health checks, and the host runs its code in a sandbox that never sees the credential.

App id
io.w6w.otter
Version
0.1.0
Author
w6w
Licence
MIT
Categories
AI & Machine Learning · Productivity · Video & Streaming

Overview

Otter.ai is an AI meeting assistant that records, transcribes and summarizes conversations, then turns them into searchable transcripts, abstractive summaries, action items, topic insights and outlines. This app reads that output into a workflow: list and search conversations, fetch one with any combination of its generated action items, insights, outline or full transcript, download the meeting’s MP3, and organize by Channel (Otter’s shared-folder concept) and workspace member.

A conversation-create action covers the other direction — importing a publicly downloadable audio or video URL as a new Otter conversation, the documented path for pulling calls in from a dialer or another recording source.

Otter’s Public API is gated to Enterprise workspaces only; a Free, Pro or Business account has no access to any endpoint this app calls, and Auth.test reports that distinctly from a bad key. Real-time updates are documented as a separate Webhooks surface rather than anything pollable here — out of scope for this app’s Actions, which only cover reads and the one documented write.

Build with Otter.ai

Three routes to the same 7 actions. The Workflow tab is generated from Otter.ai'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.

List Channels

channel-list

List channels for the authenticated user, in alphabetical order by name.

List Channel Members

channel-members-list

List all members of a channel, in alphabetical order by member name.

Get Conversation Audio URL

conversation-audio-get

Get the MP3 audio download link for a specific conversation.

Create Conversation From File

conversation-create

Import a publicly downloadable audio or video URL as a new Otter conversation — for pulling calls in from a Dialer or another recording source.

Get Conversation

conversation-get

Get a conversation's summary and details, plus the requested relationships (action items, insights, outline, transcript).

List Conversations

conversation-list

List conversations for the authenticated user, most recent first. Cursor-paginated.

Get Workspace

workspace-get

Get the authenticated user's Otter workspace — id, name, owner, member count, handle and type.

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 Otter.ai's real ids.

{
  "manifestVersion": "2",
  "name": "otter-example",
  "steps": [
    {
      "id": "channel-members-list",
      "uses": {
        "app": "io.w6w.otter",
        "action": "channel-members-list",
        "connection": "conn_YOUR_CONNECTION_ID"
      },
      "with": {
        "channelId": "<channelId>"
      }
    }
  ]
}

Here are some of the things you can do

  • List Channel Members

    read
    channel-members-list
  • List Channels

    read
    channel-list
  • Get Conversation Audio URL

    read
    conversation-audio-get
  • Create Conversation From File

    perform
    conversation-create
  • Get Conversation

    read
    conversation-get

+2 more actions available

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 Otter.ai, 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 Otter.ai. The Workflow tab is where this app's real ids are.

Install
npm install @w6w/sdk
yarn add @w6w/sdk
pnpm add @w6w/sdk
deno add npm:@w6w/sdk
Code
import { 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: "channel-members-list",
  payload: {
    channelId: "<value>",
  },
});

if (isActionRun(envelope)) console.log(envelope.value);
Install the CLI
npm install -g @w6w/cli
CLI
w6w run conn_YOUR_CONNECTION_ID --action channel-members-list --payload '{"channelId":"<value>"}'

Give an AI agent Otter.ai — without giving it Otter.ai'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.otter#channel-members-list",
    "input": {
      "channelId": "<channelId>"
    }
  }
}

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 Otter.ai 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

Otter.ai'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. Otter.ai itself is MIT, and the runtime that executes it is source-available (FSL).

Request MCP access

Health checks

Otter.ai declares its own checks, so its health is a property of the app rather than something the host guesses at.

service

Otter.ai platform status

Component status from status.otter.ai, an Atlassian Statuspage. Highlights the 'Public API' component specifically, alongside the vendor's own page-level roll-up.

quota

API rate-limit headroom