製作 AI 簡報應用程式 VoxDeck，令我意識到自己多需要語音聽寫
How Building an AI Pitch Deck App Made Me Realize How Much I Need Voice Dictation
開發 VoxDeck 的過程中，Wispr Flow 免費訂閲結束，令作者意識到自己多依賴語音聽寫。作者透過 Wispr Flow 在 21 個應用程式中聽寫了 20,048 個字，平均速度為 125 WPM；VoxDeck 以 Next.js 15 和 Google Gemini 建構，可把語音內容整理成簡報、行政摘要及 60 秒講稿等。
Starting my build session late today brought a sudden wave of panic when I realized my Wispr Flow free subscription had officially ended. Building VoxDeck over the last few days had become so seamlessly tied to speaking at 125 WPM across 21 different apps—racking up over 20,000 dictated words[cite: 15]—that going back to a standard keyboard felt like typing through wet cement. Without that lightning-fast voice dictation, my inner friction returned instantly, showing me just how deeply a great tool transforms the developer workflow. It really made me appreciate how much faster raw thought translates into code when your hands aren't locked to a mechanical keyboard. If you've been relying on voice-first tools to crush your building goals, hitting that subscription wall is a harsh reminder of how indispensable they become to your daily routine.
🚀 What is VoxDeck?
VoxDeck is an AI-powered voice-to-deck engine built on Next.js 15 and Google Gemini. Instead of forcing founders to type out rigid bullet points or struggle with a blank screen, VoxDeck takes a raw voice brain-dump and instantly structures it into:
- A 10-Slide YC Narrative Deck
- An Executive Overview
- A 60-Second Spoken Pitch Script
- A TAM / Business Model Breakdown
- Dedicated About Us & FAQ Sections
📊 The Stats That Powered the Build
Before my free tier wrapped up, my Wispr Flow highlights captured a wild ride:
- 20,048 Words Dictated.
- 125 Words Per Minute Average Speed.
- 21 Different Apps Used.
Hitting 125 WPM meant my voice was operating nearly three times faster than my average typing speed. Being able to "brain-dump" architectural layouts, prompt logic, and documentation vocally while my hands focused entirely on writing clean code completely changed my shipping velocity.
🛠️ The Tech Stack
- Framework: Next.js 15 (App Router)
-
AI Integration: Google Gemini API (
GEMINI_API_KEY) for rapid unstructured text parsing - Voice Dictation: Wispr Flow (supporting multi-language brain-dumps in English, Punjabi, Marathi, Tamil, and Japanese)
- Deployment: Vercel (Production serverless deployment)
🎯 Final Thoughts
Building VoxDeck taught me that the true bottleneck of software development isn't thinking or coding—it's translation speed. Going back to manual typing today made me realize how spoiled I got dictating over 20k words[cite: 15].
If you haven't tried pairing your development workflow with high-speed voice dictation, check out your own stats and see how much faster you can ship. Let me know your thoughts in the comments below! 👇
來源：DEV Community · dev.to