FastVLM WebGPU
π
446
Real-time video captioning powered by FastVLM
Generate spokenβready scripts from documents for podcasts, lectures, or summaries
Generate any application by Vibe Coding it
Split text into chunks
Divide text into chunks with overlap
Chat with an assistant to get information and help
Zero SQL
Generate a transcript with speaker identification from an audio file
Fight AI models with prompts
OmniParser, turn your LLM into GUI agent
Testing Multimodal Gemini
Testing Multimodal Gemini