reloadium.com
Paste a topic, URL, or PDF/TXT/MD — get a multi-episode AI podcast with audio, transcripts, timelines and quizzes. 60+ languages.
First seen 2026-11-05 · Last seen 2026-11-05 · Source: webmcp.com
Answer 67 · Act 127 · Transact 10 · Score: Not yet scored
Tool inspector
showQuiz
Show an interactive quiz in the chat — the user answers one question at a time and gets immediate feedback plus an explanation, ending in a running score. Use for practice/testing requests: language practice, interview prep, studying for something, 'quiz me on X' — not a one-off poll or a single yes/no question, just ask that in text. Mix question types freely within one quiz the way a real practice session does (e.g. a language lesson testing both recognition and recall) — you're not limited to one type per quiz. Each item in `questions` has a `type` ('choice', 'text', 'sequence', or 'listen' — defaults to 'choice') plus a `question` prompt and optional `explanation` (shown after answering either way — make it teach the concept, not just restate the right answer; a bad question undermines the practice it's meant to give). For type 'choice': {options: [2-6 strings], correctIndex: 0-based index}. Keep every option genuinely plausible, not one obviously-right answer among filler. Optionally add {text: 'sentence to speak', language?: 'fr-FR'} to turn it into a listen-and-select exercise — the browser speaks `text` aloud and the user picks the matching option, instead of typing it like type 'listen' does; good for testing recognition (faster, easier) as opposed to production (typing, harder) of the same material. Same rule as type 'listen': if you set `text`, keep `question` an instruction, not the sentence itself. For type 'text': {acceptedAnswers: [1+ strings]} — the user types a free-text answer, graded by normalized (trimmed, case-insensitive) match against any of these; list real variants (with/without an article, common alternate spellings/phrasings), not just one exact string, since anything not listed is marked wrong even if it's a reasonable answer. Only use this for short, unambiguous answers (a word, a name, a number, a short phrase) — not open-ended ones, since matching can't judge nuance. For type 'sequence': {sequence: [2-10 strings]} — the correct order…
Page: /
Input schema
| Property | Type | Required | Description |
|---|---|---|---|
title |
string | no | — |
questions |
array | yes | — |
Raw JSON schema
{
"type": "object",
"properties": {
"title": {
"type": "string"
},
"questions": {
"type": "array",
"items": {
"type": "object",
"properties": {
"type": {
"type": "string",
"enum": [
"choice",
"text",
"sequence",
"listen"
],
"description": "Defaults to 'choice'."
},
"question": {
"type": "string"
},
"explanation": {
"type": "string",
"description": "Shown after answering, right or wrong."
},
"options": {
"type": "array",
"items": {
"type": "string"
},
"description": "Choice only: 2-6 answer choices."
},
"correctIndex": {
"type": "number",
"description": "Choice only: 0-based index into options."
},
"acceptedAnswers": {
"type": "array",
"items": {
"type": "string"
},
"description": "Text only: accepted answer variants, matched case-insensitively."
},
"sequence": {
"type": "array",
"items": {
"type": "string"
},
"description": "Sequence only: the correct order of words/phrases/steps."
},
"text": {
"type": "string",
"description": "Listen: the sentence to speak and grade against. Choice: optional — adds a Play button that speaks this before the options (listen-and-select)."
},
"language": {
"type": "string",
"description": "With `text`: BCP-47 code, e.g. 'fr-FR'. Omit for the browser default."
}
},
"required": [
"question"
]
}
}
},
"required": [
"questions"
]
}
Similar websites
api.lmm.best
Connect AI models, tools and applications with LMM Forge. Explore model access, developer guides and open-source collaboration.
deskintab.dgkhan08.workers.dev
An operating system in your browser, where you and your AI agent share apps, files, and projects through WebMCP.
webmcp.agentsdesk.dev
Meridian Ops
cesium-browser-agent.pages.dev
Cesium Agent Lab