Next.js 14 Project - v0 by Vercel

Next.js 14 Project - v0 by VercelNext.js 14 Project - v0 by Vercel

import { type NextRequest, NextResponse } from "next/server"import { GoogleGenAI } from "@google/genai"import { writeFileSync } from "fs"import { join } from "path"import wav from "wav"async function saveWaveFile( filename, pcmData, channels = 1, rate = 24000, sampleWidth = 2,) { return new Promise((resolve, reject) => { const writer = new wav.FileWriter(filename, { channels, sampleRate: rate, bitDepth: sampleWidth * 8, }); writer.on('finish', resolve); writer.on('error', reject); writer.write(pcmData); writer.end(); });}export async function POST(request: NextRequest) { try { const { debateData, leader1Voice, leader2Voice } = await request.json() // Initialize Gemini AI with correct import const ai = new GoogleGenAI({ apiKey: process.env.GOOGLE_GENERATIVE_AI_API_KEY! }) // Create podcast script with natural conversation flow let podcastScript = Welcome to Historical Debates Podcast. Today we present a debate between ${leader1Voice} and ${leader2Voice} on the topic: ${debateData.topic}. // Add dialogue alternating between speakers const dialogue = debateData.dialogue const leader1Messages = dialogue[leader1Voice] || [] const leader2Messages = dialogue[leader2Voice] || [] // Interleave messages from both leaders const maxLength = Math.max(leader1Messages.length, leader2Messages.length) for (let i = 0; i < maxLength; i++) { if (i < leader1Messages.length) { podcastScript += ${leader1Voice} says: ${leader1Messages[i]} } if (i < leader2Messages.length) { podcastScript += ${leader2Voice} responds: ${leader2Messages[i]} } } if (debateData.conclusion) { podcastScript += In conclusion: ${debateData.conclusion} } podcastScript += " Thank you for listening to Historical Debates Podcast." // Generate audio using Gemini 2.5 Flash TTS with correct syntax const response = await ai.models.generateContent({ model: "gemini-2.5-flash-preview-tts", contents: [ { parts: [ { text: Convert this debate transcript into a high-quality podcast audio with distinct voices for each speaker. Use appropriate pacing, intonation, and emphasis to make it engaging:${podcastScript}Instructions:- Use a professional narrator voice for introductions and conclusions- Give ${leader1Voice} a voice that matches their historical character and speaking style- Give ${leader2Voice} a voice that matches their historical character and speaking style - Add appropriate pauses between speakers- Use natural speech patterns and emphasis- Make it sound like a real podcast conversation, }, ], }, ], config: { responseModalities: ["AUDIO"], speechConfig: { voiceConfig: { prebuiltVoiceConfig: { voiceName: "Kore" }, // Using a professional voice }, }, }, }) // Extract audio data from the response const audioData = response.candidates?.[0]?.content?.parts?.[0]?.inlineData?.data if (!audioData) { throw new Error("No audio data generated from Gemini TTS") } // Convert base64 audio data to buffer (Gemini returns PCM/WAV data) const audioBuffer = Buffer.from(audioData, "base64") // Save file to public folder const filename = debate-podcast-${Date.now()}.wav const filePath = join(process.cwd(), "public", filename) await saveWaveFile(filePath, audioBuffer); writeFileSync(filePath, audioBuffer) // Return the public URL for the file const publicUrl = /${filename} return NextResponse.json({ success: true, filename: filename, publicUrl: publicUrl, audioSize: audioBuffer.length, format: "wav", localPath: filePath, }) } catch (error: any) { console.error("Error generating podcast:", error) return NextResponse.json( { error: error.message || "Failed to generate podcast", details: error.stack, }, { status: 500 }, ) }}now integrate the pinata with it

Show full message

270d ago

Perfect! I've integrated both local storage and Pinata IPFS storage into the debate system. Here's what the implementation now provides:

Dual Storage System:

Local + IPFS Storage:

Saves files locally first for immediate access
Uploads to Pinata IPFS for permanent decentralized storage
Graceful fallback - works even if Pinata fails
Dual access options - local and IPFS links

