Recall AI connector for AI agents

Tools your meeting bot agent reaches for on Recall AI, scoped per user.

CALL ANY TOOL

71 tools for meeting bots in Recall AI: create, schedule, and control bots, start and pause recordings, send chat messages, read recordings, transcripts, and participant events, and manage calendars and real-time endpoints.

recall_audio_mixed_delete

Delete audio mixed

Permanently delete a Recall.ai mixed audio artifact. Returns an empty body on success. Use audio_mixed_delete to remove only this artifact. Use recording_delete to remove the whole recording.

Parameters

Name

Type

Required

Description

audio_mixed_id

string

Required

UUID of the mixed audio artifact. Get it from List Mixed Audio Files or the recording's media_shortcuts.

recall_audio_mixed_get

Get audio mixed

recall_audio_mixed_list

List audio mixed

recall_audio_mixed_update

Update audio mixed

recall_bot_create

Create bot

Send a Recall.ai bot to a meeting now, or schedule it with join_at. Returns the bot with its id, meeting_url, join_at, recording_config and status_changes. Use bot_create for a single meeting link. Use calendar_event_bot_schedule to attach a bot to a synced calendar event.

Parameters

Name

Type

Required

Description

meeting_url

string

Required

Meeting link the bot joins, e.g. a Zoom, Google Meet, Microsoft Teams or Webex URL.

automatic_audio_output

object

Optional

Audio the bot plays when recording starts. Required before you can use Start Output Audio. Example: {"in_call_recording": {"data": {"kind": "mp3", "b64_data": "SUQzBAAAAAAA..."}}}.

automatic_leave

object

Optional

Timeouts, in seconds, after which the bot leaves on its own: waiting room, nobody joined, everyone left, not recording, recording, or recording permission denied. Example: {"waiting_room_timeout": 600, "noone_joined_timeout": 900}.

automatic_video_output

object

Optional

Image the bot shows as its video while recording or not recording. Each state takes a kind (jpeg) and base64 image data, 16:9. Example: {"in_call_recording": {"kind": "jpeg", "b64_data": "/9j/4AAQ..."}}.

bot_name

string

Optional

Name the bot shows in the call. Defaults to 'Meeting Notetaker'. Authenticated Google Meet bots use the Google account name instead.

breakout_room

object

Optional

How the bot handles Zoom breakout rooms. Example: {"mode": "join_main_room"} or {"mode": "join_specific_room", "room_id": "<uuid>"}.

chat

object

Optional

Chat messages the bot sends automatically when it joins or when a participant joins (Zoom, Google Meet and Teams). Each message needs send_to and message. Example: {"on_bot_join": {"send_to": "everyone", "message": "This call is being recorded."}}.

google_meet

object

Optional

Google Meet settings. Set google_login_group_id to send a signed-in bot. Example: {"google_login_group_id": "8a6f2c1e-3b4d-4e5f-9a7b-1c2d3e4f5a6b"}.

join_at

string

Optional

When the bot should join, as an ISO 8601 date-time. Set it at least 10 minutes in the future for a scheduled bot that is guaranteed to join on time; leave empty to send an ad-hoc bot now.

metadata

object

Optional

Custom key-value metadata to store on the object. Keys and values must be strings. Example: {"customer_id": "cus_123", "deal_stage": "demo"}.

output_media

object

Optional

Stream a webpage as the bot's camera or screenshare from the moment it joins. Example: {"camera": {"kind": "webpage", "config": {"url": "https://example.com/agent"}}}.

recording_config

object

Optional

Recording settings: which artifacts to capture (mixed video is on by default), the transcript provider, real-time endpoints, retention, video layout and when to start recording. Example: {"transcript": {"provider": {"recallai_streaming": {}}}, "retention": {"type": "timed", "hours": 168}}.

variant

object

Optional

Bot machine variant per meeting platform. Example: {"zoom": "web_4_core"}.

webex

object

Optional

Webex settings. Set login_group_name to send a signed-in bot. Example: {"login_group_name": "default"}.

zoom

object

Optional

Zoom-specific settings, such as a join token URL, ZAK URL or OBF token URL. Example: {"zak_url": "https://example.com/zak"}.

recall_bot_delete

Delete bot

recall_bot_get

Get bot

recall_bot_leave_call

Call bot leave

recall_bot_output_audio_start

Start bot output audio

recall_bot_output_audio_stop

Stop bot output audio

recall_bot_output_screenshare_start

Start bot output screenshare

recall_bot_output_screenshare_stop

Stop bot output screenshare

recall_bot_pause_recording

Bot pause recording

recall_bot_send_chat_message

Bot send chat message

recall_bot_update

Update bot

Change a scheduled Recall.ai bot that has not joined its call yet, such as its join time, meeting link, name or recording settings. Returns the updated bot. Use bot_update only before the bot joins. Use bot_leave_call or the recording tools to control a bot already in a call.

