It would be amazing if Manychat allowed us to send audio messages (e.g., voice notes, generated speech, or custom audio files) through custom fields.

For example, a workflow could use Make to generate an audio response using ElevenLabs, and then send the resulting audio file back to Instagram or Messenger through Manychat.

This feature would make it possible to create voice-based chat experiences, such as personalized replies or AI voice assistants, directly within Manychat.

This feature is already working with other types of files (images and video), but not with audio.