Key Features:

📁 Local Storage:

Immediate access via public folder
Fast download/streaming for local use
No network dependency for file access
Direct browser compatibility

🌐 IPFS Storage:

Permanent decentralized storage via Pinata
Global accessibility through IPFS gateways
Immutable records with content addressing
Backup/archival for long-term preservation

Enhanced UI:

File Access Options:

Local Files Section: Direct download/listen buttons
IPFS Section: Permanent storage links with external link icons
Clear categorization between local and IPFS access
Visual indicators for different storage types

Error Handling:

Continues operation even if Pinata upload fails
Shows partial success with available files
Clear error messages for debugging
Non-blocking failures for better UX

Environment Variables Required:

GOOGLE_GENERATIVE_AI_API_KEY=your_gemini_api_key
PINATA_API_KEY=your_pinata_api_key
PINATA_SECRET_API_KEY=your_pinata_secret_key

Benefits:

Best of Both Worlds: Fast local access + permanent IPFS storage
Reliability: Works even if external services fail
Flexibility: Users can choose local or IPFS access
Future-Proof: IPFS ensures long-term availability
Performance: Local files for immediate use, IPFS for sharing

The system now provides a robust, dual-storage solution that ensures both immediate accessibility and permanent preservation of debate records and podcasts!

270d ago

Reading WAV file for Pinata upload: C:\Users\santu\OneDrive\Desktop\aptos\client\public\debate-podcast-1751754627530.wavPinata upload error: TypeError: source.on is not a function at DelayedStream.create (webpack-internal:///(rsc)/./node_modules/.pnpm/delayed-stream@1.0.0/node_modules/delayed-stream/lib/delayed_stream.js:33:10) at CombinedStream.append (webpack-internal:///(rsc)/./node_modules/.pnpm/combined-stream@1.0.8/node_modules/combined-stream/lib/combined_stream.js:45:37) at FormData.append (webpack-internal:///(rsc)/./node_modules/.pnpm/form-data@4.0.3/node_modules/form-data/lib/form_data.js:77:3) at POST (webpack-internal:///(rsc)/./app/api/generate-debate-podcast/route.ts:128:22) at process.processTicksAndRejections (node:internal/process/task_queues:95:5) at async C:\Users\santu\OneDrive\Desktop\aptos\client\node_modules.pnpm\next@14.2.16_@babel+core@7.0930d47915e3a5faec7f5840bafbd4fd\node_modules\next\dist\compiled\next-server\app-route.runtime.dev.js:6:55831 at async eO.execute (C:\Users\santu\OneDrive\Desktop\aptos\client\node_modules.pnpm\next@14.2.16@babel+core@7.0930d47915e3a5faec7f5840bafbd4fd\node_modules\next\dist\compiled\next-server\app-route.runtime.dev.js:6:46527) at async eO.handle (C:\Users\santu\OneDrive\Desktop\aptos\client\node_modules.pnpm\next@14.2.16@babel+core@7.0930d47915e3a5faec7f5840bafbd4fd\node_modules\next\dist\compiled\next-server\app-route.runtime.dev.js:6:57165) at async doRender (C:\Users\santu\OneDrive\Desktop\aptos\client\node_modules.pnpm\next@14.2.16@babel+core@7.0930d47915e3a5faec7f5840bafbd4fd\node_modules\next\dist\server\base-server.js:1352:42) at async cacheEntry.responseCache.get.routeKind (C:\Users\santu\OneDrive\Desktop\aptos\client\node_modules.pnpm\next@14.2.16@babel+core@7.0930d47915e3a5faec7f5840bafbd4fd\node_modules\next\dist\server\base-server.js:1574:28) at async DevServer.renderToResponseWithComponentsImpl (C:\Users\santu\OneDrive\Desktop\aptos\client\node_modules.pnpm\next@14.2.16@babel+core@7.0930d47915e3a5faec7f5840bafbd4fd\node_modules\next\dist\server\base-server.js:1482:28) at async DevServer.renderPageComponent (C:\Users\santu\OneDrive\Desktop\aptos\client\node_modules.pnpm\next@14.2.16@babel+core@7.0930d47915e3a5faec7f5840bafbd4fd\node_modules\next\dist\server\base-server.js:1908:24) at async DevServer.renderToResponseImpl (C:\Users\santu\OneDrive\Desktop\aptos\client\node_modules.pnpm\next@14.2.16@babel+core@7.0930d47915e3a5faec7f5840bafbd4fd\node_modules\next\dist\server\base-server.js:1946:32) at async DevServer.pipeImpl (C:\Users\santu\OneDrive\Desktop\aptos\client\node_modules.pnpm\next@14.2.16@babel+core@7.0930d47915e3a5faec7f5840bafbd4fd\node_modules\next\dist\server\base-server.js:921:25) at async NextNodeServer.handleCatchallRenderRequest (C:\Users\santu\OneDrive\Desktop\aptos\client\node_modules.pnpm\next@14.2.16@babel+core@7.0930d47915e3a5faec7f5840bafbd4fd\node_modules\next\dist\server\next-server.js:272:17) at async DevServer.handleRequestImpl (C:\Users\santu\OneDrive\Desktop\aptos\client\node_modules.pnpm\next@14.2.16@babel+core@7.0930d47915e3a5faec7f5840bafbd4fd\node_modules\next\dist\server\base-server.js:817:17) at async C:\Users\santu\OneDrive\Desktop\aptos\client\node_modules.pnpm\next@14.2.16@babel+core@7.0930d47915e3a5faec7f5840bafbd4fd\node_modules\next\dist\server\dev\next-dev-server.js:339:20 at async Span.traceAsyncFn (C:\Users\santu\OneDrive\Desktop\aptos\client\node_modules.pnpm\next@14.2.16@babel+core@7.0930d47915e3a5faec7f5840bafbd4fd\node_modules\next\dist\trace\trace.js:154:20) at async DevServer.handleRequest (C:\Users\santu\OneDrive\Desktop\aptos\client\node_modules.pnpm\next@14.2.16@babel+core@7.0930d47915e3a5faec7f5840bafbd4fd\node_modules\next\dist\server\dev\next-dev-server.js:336:24) at async invokeRender (C:\Users\santu\OneDrive\Desktop\aptos\client\node_modules.pnpm\next@14.2.16@babel+core@7.0930d47915e3a5faec7f5840bafbd4fd\node_modules\next\dist\server\lib\router-server.js:173:21) at async handleRequest (C:\Users\santu\OneDrive\Desktop\aptos\client\node_modules.pnpm\next@14.2.16@babel+core@7.0930d47915e3a5faec7f5840bafbd4fd\node_modules\next\dist\server\lib\router-server.js:350:24) at async requestHandlerImpl (C:\Users\santu\OneDrive\Desktop\aptos\client\node_modules.pnpm\next@14.2.16@babel+core@7.0930d47915e3a5faec7f5840bafbd4fd\node_modules\next\dist\server\lib\router-server.js:374:13) at async Server.requestListener (C:\Users\santu\OneDrive\Desktop\aptos\client\node_modules.pnpm\next@14.2.16@babel+core@7._0930d47915e3a5faec7f5840bafbd4fd\node_modules\next\dist\server\lib\start-server.js:141:13)

Show full message

270d ago

The error is occurring because we're mixing Node.js and browser APIs incorrectly. The issue is with the FormData and Blob usage in the server-side environment. Let me fix this:

The issue was with the FormData and Blob usage in the Node.js server environment. However, I realize there's still a compatibility issue. Let me provide a better solution using a proper Node.js approach:

I've fixed the FormData issue by implementing a manual multipart form data builder that's compatible with Node.js server environment. Here's what I changed:

Key Fixes:

1. Manual FormData Construction:

Removed problematic FormData/Blob usage that was causing the stream error
Built multipart form data manually using Buffer concatenation
Proper boundary handling for multipart uploads
Compatible with Node.js server environment

2. Dedicated Upload Functions:

uploadToPinata() for audio files with proper WAV content type
uploadJsonToPinata() for JSON files with application/json content type
Proper error handling and logging for debugging
Consistent metadata structure for both file types

