Skip to main content

Process images, audios and videos in WhatsApp with AI 🤖


Gustavo Boregio
Forum|alt.badge.img+6

🚨 Big Update: You can now process images, audios and videos in WhatsApp (yes, finally!)

We’ve been waiting for this for a while… and it’s finally here.

Manychat now gives you access to media file URLs when a user sends an image, video or audio on WhatsApp — even out of the blue (default reply style).

That means:

👉 You can now process those files with AI.

👉 You don’t need to manually review inboxes anymore.

👉 You can fully automate things that were impossible before.

We’ve already tested this with GPT:

🖼️ Detect objects in images

💳 Identify credit card brands

💻 Spot devices, screens, contracts, and more

🎧 Transcribe audios using Make + OpenAI

This is a game-changer for WhatsApp, especially since users love to send voice notes and random photos instead of typing 😅

Anyone already testing it? I’d love to hear your use cases 👇

!-->

10 replies

AndreasHelbo
  • Up-and-Comer
  • 2 replies
  • April 23, 2025

Amazing, when will this be available on instagram and facebook?! 

JUST WHAT I’VE BEEN WAITING FOR


Gustavo Boregio
Forum|alt.badge.img+6
  • Author
  • Manychat Community Moderator
  • 2394 replies
  • April 23, 2025

@AndreasHelbo it’s also available for IG and Facebook! 🔥

Test it out!!


AndreasHelbo
  • Up-and-Comer
  • 2 replies
  • April 23, 2025

 

I don’t get the URL on either Instagram or Facebook. Don’t know what I’m doing wrong.


Gustavo Boregio
Forum|alt.badge.img+6
  • Author
  • Manychat Community Moderator
  • 2394 replies
  • April 23, 2025

@AndreasHelbo are you doing these first steps?

 


IKmcAcademy
  • Up-and-Comer
  • 1 reply
  • June 10, 2025

Can we process the images like business card to extract out the information like company name, email address, phone number etc and added all this into user custom field via whatsapp automation


Gustavo Boregio
Forum|alt.badge.img+6
  • Author
  • Manychat Community Moderator
  • 2394 replies
  • June 10, 2025

@IKmcAcademy yes sir!

I’d do a custom prompt for this and have OpenAI return JSON code so I can map it to user fields in Manychat.


Gamma
  • Up-and-Comer
  • 2 replies
  • June 16, 2025

Hi, i already do that, but, whit MAKE, how can i get transcription whiout MAKE, becuase, when i use MAKE, usually thats no answer, or not answer whit sense, thats way , i only want a good transcription , even if costumer not send good audio or good pic


Gustavo Boregio
Forum|alt.badge.img+6
  • Author
  • Manychat Community Moderator
  • 2394 replies
  • June 16, 2025

@Gamma you can process images directly in Manychat, but for audios you need Make or some other external tool.

Here's a video that can help:

We also have it in Spanish in our youtube channel: https://www.youtube.com/@SuperarmeOnline :)

EDIT: Just realized I referenced this same post 🙃


Gamma
  • Up-and-Comer
  • 2 replies
  • June 16, 2025

How i can do it, whit http request? , because MAKE, no work good, and also, sometimes, i think not start 


Gustavo Boregio
Forum|alt.badge.img+6
  • Author
  • Manychat Community Moderator
  • 2394 replies
  • June 17, 2025

@Gamma I usually do it with an External Request and a Webhook trigger in Make and this works flawlessly.


Cookie policy

We use cookies to enhance and personalize your experience. If you accept you agree to our full cookie policy. Learn more about our cookies.

 
Cookie settings