hi to everyone ! im deployin an app, for blind people whish model do you recomend it to integrate, whit other tools, obvious whit an imagen detecttion, voice recognition and if it will be able to conect whit the camera and describe what theair on the enviroment.
Hi there!
gpt-4o will likely be your model of choice given it has multi-modal capabilities and allows for text and image input and in the future will also support voice input.
For your work, you may also find the example of the app BeMyEyes helpful as their solution relies on OpenAI’s models. Sharing a few links about them:
2 Likes
thank you! jr.2509
im just download the app "BeMyEyes.
1 Like