Task List

• Manage to use Fuyu API for image upload
• Use Seamless text to text translation to translate the outputs into the selected language
• Use Seamless text to voice to produce the TTS of the outputs into the selected language
• Add Text Examples , Audio Examples (already uploaded!) , Image Examples (already uploaded!)
• Improve the seamless with a simple text chunking then call
• adapt to better/larger models
• add conversation memory