Processing Multiple Voice Notes: Combining Telegram, Make.com, and ChatGPT

How To
, ,
1

I’m looking for help with enhancing my current make.com scenario. Here’s what I have now and what I want to achieve:

Current scenario:

  1. I send a single voice note to a Telegram bot.
  2. The audio file is processed in make.com.
  3. The audio is converted to text.
  4. The text is sent to ChatGPT for processing.
  5. ChatGPT’s response is sent back to Telegram.

Desired scenario: I want to modify this to handle multiple voice notes more efficiently. Specifically:

  1. I should be able to send multiple voice notes to the Telegram bot.
  2. Each voice note should be converted to text individually.
  3. All the resulting text from these multiple voice notes should be combined.
  4. This combined text should be sent to ChatGPT as a single input.
  5. ChatGPT’s response should then be sent back to Telegram.

My questions are:

  1. How can I modify my current scenario to achieve this?
  2. What modules or steps should I add or change in make.com?
  3. Is there a way to efficiently collect and process multiple voice notes before sending the combined text to ChatGPT?
  4. Are there any potential limitations or issues I should be aware of when implementing this?

Any guidance, tips, or example scenarios would be greatly appreciated. Thank you!

2

Hi,

I assume that you are using the “Watch Updates” module as your scenario trigger eg. each message sent to your bot instantly triggers action in Make.

If so, each webhook trigger is a separate scenario execution.

Here you can learn more: Make.com: execution, cycles, phases

You cannot merge these unless you create a database and some rather advanced logic to handle it.

Have a nice day!