Yes. When a customer sends a voice note, image, video, or document over WhatsApp, Stravax Engage downloads it and stores it so your team can view it in the conversation. Voice notes are automatically transcribed, and when the AI qualifier is turned on for a conversation, it can read images too.
When an inbound message carries media, Stravax Engage downloads it right away rather than waiting, because WhatsApp's media links expire after a few minutes. The file is stored securely and attached to the message, and any open inbox refreshes automatically the moment it is ready, so your team never has to reload the page to see it. If a download job has to retry, it picks up only the part that did not finish rather than starting over.
Once a voice note is stored, it is automatically transcribed to text. The audio stays the actual message; the transcript is additional context attached alongside it, shown under the audio player in the conversation. If the AI qualifier is active on that conversation, the transcript feeds the qualifying conversation exactly the way a typed reply would, referenced as a voice note.
Only when vision is turned on for that qualifier's setup. When it is enabled, the AI reads the most recent images in the conversation, so it can act on something like a bill or a screenshot a customer sends. It looks at up to the last three images in a conversation; very large images and unsupported image formats are skipped rather than sent through.
Documents and videos are downloaded and stored the same way voice notes and images are, so nothing a customer sends is lost while the conversation is open.
| Media type | Downloaded and stored | Transcribed | Read by the AI qualifier |
|---|---|---|---|
| Voice note | Yes | Yes | Yes, via the transcript |
| Image | Yes | No | Yes, only when vision is enabled |
| Document | Yes | No | No |
| Video | Yes | No | No |
Related reading: