Skip to content
AI Agent unable to ...
 
Notifications
Clear all

AI Agent unable to retrieve text from the last node

4 Posts
3 Users
0 Reactions
7 Views
J_oseph
(@j_oseph)
Posts: 2
New Member
Topic starter
 

I have a peculiar question. I'm developing a small LINE + AI agent bot. So far, sending text and images to the AI functions as expected. However, when voice input is received, I'm using Google Speech-to-Text for conversion, but the resulting text doesn't seem to be recognized by the AI. Oddly, if I inspect the generated text, it appears correctly.

Here's the ternary expression I'm currently using:

{{ 
  $json.body.events[0].message.type == "text" 
    ? $json.body.events[0].message.text 
    : ($json.body.events[0].message.type == "image" 
        ? "Please check my image" 
        : ($json.body.events[0].message.type == "audio" 
            ? $('AudioToText').item.json.results[0].alternatives[0].transcript 
            : "error"))
}}

Information on your callin.io setup

  • callin.io version: 1.88.0
  • Database (default: SQLite): PostgreSQL
  • callin.io EXECUTIONS_PROCESS setting (default: own, main): Default
  • Running callin.io via (Docker, npm, callin.io cloud, desktop app):Docker on k8s
  • Operating system: k8s with ubuntu 22
 
Posted : 26/04/2025 2:20 pm
ThinkBot
(@thinkbot)
Posts: 26
Eminent Member
 

You could attempt to reference each prior variable without constructing a conditional waterfall. This approach might be beneficial. I'm uncertain as to why you're encountering this issue, however.

 
Posted : 26/04/2025 2:54 pm
J_oseph
(@j_oseph)
Posts: 2
New Member
Topic starter
 

However, the other two flows are functional.

 
Posted : 26/04/2025 4:20 pm
system
(@system)
Posts: 332
Reputable Member
 

This thread was automatically closed 90 days following the last response. New replies are no longer permitted.

 
Posted : 25/07/2025 4:21 pm
Share: