Asterisk:
A Sentient Camera
Asterisk:
A Sentient Camera
Asterisk: A Sentient Camera
SCOPE
SCOPE
Prototyping with AI
Prototyping with AI
DURATION
DURATION
4 W (2025)
4 W (2025)
CREDITS
CREDITS
Team: Sakshi Suthar, Uttkarsh Mandaknale
Mentors: Alexander Baumgardt, Thomas J McLeish
Team: Sakshi Suthar, Uttkarsh Mandaknale
Mentors: Alexander Baumgardt, Thomas J McLeish
Ever wondered what a camera would say if it could talk and had a sense of humor?
Ever wondered what a camera would say if it could talk and had a sense of humor?
Ever wondered what a camera would say if it could talk and had a sense of humor?
CONCEPT
CONCEPT
Asterisk is not just a sentient camera, it’s an experience that transforms your presence into poetic satire.
Asterisk is not just a sentient camera, it’s an experience that transforms your presence into poetic satire.
It doesn’t capture your photo, it captures you in your environment, interprets the scene, and whispers back a witty, personalized poem that playfully roasts you.
It doesn’t capture your photo, it captures you in your environment, interprets the scene, and whispers back a witty, personalized poem that playfully roasts you.
PROCESS
PROCESS
AI powers the transformation from visual input to personalized, spoken poetic output.
AI powers the transformation from visual input to personalized, spoken poetic output.
Using the GitHub link given below, you can explore the modular components that generate context-aware, humorous poetry.
Using the GitHub link given below, you can explore the modular components that generate context-aware, humorous poetry.
A photo is captured with the Raspberry Pi Camera, recording the user’s expression, posture, and surroundings. The image is sent to LLaVA-13B, which generates a scene description, and then to DeepSeek V3 to create an 8-line free verse poem. Finally, Kokoro-82m converts the text into a human-like spoken voice, delivering a witty, spoken poem that humorously reflects the user and their environment.
A photo is captured with the Raspberry Pi Camera, recording the user’s expression, posture, and surroundings. The image is sent to LLaVA-13B, which generates a scene description, and then to DeepSeek V3 to create an 8-line free verse poem. Finally, Kokoro-82m converts the text into a human-like spoken voice, delivering a witty, spoken poem that humorously reflects the user and their environment.
GITHUB REPOSITORY
GITHUB REPOSITORY
GITHUB REPOSITORY
RETURN TO TOP
RETURN TO TOP
RETURN TO TOP