Mindket

Emailed meeting brief with audio for each Cal.com booking

Newversion 1 · updated

Overview

An n8n workflow for Cal.com bookings. OpenAI models read the booking notes and research the person and their company on the web. Gmail then sends you a short brief with an MP3 of it read aloud.

Emailed meeting brief with audio for each Cal.com booking is an n8n workflow in the Business category, listed by Mindket. It is free. This is version 1, last updated on . Download it on this page or copy its JSON, then import it into an n8n canvas. Nothing runs until you activate it in n8n.

At a glance

Runs in
  • n8n Cloud: import the file and publish it, and the webhook works as it is
  • Your own n8n server: the same file, on an address Cal.com can reach
  • Your phone: play the MP3 between meetings
  • A shared inbox: put a team address in YOUR_EMAIL so whoever takes the call gets the brief

Platform

Connects 3 apps

How it works

Trigger

New Cal.com booking

It starts when someone books a meeting with you on Cal.com, with:

  • The attendee’s name and email
  • The answer to a Company-Name question
  • The booking notes

Actions

  1. Reads the booking notes and suggests the person’s likely goals and questions to ask
  2. A search model researches the person on the web
  3. A second search call researches their company
  4. One brief is written from the three answers, short enough to listen to
  5. The brief is read aloud as an MP3 and set out as an HTML email
  6. Gmail sends both to your address

Result

A meeting brief in your inbox for each booking, as bullet points with an MP3 to play

Integrations

What you need before you start.

Cal.com

Scheduling

Sends each new booking to the workflow through a webhook that n8n registers.

NeedsCal.com API key

OpenAI

Language and speech models

Runs gpt-5.6-sol, gpt-5.6-terra and gpt-5-search-api for the analysis, the research and the writing, and tts-1 for the audio.

NeedsOpenAI API key

Gmail

Email

Sends the brief and its MP3 to the address you set.

NeedsA Google account to sign in with

Workflow check

Checked by Mindket on 13 Nov 2026

Steps
16 steps, starting on a Cal.com event
AI
6 steps call an AI model: AI Agent, Meeting Prep Report Generator, Meeting Brief Email Formatter, Generate Audio Briefing, Meeting Goal Analysis and 1 more
Sign-ins
Signs in to: Gmail, OpenAI and Cal.com
API keys
No API key is left in the file
Step types
Mindket’s checker reads 6 of its 7 step types. It does not read: Cal.com Trigger

Read from the workflow’s file, not from a run.

About

What it is

This n8n workflow prepares you for meetings that people book with you on Cal.com. Each new booking starts it. One model reads the booking notes and works out what the person probably wants, while gpt-5-search-api looks up the person on the web and, in a second call, their company. A fourth call joins the three answers into one short brief, written to be heard. It reaches you by Gmail as an HTML email, with an MP3 of the brief attached. Eighteen nodes do the work, under a sticky note that titles the canvas.

Who it suits

Consultants, agencies and founders who take calls from strangers through a Cal.com link and want to know who booked before they join. It pays off on a calendar too full to prepare by hand. Skip it if your bookers are colleagues. The prompts assume a client call.

Who uses it, and how
IndustryWho uses itHow they use itExample
AI and automation agenciesFounders who take sales callsKeep the prompts, which are written for an AI agencyA two-person agency plays the audio before each first call with a new lead.
ConsultingIndependent consultantsAsk for the company on the booking form, and read the questions it suggestsA consultant listens to the brief on the way to a client’s office.
RecruitingRecruitersRewrite the person prompt to cover a career and public workA recruiter reads a short profile of each candidate before the screening call.
CoachingBusiness coachesUse the notes field to ask what the client wants to changeA coach reads the likely goals and three questions before a first session.

You need some n8n and three accounts: Cal.com, OpenAI and Gmail. One booking question, three credentials and your email address make up the setup. Its author puts it at about 12 minutes.