Parameters

Name

Type

Required

Description

bot_id

string

Required

UUID of the bot. Get it from List Bots or the `id` returned by Create Bot.

automatic_audio_output

object

Optional

Audio the bot plays when recording starts. Required before you can use Start Output Audio. Example: {"in_call_recording": {"data": {"kind": "mp3", "b64_data": "SUQzBAAAAAAA..."}}}.

automatic_leave

object

Optional

automatic_video_output

object

Optional

bot_name

string

Optional

Name the bot shows in the call. Defaults to 'Meeting Notetaker'. Authenticated Google Meet bots use the Google account name instead.

breakout_room

object

Optional

How the bot handles Zoom breakout rooms. Example: {"mode": "join_main_room"} or {"mode": "join_specific_room", "room_id": "<uuid>"}.

chat

object

Optional

google_meet

object

Optional

Google Meet settings. Set google_login_group_id to send a signed-in bot. Example: {"google_login_group_id": "8a6f2c1e-3b4d-4e5f-9a7b-1c2d3e4f5a6b"}.

join_at

string

Optional

When the bot should join, as an ISO 8601 date-time. Set it at least 10 minutes in the future for a scheduled bot that is guaranteed to join on time; leave empty to send an ad-hoc bot now.

meeting_url

string

Optional

New meeting link for the scheduled bot.

metadata

object

Optional

Custom key-value metadata to store on the object. Keys and values must be strings. Example: {"customer_id": "cus_123", "deal_stage": "demo"}.

output_media

object

Optional

Stream a webpage as the bot's camera or screenshare from the moment it joins. Example: {"camera": {"kind": "webpage", "config": {"url": "https://example.com/agent"}}}.

recording_config

object

Optional

variant

object

Optional

Bot machine variant per meeting platform. Example: {"zoom": "web_4_core"}.

webex

object

Optional

Webex settings. Set login_group_name to send a signed-in bot. Example: {"login_group_name": "default"}.

zoom

object

Optional

Zoom-specific settings, such as a join token URL, ZAK URL or OBF token URL. Example: {"zak_url": "https://example.com/zak"}.

recall_bots_list

List bots

recall_calendar_delete

Delete calendar

recall_calendar_event_bot_schedule

Calendar event bot schedule

recall_calendars_list

List calendars

recall_meeting_direct_connect_get

Get meeting direct connect

recall_meeting_metadata_update

Update meeting metadata

recall_participant_events_delete

Delete participant events

recall_participant_events_list

List participant events

recall_realtime_endpoint_get

Get realtime endpoint

recall_realtime_endpoint_update

Update realtime endpoint

recall_recordings_list

List recordings

recall_transcript_delete

Delete transcript

recall_transcript_get

Get transcript

recall_transcript_update

Update transcript

recall_transcripts_list

List transcripts

For more tools, view docs.

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Recall AI tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["recall"], toolNames: [
    "recall_bot_create",
    "recall_recordings_list",
    "recall_recording_transcript_create"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Send a bot to this meeting link and transcribe the recording when it ends" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["recall"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Send a bot to this meeting link and transcribe the recording when it ends" }],
  tools,
});

// Execute the tool call with the user's vaulted Recall AI API key
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["recall"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Send a bot to this meeting link and transcribe the recording when it ends" }],
  tools,
});

// Tool call runs with the user's vaulted Recall AI API key
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["recall"] }, pageSize: 100,
});

const agent = new Agent({
  name: "meeting_bot_agent",
  model: "gemini-2.5-pro",
  instruction: "Recall AI tools scoped to this user",
  tools,
});

await agent.run("Send a bot to this meeting link and transcribe the recording when it ends");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Recall AI tool. Click to copy, paste into your agent, done.

Bots

Copy the prompt

Copied

Send a bot to this meeting link now.

Copy the prompt

Copied

Schedule a bot to join this calendar event.

Copy the prompt

Copied

Post a welcome message in the meeting chat as the bot.

Recordings and transcripts

Copy the prompt

Copied

List recordings completed in the last 24 hours.

Copy the prompt

Copied

Start a transcript for this finished recording.

Copy the prompt

Copied

Get the download link for this recording's mixed video.

Calendars and usage

Copy the prompt

Copied

List the calendars connected to our workspace.

Copy the prompt

Copied

Show bot usage in seconds for this month.

Copy the prompt

Copied

Pause the bot's recording while we discuss pricing.

SEE HOW AUTH WORKS

Each user connects their own Recall AI API key once, and Scalekit sends it with every call. Keys stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

Recall AI

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Recall AI

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Recall AI

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Recall AI

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other transcription and developer connectors.

Support and Ops Teams

Meeting prep

Pulls agenda, participant context, and open action items before every meeting.

GTM and RevOps Teams

Sales call prep agent

Reads tomorrow's calls from Google Calendar, mines past Granola notes and Attio history for context, and delivers each rep a prep brief in Slack, scoped to the calls that rep actually owns.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Recall AI API key looks fine in a demo. In production every bot and recording looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared key
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Recall AI today. Ten connectors tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Recall AI as the user or through a shared key?

As the user. Each user connects their own Recall AI API key once, and Scalekit sends it with every call. Audit logs attribute every bot, recording, and calendar change to that user, not a shared service account.

Where is the Recall AI API key stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate it, the user reconnects with a new API key. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Recall AI?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example the bot and recording read tools without recall_bot_media_delete, which permanently deletes every recording, transcript, and artifact stored for a bot. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Recall AI access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

What does a Recall AI bot capture?

Each recording carries artifacts the agent can read separately: mixed and per-participant audio and video, transcripts, participant events, and meeting metadata. recall_recording_transcript_create starts a transcript for a finished recording with the provider you choose.