DEV Community: Vishal Pandey

Dear JavaScript developers

Vishal Pandey — Fri, 25 Sep 2026 17:59:06 +0000

One Package to Parse Them All — Meet pageslice

As a JavaScript developer, I was tired of installing a different package for every file type I needed to parse. One for PDF. One for DOCX. One for Excel. One for CSV. Each with its own API, its own quirks, and its own set of headaches.

Why not just use one package that handles all of it — cleanly?

That's exactly why I built pageslice.

What Can pageslice Do?

Right now, pageslice can parse:

PDF files
DOCX files
XLSX / XLS spreadsheets
CSV files
TXT / MD files

And we're not stopping here — OCR support and more file formats are on the way.

But Wait, There's More

You'd think a document parser is all pageslice does?

Nope.

pageslice also comes with built-in LLM support. No need to set up an AI client separately — just bring your API key and pageslice can:

Extract structured data using Zod schemas
Answer questions directly from your documents
Work with any OpenAI-compatible provider (OpenAI, Gemini, OpenRouter, and more)

One package. Parsing + AI. Done.

Let's Talk Speed

Here's how fast pageslice runs on real documents:

Want to test it on your own machine? Just run:

npx pageslice test

Try It Out

npmjs.com

If pageslice saved you some headaches, consider giving it a ⭐ on GitHub — it means a lot!

Viishal-62 / pageslice

pageslice 📄⚡

Zero-glue document parser & AI extraction toolkit for Node.js & TypeScript.
Slice any PDF, DOCX, XLSX, TXT, or Markdown into raw text or guaranteed typed JSON using Zod schemas.

Why `pageslice`?

Every developer building document AI in JavaScript/TypeScript knows the pain:

Installing pdf-parse, mammoth, and fighting node-gyp / C++ native build errors in Next.js, Vercel, and Docker.
Writing 80+ lines of glue code to handle file formats, buffers, and clean whitespace.
Dealing with LLMs returning broken JSON or missing schema fields.

pageslice eliminates all of that. One single package. Zero native C++ dependencies. Pure JavaScript. Works offline for text parsing, and supports OpenAI, Google Gemini, OpenRouter, or local Ollama for AI.

Key Features

📦 All-in-One: PDF, DOCX, XLSX/XLS (Excel), TXT, MD, CSV, JSON support out of the box.
🔓 0 API Keys Needed for Text: Extract…

View on GitHub

Feedback, suggestions, and contributions are always welcome. Thanks for reading! 🙌

What you do to be updated?

Vishal Pandey — Fri, 28 Aug 2026 13:35:01 +0000

Do you ever feel completely overwhelmed by the sheer volume of tech news?

Between endless newsletters, massive long-form articles, and breaking updates every single hour, trying to stay up-to-date can easily feel like a second full-time job. I’ve always wanted to remain informed about what's happening in the industry, but honestly? I hate reading through walls of text just to catch up.

If you are like me and suffer from tech-news fatigue, I recently found a workflow that completely solved this problem for me, and I wanted to share it with you all.

The Problem with Traditional Tech News

Every morning, we are bombarded with:

Densely packed newsletters that take too long to skim.
Tab-hoarding, where we open 15 articles to read "later" and never actually get to them.
Noise that makes it hard to separate genuinely important engineering shifts from marketing fluff.

I wanted something frictionless—something that gives me the signal without all the noise.

Finding a Better Way

After looking around for alternative ways to consume updates, I started using Recent Brief.

Instead of forcing me to sit down and read through articles, it delivers a quick, curated brief straight to me. If you want to hear what it sounds like in practice, you can listen to a sample latest brief here.

How It Fits Into My Morning Routine

The best part is how seamlessly it integrates into my day without adding friction.

Every single day at 8:00 AM, my brief lands right on time based on my custom preferences. My morning routine now looks like this:

Wake up and grab a coffee ☕
Listen to the brief while waking up 🎧
Head straight into development work without missing a beat 💻

It’s fast, incredibly efficient, and keeps me fully in the loop.

Let's Chat!

