# Limitations * Currently, LLMs/Generative AI is very good at language or image generation in silos. However, it is not efficient or accurate with multi-modal capabilities in sequence. For eg: generating a sequence of images relevant to long paragraphs or stories is not possible. This limits us from generating the following as they are still in the research phase: * MCQ’s with images * Stories with images ### What is possible today? * Speech recognition and evaluation (helpful for evaluation of pronunciation of students) * Text to speech (helpful for listening and also facilitating teachers in a classroom) * Rapid creation of content based on the interest of the learners * Textual MCQ’s * Textual Reading Comprehensions --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://v1azdocs.aiforworld.com/limitations.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.