AOSSIE-Org / AOSSIE-Org/DebateAI

[FEATURE]: Daily Impromptu Speaking Challenge

未关闭
#379 0 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看
enhancement
主要语言
TypeScript
星标
84
派生
198
平均合并
2 天 19 小时
30 天内合并 PR
30

描述

### Feature and its Use Cases

### **The Problem**
Currently, users (especially beginners) face a steep learning curve and high "speaking anxiety" when entering a full-length 3-phase debate. A standard debate requires extensive time commitment and deep preparation, which can be intimidating. Also, the most important debate skill is thinking on your feet and answering unexpected points, which is hard to practice on its own. Users need a quick, low-stress way to practice speaking and build their confidence.

### **Proposed Solution**
I propose adding a "Daily Impromptu Challenge".

- How it works: The user gets a random topic (like "Homework should be banned"). They get 30 seconds to think, and 60 seconds to speak into their camera.

- The Tech: We use the browser's built-in microphone feature to turn their speech into text. Then, we send that text to Gemini AI.

- The Feedback: The AI acts as a judge. It plugs right into our existing JudgementPopup to give them a score, a win/loss result, and quick tips on how to improve their argument.

### Additional Context

_No response_

### Code of Conduct

- [x] I have joined the [Discord server](https://discord.gg/hjUhu33uAn) and will post updates there
- [x] I have searched existing issues to avoid duplicates

贡献指南

这个仓库没有索引到贡献指南

评估

这个 Issue 还没有评估数据。

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。