How do you keep up with the endless stream of tech updates without burning out? Have you tried out audio digests or alternative ways to consume news, or are you still battling the endless browser tabs?

Let me know your thoughts, routines, and workflows in the comments below! 👇

Best anonymous confession apps in 2026

Vishal Pandey — Fri, 10 Apr 2026 07:45:51 +0000

Tried anonymous apps again after a long time… and ngl it still feels kinda fake

Like I got messages instantly after sharing the link — but they all felt generic af
“someone has a crush on you 👀” type stuff 💀

I get why they do it (to keep you hooked), but it kinda kills the whole point of anonymity

I wanted something more… real? like actual unfiltered thoughts, even if it’s brutal

Found this small site recently where you can just create a board and people drop anything anonymously — no login, no forced prompts

honestly feels way more raw compared to most apps

curious if anyone else feels the same about these apps or am I overthinking it lol

(if you wanna try it: https://www.teaadrop.xyz)

Project : Async-Await || Real time visual narrator + Multilanguage Tutor

Vishal Pandey — Mon, 01 Sep 2025 07:22:49 +0000

Here you can see our visual-narrator, so you can cleary see a cool toggle button also so yessss it will work with your** rear camera** and also on the right side there is a box where you will get written narration and you will hear voice also in real time

Here in the second image you can see cleary language tutor will teach you how to speak with fluency and you have multiple voice selection + language selection option also

Here is the github repo you can check :- Async-Await

This project is also part of murf ai coding challenge 4 #murfai #murfcc4
Tools we have used to make it work

- Gemini - response
- google cloud speech to text - for transcription
- murf ai - for real time audio streaming also murf ai gives you ~120+voices in ~28+languages

Listenify – Convert Complex Text into Clean, Audio-Based Learning

Vishal Pandey — Sun, 29 Jun 2025 14:40:47 +0000

This is a submission for the Murf AI Coding Challenge 2)

🚀 What I Built

Listenify is an AI-powered audio companion that converts written content into high-quality, natural-sounding audio. It’s designed for users who prefer listening over reading, enabling content consumption on the go. From URLs to custom prompts, PDFs, and interactive AI conversations — Listenify transforms everything into speech.

It solves the problem of accessibility and convenience for learners, professionals, and casual users who want to save time and boost productivity through audio experiences.

🎥 Demo

Here is the video demo in action

🔗 Code Repository:
GitHub Repo – Listenify

🔧 How I Used Murf API

Murf API powers the core audio generation across all Listenify features, enabling natural, expressive voiceovers.

Here’s how I integrated it into each module:

URL to Audio: Parsed article → Gemini simplification → Murf for spoken output
Text to Audio: User writes prompt → Gemini response → Murf generates audio Text Prompt to AI Response + Audio: User writes a custom prompt, selects a language (e.g., Hindi, English, etc.), and gets a Gemini-generated response in that language — which is then sent to Murf to produce localized audio and if they want audio in different language they can do it
PDF to Audio: Uploaded document → Extracted readable text → Murf voiceover
Talk to AI: Real-time user queries → Gemini responds → Murf instantly converts replies to voice

✅ This last feature offers a hands-free, AI voice assistant experience — made possible through Murf's responsive and realistic audio generation.

🌍 Use Case & Impact

Who can benefit?

Students can learn interactively by talking to the AI and listening to explanations in real time
Visually impaired users or those with learning differences can use voice-first AI for hands-free interaction
Busy professionals can ask questions on the go and get verbal answers — like an AI podcast
Language learners can practice conversations with AI and hear responses in various accents and languages

How it improves existing experiences:

✅ Voice-First AI Access: Unlike typical AI tools that are text-based, Listenify allows users to speak to the AI and get spoken replies, which feels more human and intuitive
✅ Multilingual Support: Users can choose their preferred response languager but for now it only supports english and hindi and voice of male and female , helping break language barriers
✅ Accessibility-Friendly: Makes AI conversational tools usable for those who can't or don’t want to type
✅ Engaging Learning: Turns boring text-based Q&A into an interactive, auditory learning experience

This is a solo submission by: @vishal_pandey_cc36c279e7a