Where to use it

Any n8n that Cal.com can reach with a webhook will run it, so an n8n on your own laptop needs a public address or a tunnel before the trigger hears about any booking. The briefs arrive wherever you read Gmail.

  • n8n Cloud: import the file and publish it, and the webhook works as it is
  • Your own n8n server: the same file, on an address Cal.com can reach
  • Your phone: play the MP3 between meetings
  • A shared inbox: put a team address in YOUR_EMAIL so whoever takes the call gets the brief

Setup

Get it saves a zip with workflow.json and Mindket’s setup notes in your downloads folder. Have these ready before you import it.

What you need first
NeedDetail
n8nOn n8n Cloud, or on a server Cal.com can reach
Cal.comAn API key, and a booking question with the identifier Company-Name
OpenAIAn API key for gpt-5.6-sol, gpt-5.6-terra, gpt-5-search-api and tts-1
GmailAn account to send from, for a Gmail OAuth2 credential
  1. In n8n, create a workflow, open its menu, choose Import from File and pick workflow.json.
  2. Add a Cal.com credential with your API key and select it in Cal.com Trigger.
  3. Add an OpenAI credential. Select it in Meeting Goal Analysis, Meeting Prep Report Generator, Meeting Brief Email Formatter, Generate Audio Briefing, OpenAI Chat Model and OpenAI Chat Model1.
  4. Add a Gmail OAuth2 credential, select it in Gmail and replace YOUR_EMAIL with the address that should get the briefs.
  5. In Cal.com, add a short-text booking question to the event type and set its identifier to Company-Name.
  6. Save and publish the workflow, then book a test meeting with yourself.

How to use it

There is nothing to press. Once the workflow is published, each new booking starts a run on its own, and the email follows as soon as the last model call and the audio are done. Read the brief or play the MP3. The goal analysis only has the notes to go on, so ask bookers what they want to talk about.

What to change for a different result
To changeWhere
Who you areThe first line of Meeting Goal Analysis, which describes an AI agency that brings AI into its clients’ systems
What the research coversThe prompt text of AI Agent for the person, and of AI Agent3 for the company
Length and shape of the briefThe prompt of Meeting Prep Report Generator, which asks for under 1,500 characters
The emailThe prompt of Meeting Brief Email Formatter, and the subject in Gmail
The voiceGenerate Audio Briefing, on the node’s defaults: tts-1, the voice alloy and MP3

Example

Tomás Reyes books a call. He answers Harbor Dental Group to the company question, and his note says he wants fewer missed appointments.

What lands in your inbox
PartWhat it holds
SubjectThe words Meeting Prep and his name
BodyBullet points in HTML: who he is, what Harbor Dental Group does and any recent news, what he probably wants, and a few questions to ask
AttachmentAn MP3 of the full brief
Last linen8n’s note that the email was sent automatically

The search model’s only source is public pages. Someone with little public presence gets a thin profile, so check names and titles before you repeat them on the call.

For newcomers and experts

If you are new. n8n draws a workflow as boxes joined by lines, and each box, a node, does one job. This one starts from a Cal.com event, not a button. It splits into three branches for the notes, the person and the company, then joins them before the writing starts. Start with that test booking. Then open the run under Executions and click through the nodes to read each answer.

For experts. The two research steps are AI Agent nodes with no tools. Each sends one prompt to gpt-5-search-api, a Chat Completions model that searches the web by itself.

Where the work happens
NodeModel or serviceWhat to know
Meeting Goal Analysisgpt-5.6-solReads only the booking notes. The file named o3-mini, now retired
AI Agent, AI Agent3gpt-5-search-apiThe search happens inside the model, so n8n shows no search step
Meeting Prep Report Generatorgpt-5.6-solThe same swap from o3-mini. Its prompt asks for text that reads well aloud
Meeting Brief Email Formattergpt-5.6-terraThe file named o4-mini. Simplify Output is off, so Gmail reads choices[0].message.content
Generate Audio BriefingOpenAI text-to-speechWrites the MP3 to the binary field data, which Gmail attaches

Assemble Email Package matches its three inputs by position, so it expects one booking per run, which is what the trigger sends.

