AI Agent: Support for Audio Processing
in progress
Attia Saleh
Business Problem:
Currently, AI Agents can only process a limited range of file types — mainly text, images and files. However, many customers receive valuable information through audio messages. The inability to parse and respond to these content format restricts the AI Agent’s usefulness and limits automation potential.
Use Case Pain Points:
- Audio files: Customer send voice notes or support queries via platforms like WhatsApp or Messenger. These aren’t transcribed or actionable by the AI Agent.
Desired Outcome:
- Audio files: Transcribe and analyze content (e.g. .mp3, .wav)
N
Nabilah Binti Salleh
Merged in a post:
AI Agent: Process voice note messages
J
Joshua Loo
Business problem:
Currently, AI Agent does not have the capability to process voice notes from messages. This limits platform users from handling situations where contacts prefer speaking rather than typing. Many users rely on voice messages for convenience, cultural reasons, or to describe complex issues faster. Without the ability to process voice notes, agents must manually listen, interpret, and respond, leading to slower resolution times and missed automation opportunities.
Desired outcome:
Allow AI to process voice notes from incoming messages and generate contextual responses. Specific use cases:
- Transcribe voice notes into text and provide relevant answers.
- Understand spoken product queries and suggest matching items.
- Diagnose issues described verbally and respond based on knowledge sources.
- Process voice messages containing order details, complaints, or instructions.
Use case (Capture, Convert, Retain):
This feature spans multiple phases:
Capture:
Engage users who prefer voice over text, lowering friction and making it easier to interact with the business.Convert:
Use voice-based queries for faster product discovery, order placement, and upselling.Retain:
Reduce effort for customers by removing the need to type, while ensuring quick and accurate responses that build trust and loyalty.Nafey Bin Zahid
Must have feature please.
Nafey Bin Zahid
A must have feature please.
If currently AI can not generate a voice note itself, its okay. At least it should be able to listen to the voice note, provide a summary of what the client has said and also based on the connected knowledge base, provide relevant answer that the agent should reply back manually, either text or voice
S
Shi Hui
in progress
Rosario Honorato Saxton
Totally, it's urgent because many speak by voice message
Nelsijan Santana da Silva
This is a very important feature for my company and I hope it will be implemented as soon as possible.