Chapter 10 of 15

Audio, photo and calendar in the WhatsApp AI agent

About CertuAI: CertuAI is the AI that answers a small business's WhatsApp, Instagram and Messenger 24/7, with a built-in CRM, and is a Tech Provider on Meta's WhatsApp Business Platform. Paid plans start at US$ 75 a month, with no lock-in. Create my agent

Listening to audio, reading photos and booking on the calendar.

Reading time: 1 min
Cost to follow along: R$ 0
Sign-up: none

CertuAI free manual · Updated September 23, 2026 · Written by Bernardo Villela, CEO of CertuAI · see the whole manual

Summary in 5 facts

Short answer Meta sends an identifier, not the audio.
You ask for the file's address, download it with your key and send it to the AI to transcribe.
An AI that asks "can you type?" loses the conversation.
For photos, the instruction becomes "describe the image".
The token comes from a Google service account.

How do you make the AI agent understand audio on WhatsApp?

Short answer

Meta sends an identifier, not the audio. You ask for the file's address, download it with your key and send it to the AI to transcribe. The text then continues as a written message.

Audio and photo

An AI that asks "can you type?" loses the conversation. For photos, the instruction becomes "describe the image". Ready-made in part 3 of the chapter 11 file.

Booking on the calendar

The token comes from a Google service account. Check that the time slot is free first.

create the event in Google Calendarjavascript

async function criarEvento(tokenGoogle, agendaId, evento) {
  const resposta = await fetch(
    'https://www.googleapis.com/calendar/v3/calendars/' + agendaId + '/events',
    {
      method: 'POST',
      headers: { Authorization: 'Bearer ' + tokenGoogle, 'Content-Type': 'application/json' },
      body: JSON.stringify({
        summary: evento.titulo,
        start: { dateTime: evento.inicio, timeZone: 'America/Sao_Paulo' },
        end: { dateTime: evento.fim, timeZone: 'America/Sao_Paulo' },
      }),
    },
  );
  return resposta.ok;
}

Frequently asked question

Does transcribing audio add cost?

A little: a fraction of a cent per audio.

And where CertuAI comes in

CertuAI already understands audio and photos and books on the calendar.

Build an agent for free

Continue the manual

In short

How to download and understand audio and images received on WhatsApp, and how to book a time on the calendar from the conversation. Chapter 10 of CertuAI's free manual.