Gemini HTML stripper

Gemini structures most answers as a bolded term, a short explanation, then indented sub-points, and every layer of that structure is genuine markup: a bold tag, a nested list tag, before it ever reaches your clipboard. Export the same answer to Docs and a second layer of styling wraps around the first, since a Google Docs document represents bold text and nested lists in its own way.

This tool strips both layers in a single pass, along with attributes, script and style blocks, and decodes a handful of common entities. The pass runs client-side, in JavaScript, in your own browser, with no request sent to a server, which is also why there is no run limit.

Nothing to configure, and it works the same whether the text came from the chat window or a Docs export.

Step 1

Paste the reply from the chat window, or the text copied out of an exported Doc.

Step 2

Run the strip. It executes instantly, on your own device.

Step 3

Read the output, checking for any unusual entity the pass left behind.

Export to Docs rebuilds a chat answer as an actual Google Docs document, with its own representation of bold text, headings and nested lists, entirely separate from how the chat window rendered the same content. Text copied back out of that Doc carries the export's own markup, layered on top of an answer that was already built from bold tags and list tags in the first place.

This distinguishes a Gemini reply from a plain chat answer copied once: the same words can pick up two independent rendering passes depending on whether you copied straight from the chat or from a Doc built afterward.

A tag is a structural instruction, an angle-bracket wrapper telling a renderer how a piece of text should display. An entity is a character encoded as text because the literal character would be ambiguous or unsafe to include directly: & for an ampersand, < and > for the angle brackets that would otherwise be read as the start of a tag.

A nested list can carry no entities at all, while a Docs export can introduce a stray entity nowhere near a list tag. This tool performs both operations in the same pass, but they are independent failure modes.

Four entities are decoded automatically:   to a normal space, & to &, and < and > to their literal angle brackets. Those four account for most of what breaks when markup-carrying text lands in a plain field.

Numeric entities and less common named entities are left exactly as written. Review the output for any stray entity code still sitting in the text as literal characters, particularly after a Docs export.

It is a regex-based pass built around the common case, not a validating HTML parser. It does not touch the non-breaking spaces a Docs export commonly inserts around list indentation, since a space is a character, not a tag; the Gemini zero-width space remover handles that separately. There is no batch mode or API.

People who exported a Gemini answer to Docs and then need it elsewhere use this to strip both the Docs wrapper and the original chat markup in one pass. Editorial and support teams moving a Gemini answer into a CMS or a ticket use it so a bolded lead-in or a nested bullet doesn't surface as literal tags.

Anyone quoting a Gemini paragraph in a document uses it too, so the sentence arrives as words rather than a bold-and-list-wrapped fragment.