Understands photos, audio and video

Photos: it understands the scene and reacts naturally.
Audio: it transcribes and replies to the content.
Video: it grasps what's shown and adjusts the message.

The AI interprets what the fan sends and replies to what was actually sent.

When a fan sends a photo, a voice note or a video, Chispa interprets it and replies to what it actually contains, not with a generic answer.

only Chispa The reply scales with the richness of the media: a long video from the fan deserves more than a "haha".

Was this helpful?