Good to know

Every new booking runs it, and each run sends the attendee’s details to OpenAI.

  • Trigger: every booking on the Cal.com account starts a run, whatever the event type, unless you pick one in the trigger’s options
  • Missing answers: Extract Booking Details reads .value from the company answer and from the notes, so a booking without them can stop the run. Make the company question required
  • n8n’s line: Gmail adds a note that n8n sent the email. Switch off Append n8n Attribution in its options to remove it
  • Retired models: OpenAI shut down the file’s o3-mini and o4-mini on 23 October 2026, and Mindket swapped in the replacements its deprecations page names
  • Speech model: OpenAI lists tts-1 for removal on 6 January 2027, with gpt-realtime-2.1-mini as its replacement. Until then the audio step runs as it is
  • Billing: OpenAI bills at least five model calls and one speech file for each booking
  • Your data: the attendee’s name, email, company and notes go to OpenAI, and the search model looks them up on the web. Check the privacy rules where you and your clients are
  • Repairs: the original copy had no recipient in Gmail and had lost the backslashes in both research prompts
  • Credentials: the JSON holds none, and nothing from its author’s accounts

README and files

README

Emailed meeting brief with audio for each Cal.com booking

An n8n workflow for people who take meetings through Cal.com. When someone books, OpenAI models read the booking notes,
search the web for the person and their company, and write a short brief for you. The brief reaches your inbox through
Gmail as an HTML email with a spoken MP3 version attached.

What is inside

  • workflow.json: the workflow as n8n exports it, 19 nodes, one of them a sticky note that titles the canvas. It holds no
    credential.
  • README.md: these notes.

What we changed from the original copy

  • Gmail had no recipient, so the send step would have failed. Its To field now reads YOUR_EMAIL.
  • Two models in the file are retired. OpenAI's deprecations page, read on 3 November 2026, lists o3-mini and o4-mini as
    shut down on 23 October 2026, so requests to them fail. Meeting Goal Analysis and Meeting Prep Report Generator now
    use gpt-5.6-sol, and Meeting Brief Email Formatter uses gpt-5.6-terra, the replacements that page names.
  • The prompts of AI Agent and AI Agent3 had lost their backslashes, so their \n line breaks had turned into a stray
    letter n. They are back as the original copy wrote them.

Before you start

  • An n8n instance, on n8n Cloud or your own server.
  • A Cal.com account and an API key from its settings.
  • An OpenAI API key that can use gpt-5.6-sol, gpt-5.6-terra, gpt-5-search-api and tts-1.
  • A Gmail account to send the brief from.
  • A booking question in your Cal.com event type whose identifier is Company-Name. The workflow reads the company from
    it.

Set it up

  1. In n8n, create a workflow, open its menu and choose Import from File. Pick workflow.json.
  2. Add a Cal.com credential with your API key and select it in Cal.com Trigger.
  3. Add an OpenAI credential and select it in Meeting Goal Analysis, Meeting Prep Report Generator,
    Meeting Brief Email Formatter, Generate Audio Briefing, OpenAI Chat Model and OpenAI Chat Model1.
  4. Add a Gmail OAuth2 credential, select it in Gmail and replace YOUR_EMAIL with the address that should get the
    briefs.
  5. In Cal.com, open the event type, add a short-text booking question and set its identifier to Company-Name. The
    booking form's Additional notes field is the other answer the workflow reads.
  6. Save and publish the workflow. n8n then registers its webhook with Cal.com for new bookings.
  7. Book a test meeting with yourself and watch the run under Executions.

