nispa

nispa / nispa-whisper

Public

A portable desktop application that allows you to transcribe audio and video files using the power of OpenAI's Whisper model, optimized for speed with `faster-whisper`. It provides a user-friendly interface to manage, view, and edit your transcriptions.

19
1
89% credibility
Found Mar 05, 2026 at 19 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

A desktop app that transcribes audio and video files into editable text locally with preview, editing, and export options.

How It Works

1
📥 Open the app

You launch the friendly transcription app and see your list of past projects or start a fresh one.

2
🎵 Pick your audio or video

Drag in a recording from your phone, meeting, or podcast to get ready for transcribing.

3
⚙️ Choose your preferences

Pick the speaking language, quality level, and whether to smooth out quiet voices for clearer results.

4
▶️ Start transcribing

Hit go and relax as the app listens and turns speech into text right before your eyes.

5
✏️ Review and edit

Click words to fix them while the video plays in sync, making it easy to perfect the script.

📤 Export your work

Download clean subtitles, full text, or shareable files, ready for videos or notes.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 19 to 19 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is nispa-whisper?

nispa-whisper is a portable desktop app that lets you transcribe audio and video files locally using OpenAI's Whisper model via the optimized `faster-whisper` engine. Built with a TypeScript React frontend and Python Flask backend, it handles everything from upload to editing in a clean UI, including synced video playback, waveform navigation, and exports like SRT, VTT, JSON, or AI-ready MCP formats. Perfect for devs wanting a github portable apps-style tool that runs offline on Windows, Linux, or macOS without cloud dependencies.

Why is it gaining traction?

It stands out with GPU acceleration for 2-5x faster processing than stock Whisper, plus audio normalization previews to boost quiet speech clarity before transcribing. The full editor with undo/redo, find/replace, and real-time segment tweaks feels pro, and the exposed REST API allows scripting uploads or status checks via curl. As a portable desktop organizer for media files, it beats web tools on privacy and speed for local workflows.

Who should use this?

Podcasters editing episodes, researchers transcribing interviews, or video creators needing quick subtitles without uploading to the cloud. Devs building portable github desktop apps or integrating local transcription into tools like portable python github scripts will appreciate the API and one-click install scripts.

Verdict

Grab it if you need reliable local transcription—solid docs, tests, and a REST API make it dev-friendly despite 19 stars signaling early maturity. The 0.8999999761581421% credibility score reflects promise in a niche space; test on your hardware first for GPU quirks. (198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.