{"slug": "hacktoberfest-weekend-challenge-build-for-a-friend-speakmate-ai", "title": "Hacktoberfest Weekend Challenge: Build for a Friend — SpeakMate AI", "summary": "A developer built SpeakMate AI, an English practice companion for a friend, as an entry in the Hacktoberfest 2026 Weekend Challenge. The Next.js and TypeScript app offers grammar, vocabulary, and sentence-correction exercises generated by a Qwen2.5 model running locally in the browser via Transformers.js and WebGPU, avoiding a paid hosted AI API. The source code is published on GitHub.", "body_md": "**# 🤖 SpeakMate AI: An AI English Practice Companion I Built for a Friend**\n\nLearning a language is not only about knowing the rules. You need a place where you can actually practice, make mistakes, and understand why an answer is correct.\n\nOne of my friends is learning English, and I wanted to build something specifically around that problem.\n\nFor the Hacktoberfest 2026 Weekend Challenge, I built SpeakMate AI — a focused English practice companion for a real friend.\n\n**## 🎯 The Problem**\n\nMy friend needed a simple way to practice English regularly.\n\nA general chatbot can answer questions, but I wanted to build something more focused.\n\nInstead of simply chatting with an AI, SpeakMate gives the learner actual exercises:\n\nThe goal was simple:\n\nDon't just talk to the learner. Give them something to practice.\n\n**## 💡 What I Built**\n\nSpeakMate AI has three main practice modes.\n\n**### 📝 Grammar Practice**\n\nThe learner chooses a difficulty level:\n\nThe AI generates a grammar exercise with multiple-choice answers.\n\nAfter answering, the learner gets:\n\n**### 📚 Vocabulary Practice**\n\nThe vocabulary mode introduces words with:\n\nThis makes vocabulary learning more interactive than simply reading a list of words.\n\n**### ✍️ Sentence Correction**\n\nThe learner receives an incorrect English sentence.\n\nThey then choose which option correctly fixes the sentence.\n\nAfter checking the answer, SpeakMate explains the grammar mistake.\n\n**## 🧠 The AI Behind SpeakMate**\n\nOne of the most important parts of this project is that the AI is not just a remote API call.\n\nI used:\n\nThe model runs in the browser using Transformers.js and WebGPU.\n\nThis means the project can experiment with local inference rather than depending entirely on a paid hosted AI API.\n\nThe open approach also makes the AI layer easier to experiment with: the model and inference setup can evolve as the project evolves.\n\n**## 🌱 Why Open Innovation Matters Here**\n\nFor this project, using an open/open-weight model and local inference was important because I wanted the learning tool to be lightweight and inexpensive to experiment with.\n\nA learning companion shouldn't necessarily require a paid AI service every time someone wants to practice a grammar question.\n\nRunning the model locally also gives the project more control over how the AI component is used and makes it possible to experiment with different models and configurations.\n\nThat was one of the biggest things I wanted to explore through this challenge.\n\n**## 🏗️ How It Works**\n\nThe basic flow is:\n\nChoose Practice Mode\n\n        ↓\n\nChoose Difficulty\n\n        ↓\n\nLocal AI Model\n\n        ↓\n\nGenerate Exercise\n\n        ↓\n\nAnswer Question\n\n        ↓\n\nCheck Answer\n\n        ↓\n\nExplanation + Score\n\n**### Sentence-correction Practice**\n\n**## 🛠️ Tech Stack**\n\n| Technology | Purpose | \n|---|---|\n| Next.js | Web application | \n| TypeScript | Application development | \n| Tailwind CSS | UI | \n| Transformers.js | Running the AI model | \n| WebGPU | Browser acceleration | \n| Qwen2.5 | Language model | \n\n**## 🔗 Project**\n\nThe complete source code for SpeakMate AI is available on GitHub:\n\n[View the SpeakMate AI source code on GitHub](https://github.com/rachana458/Speakmate-AI)\n\nYou can clone it and run it locally with:\n\nnpm install\n\nnpm run dev\n\nThen open:\n\n[the link](http://localhost:3000)\n\nA browser with WebGPU support is recommended for the local AI model.\n\n**## ❤️ What I Learned**\n\nBuilding SpeakMate taught me that a useful AI project doesn't have to be a huge application.\n\nThe most important part was starting with a real person's problem and building around that problem.\n\nI also learned more about:\n\n**## 🚀 What's Next**\n\nThere are several things I would like to add in the future:\n\nFor this weekend, however, the goal was simple:\n\n**Build something useful for one real person.**\n\nAnd that's what SpeakMate AI is.\n\nBuilt for the **Hacktoberfest 2026 Weekend Challenge — Build for a Friend**.\n\n#devchallenge #weekendchallenge #hf26challenge", "url": "https://wpnews.pro/news/hacktoberfest-weekend-challenge-build-for-a-friend-speakmate-ai", "canonical_source": "https://dev.to/yadavrachana458/hacktoberfest-weekend-challenge-build-for-a-friend-speakmate-ai-3m35", "published_at": "2026-10-03 07:25:04+00:00", "updated_at": "2026-10-03 07:37:54.496843+00:00", "lang": "en", "topics": ["ai-tools", "large-language-models", "ai-products", "developer-tools"], "entities": ["SpeakMate AI", "Hacktoberfest 2026", "Transformers.js", "WebGPU", "Qwen2.5", "Next.js", "TypeScript", "GitHub"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/hacktoberfest-weekend-challenge-build-for-a-friend-speakmate-ai", "markdown": "https://wpnews.pro/news/hacktoberfest-weekend-challenge-build-for-a-friend-speakmate-ai.md", "text": "https://wpnews.pro/news/hacktoberfest-weekend-challenge-build-for-a-friend-speakmate-ai.txt", "jsonld": "https://wpnews.pro/news/hacktoberfest-weekend-challenge-build-for-a-friend-speakmate-ai.jsonld"}}