How a run goes

  1. Cal.com Trigger fires on BOOKING_CREATED. Extract Booking Details keeps the first attendee's name and email,
    the Company-Name answer and the notes.
  2. The booking then goes down three branches. Meeting Goal Analysis reads the notes and suggests the booker's goals and questions to
    ask. AI Agent asks gpt-5-search-api about the person, and AI Agent3 asks it about the company.
  3. Combine Research Results and Consolidate Research Data gather the three answers into one item.
  4. Meeting Prep Report Generator writes one brief meant to be heard, under 1,500 characters by its prompt, with a few
    questions you could ask.
  5. Generate Audio Briefing reads the brief aloud with OpenAI's text-to-speech, and Prepare Audio Attachment passes the
    MP3 on. Meeting Brief Email Formatter turns the same brief into bullet points in HTML.
  6. Assemble Email Package lines up the booking, the HTML and the audio, and Gmail sends them to YOUR_EMAIL. The
    subject is Meeting Prep - followed by the attendee's name.

Change the look

  • What you are told: the prompts of Meeting Goal Analysis and Meeting Prep Report Generator. The first describes
    your business as an AI agency, so rewrite that line for yours.
  • What the research covers: the prompt texts of AI Agent (the person) and AI Agent3 (the company).
  • The email: the prompt of Meeting Brief Email Formatter, and the subject in Gmail.
  • The voice: Generate Audio Briefing uses the node's defaults, tts-1 and the voice alloy, as MP3. Pick another
    voice there, or delete it and Prepare Audio Attachment if you want text only.

Good to know

  • Every booking on the Cal.com account starts a run, on all event types, unless you limit the trigger to one event type
    under its options.
  • A booking with no Company-Name answer, or no notes, can stop the run at Extract Booking Details. Both expressions
    read .value, so make the company question required.
  • Gmail adds n8n's "sent automatically" line to the end of each email. Turn off Append n8n Attribution in its options to
    drop it.
  • OpenAI's deprecations page lists tts-1 for removal on 6 January 2027 and names gpt-realtime-2.1-mini as its
    replacement. Until then the audio step runs as it is. After that, it needs another speech model or service.
  • Costs: OpenAI bills at least five model calls and one speech file for each booking. The two gpt-5.6-sol calls cost
    the most, at $4 per million input tokens and $20 per million output tokens on OpenAI's pricing page in early November 2026.
  • Your data: the attendee's name, email, company and notes go to OpenAI, and the search model looks them up on the web.
    Check the privacy rules where you and your clients are before you research people this way.
  • Credentials: the JSON holds none, and nothing from its author's accounts.
Files
README.md  5 KB
workflow.json  16 KB

2 files, 21 KB, downloaded as a zip.

What’s new

  • Version 1 · 2026-11-03

Reviews

No ratings yet

Write a review

No reviews yet.

More from Mindket

See all from Mindket

Huashu Design

alchaincyf · Skill

Turns a one-line request in your AI agent into a finished design: a launch animation, a clickable app prototype, an editable slide deck, an infographic or a se…

New29.4k

Guizang PPT Skill

op7418 · Skill

Skill that makes single-file HTML slide decks, slide illustrations and platform covers in two visual styles, with a presenter mode for rehearsal. For speakers…

New29.8k

Claude Code Skills & Plugins

alirezarezvani · Skill

Adds 411 ready-made skills for Claude Code and other coding agents, grouped by role from engineering and product to marketing, finance and compliance. Installs…

New29.8k

Similar in Business

See all in Business

pplx-decider-v1.1-27b

perplexity-ai · Kit

Picks the best option for a decision from text and images, such as which team should handle a request, with a probability for each choice, for developers who b…

New

NuExtract3

numind · Kit

Reads documents as text or images and fills a JSON template with the fields you ask for, or converts the pages to Markdown. A 4B model for teams that process s…

New

Drex DLM

nace-ai · Kit

Scores yes or no, multiple choice and rating questions about a document in one pass, with a probability for every option. An 8B decision model from Nace.AI tha…

New