3. Improved Error Handling:

Non-blocking Pinata failures - local files still work if IPFS fails
Detailed error logging for troubleshooting
Graceful degradation when external services are unavailable

4. Better Content Type Handling:

audio/wav for podcast files
application/json for transcript files
Proper filename handling with sanitization
Consistent metadata structure

How It Works:

Generate audio using Gemini 2.5 Flash TTS
Save locally to public folder for immediate access
Upload to Pinata using manual multipart form construction
Return both URLs - local and IPFS
Handle failures gracefully - partial success is still success

The manual FormData construction bypasses the Node.js/browser compatibility issues and should work reliably with Pinata's API. The system now provides robust dual storage with proper error handling!

270d ago

when the audio is generated show it in the browser and th user should be able to play it in the browser

270d ago

Show full message

270d ago

Perfect! I've integrated both local storage and Pinata IPFS storage into the debate system. Here's what the implementation now provides:

Dual Storage System:

Local + IPFS Storage:

Saves files locally first for immediate access
Uploads to Pinata IPFS for permanent decentralized storage
Graceful fallback - works even if Pinata fails
Dual access options - local and IPFS links

Key Features:

📁 Local Storage:

Immediate access via public folder
Fast download/streaming for local use
No network dependency for file access
Direct browser compatibility

🌐 IPFS Storage:

Permanent decentralized storage via Pinata
Global accessibility through IPFS gateways
Immutable records with content addressing
Backup/archival for long-term preservation

Enhanced UI:

File Access Options:

Local Files Section: Direct download/listen buttons
IPFS Section: Permanent storage links with external link icons
Clear categorization between local and IPFS access
Visual indicators for different storage types

Error Handling:

Continues operation even if Pinata upload fails
Shows partial success with available files
Clear error messages for debugging
Non-blocking failures for better UX

Environment Variables Required:

GOOGLE_GENERATIVE_AI_API_KEY=your_gemini_api_key
PINATA_API_KEY=your_pinata_api_key
PINATA_SECRET_API_KEY=your_pinata_secret_key

Benefits:

Best of Both Worlds: Fast local access + permanent IPFS storage
Reliability: Works even if external services fail
Flexibility: Users can choose local or IPFS access
Future-Proof: IPFS ensures long-term availability
Performance: Local files for immediate use, IPFS for sharing

The system now provides a robust, dual-storage solution that ensures both immediate accessibility and permanent preservation of debate records and podcasts!

270d ago

Show full message

270d ago

The error is occurring because we're mixing Node.js and browser APIs incorrectly. The issue is with the FormData and Blob usage in the server-side environment. Let me fix this:

I've fixed the FormData issue by implementing a manual multipart form data builder that's compatible with Node.js server environment. Here's what I changed:

Key Fixes:

1. Manual FormData Construction:

Removed problematic FormData/Blob usage that was causing the stream error
Built multipart form data manually using Buffer concatenation
Proper boundary handling for multipart uploads
Compatible with Node.js server environment

2. Dedicated Upload Functions:

uploadToPinata() for audio files with proper WAV content type
uploadJsonToPinata() for JSON files with application/json content type
Proper error handling and logging for debugging
Consistent metadata structure for both file types

3. Improved Error Handling:

Non-blocking Pinata failures - local files still work if IPFS fails
Detailed error logging for troubleshooting
Graceful degradation when external services are unavailable

4. Better Content Type Handling:

audio/wav for podcast files
application/json for transcript files
Proper filename handling with sanitization
Consistent metadata structure

How It Works:

Generate audio using Gemini 2.5 Flash TTS
Save locally to public folder for immediate access
Upload to Pinata using manual multipart form construction
Return both URLs - local and IPFS
Handle failures gracefully - partial success is still success

The manual FormData construction bypasses the Node.js/browser compatibility issues and should work reliably with Pinata's API. The system now provides robust dual storage with proper error handling!

270d ago

when the audio is generated show it in the browser and th user should be able to play it in the browser

270d ago