# Multimodality We will almost certainly need to use a custom editor component for multimodal projects. ### Links/Resources [Custom editor learnings](https://timheuer.com/blog/resx-editor-for-visual-studio-code/) #### Audio See [SIL Transcriber](https://software.sil.org/siltranscriber/) app [Audio editing plugin](https://marketplace.visualstudio.com/items?itemName=chocolate-pie.sound-editor\&ssr=false#overview) (though double check license, and it’s not super functional at this point.) ![Screenshot 2023-12-20 at 8.08.17 AM.png](/files/DRgiCEssxNkrXaKr8i4A) We should explore how we might integrate AVTT software into VS Code as rendered components. #### Image Klappy has made a simple POC plugin generating images using scripture prompts. I suspect there are a number of image editing plugins. We could use these to mark up images before processing with a multimodal LLM. Cf. [Custom editor sample extension for image editing](https://github.com/microsoft/vscode-extension-samples/blob/main/custom-editor-sample/README.md) --- # 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://codex-editor.gitbook.io/project-accelerate/project-overview/multimodality.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.