Feature: Podcast Generator Implementation

IMPLEMENTATION_PLAN.md

@@ -0,0 +1,47 @@
+# Implementation Plan - Podcast Generator
+
+## Phase 0: Git Setup
+- [x] Check if the current directory is an initialized git repository.
+- [x] If it is, create and checkout a new feature branch named `podcast-generator`.
+
+## Phase 1: Project Initialization
+- [x] Initialize a new Next.js application using `create-next-app` with TypeScript, Tailwind CSS, and App Router.
+- [x] Install necessary backend dependencies: `rss-parser`, `@google/genai` (for Gemini), `@google-cloud/text-to-speech`.
+- [x] Install utility dependencies: `uuid`, `clsx`, `tailwind-merge`.
+- [x] Create a `.env.local` file and add placeholders for `GEMINI_API_KEY` and `GOOGLE_APPLICATION_CREDENTIALS` (content/path).
+- [x] Verify the project builds and runs locally (`npm run dev`).
+
+## Phase 2: Core Frontend UI
+- [x] Create a global Context (`FeedContext`) to manage the list of RSS feeds and generated podcasts state.
+- [x] Create a `Hero` component with a placeholder or generated image of a robot news anchor.
+- [x] Create a `FeedInput` component allows users to type a URL and add it to the state.
+- [x] Create a `FeedList` component to display active feeds with a "Remove" button.
+- [x] Create a `PodcastPlayer` component that wraps the standard HTML5 audio element and displays podcast details.
+- [x] Assemble the `page.tsx` with the Hero, Feed management section, and a "Generate Podcast" button (initially disabled if no feeds).
+
+## Phase 3: Backend Services - RSS & Gemini
+- [x] Create a Next.js API route handler at `app/api/generate/route.ts`.
+- [x] Implement the `fetchFeeds` function: Use `rss-parser` to fetch user-provided URLs, merge items, sort by date, and slice the top 3 unique articles.
+- [x] Implement the `summarizeArticle` function: Use `@google/genai` to send article content to the Gemini `gemini-2.5-flash` model with the specific prompt defined in specs.
+- [x] Create an "Intro" and "Outro" script generator (can be simple static text or AI-enhanced).
+
+## Phase 4: Backend Services - Audio & Stitching
+- [x] Implement the `generateAudio` function: Use `@google-cloud/text-to-speech` to convert text segments (Intro, Summaries, Outro) into MP3 binary buffers.
+- [x] Implement the `stitchAudio` function: Concatenate the resulting audio buffers into a single buffer.
+- [x] Implement file saving: Write the final buffer to `public/podcasts/[uuid].mp3`.
+- [x] Ensure the `public/podcasts` directory exists or create it dynamically.
+
+## Phase 5: Integration & Polish
+- [x] Connect the Frontend "Generate" button to the `/api/generate` endpoint.
+- [x] Implement a loading state in the UI (spinner or progress bar) while the API is processing.
+- [x] Handle API responses: On success, update the `PodcastContext` with the new podcast URL and show the Player.
+- [x] Implement error handling: Display toast notifications or alerts if RSS fetching or AI generation fails.
+- [x] Style the application using Tailwind CSS to match the "modern & clean" aesthetic.
+
+## Phase 6: Completion & Version Control
+- [ ] Verify application functionality: Add feeds, generate podcast, play audio.
+- [ ] Create a `README.md` file explaining the application functions, how to interact with them, the architecture, file breakdown and how to run and test it locally.
+- [ ] Add all changes to the repository (`git add .`).
+- [ ] Commit the changes (`git commit -m "Complete implementation of Podcast Generator"`).
+- [ ] Push the feature branch to the remote repository, creating a branch with the same name in the remote repository, using the Gemini CLI github MCP server.
+- [ ] Open a pull request for the feature branch using the Gemini CLI github MCP server, leave it open for review, don't merge it.

podcast-generator/.gitignore

@@ -0,0 +1,41 @@
+# See https://help.github.com/articles/ignoring-files/ for more about ignoring files.
+
+# dependencies
+/node_modules
+/.pnp
+.pnp.*
+.yarn/*
+!.yarn/patches
+!.yarn/plugins
+!.yarn/releases
+!.yarn/versions
+
+# testing
+/coverage
+
+# next.js
+/.next/
+/out/
+
+# production
+/build
+
+# misc
+.DS_Store
+*.pem
+
+# debug
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+.pnpm-debug.log*
+
+# env files (can opt-in for committing if needed)
+.env*
+
+# vercel
+.vercel
+
+# typescript
+*.tsbuildinfo
+next-env.d.ts

podcast-generator/README.md

@@ -0,0 +1,55 @@
+# AI News Podcast Generator
+
+This application allows users to generate personalized daily news podcasts from their favorite RSS feeds using AI summarization and natural-sounding text-to-speech.
+
+## Features
+
+- **RSS Feed Management**: Add and remove multiple RSS feeds.
+- **AI Summarization**: Uses Google Gemini (`gemini-2.5-flash`) to summarize the top stories.
+- **Audio Generation**: Uses Google Cloud Text-to-Speech (Chirp) to create a seamless audio experience.
+- **Playback**: Built-in audio player to listen to your generated podcasts.
+
+## Architecture
+
+- **Frontend**: Next.js 14+ (App Router), Tailwind CSS, React Context.
+- **Backend**: Next.js API Routes (`/api/generate`).
+- **AI**: Google Gemini API & Google Cloud TTS.
+
+## Prerequisites
+
+- Node.js 18+
+- Google Gemini API Key
+- Google Cloud Project with Text-to-Speech API enabled and credentials JSON.
+
+## Setup
+
+1.  Clone the repository.
+2.  Install dependencies:
+    ```bash
+    cd podcast-generator
+    npm install
+    ```
+3.  Configure Environment Variables:
+    - Create `.env.local` in `podcast-generator/`.
+    - Add:
+      ```env
+      GEMINI_API_KEY=your_key
+      GOOGLE_APPLICATION_CREDENTIALS=path/to/credentials.json
+      ```
+4.  Run Development Server:
+    ```bash
+    npm run dev
+    ```
+5.  Open [http://localhost:3000](http://localhost:3000).
+
+## Usage
+
+1.  Paste an RSS feed URL (e.g., `https://rss.nytimes.com/services/xml/rss/nyt/HomePage.xml`) into the input field.
+2.  Click "Add". Add more feeds if desired.
+3.  Click "Generate Podcast".
+4.  Wait for the AI to process and generate the audio (this may take 10-20 seconds).
+5.  Listen to your custom news update!
+
+## Testing
+
+Currently, the project supports manual testing via the UI. Ensure you have valid API keys to test the full generation pipeline.

podcast-generator/eslint.config.mjs

@@ -0,0 +1,18 @@
+import { defineConfig, globalIgnores } from "eslint/config";
+import nextVitals from "eslint-config-next/core-web-vitals";
+import nextTs from "eslint-config-next/typescript";
+
+const eslintConfig = defineConfig([
+  ...nextVitals,
+  ...nextTs,
+  // Override default ignores of eslint-config-next.
+  globalIgnores([
+    // Default ignores of eslint-config-next:
+    ".next/**",
+    "out/**",
+    "build/**",
+    "next-env.d.ts",
+  ]),
+]);
+
+export default eslintConfig;

podcast-generator/next.config.ts

@@ -0,0 +1,7 @@
+import type { NextConfig } from "next";
+
+const nextConfig: NextConfig = {
+  /* config options here */
+};
+
+export default nextConfig;