tanpreetjolly

tanpreetjolly / browser-whisper

Public

Transcribe Audio & Videos completely in browser with WebGPU and WebCodecs. 100% private and offline with WASM fallbacks

whisper.tanpreet.xyz audio-to-text mediabunny transcribe-audio-files transcriber transcription
33
1
100% credibility
Found Mar 15, 2026 at 33 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

A JavaScript library for transcribing audio files to text using OpenAI's Whisper model entirely within the web browser, with no servers or external services required.

How It Works

1
🔍 Discover the tool

You stumble upon Browser Whisper, a handy way to turn any audio recording into readable text right inside your web browser, without sending files anywhere.

2
📥 Add it to your site

You simply include this lightweight tool into your own webpage or app, making speech-to-text available instantly.

3
⚙️ Prepare your page

You update a couple of settings on your webpage to ensure smooth and secure handling of audio files.

4
🎤 Pick your audio

You choose an audio or video file from your device, like a podcast, meeting recording, or voice note.

5
✨ Start transcribing

Hit go, and watch as the tool processes your file piece by piece, streaming out the spoken words with timestamps in real time.

📝 Enjoy your transcript

You receive the complete, accurate text of your audio, ready to copy, edit, or share, all done privately in your browser.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 33 to 33 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 browser-whisper?

browser-whisper runs OpenAI's Whisper model in the browser to transcribe audio and video files to text, using WebGPU for inference and WebCodecs for decoding. It solves the need for private, offline transcription—no servers, no API keys like Amazon Transcribe, with models caching locally after the first download. This TypeScript library npm-installs into web apps, streaming segments via async iterators or callbacks for real-time results.

Why is it gaining traction?

Unlike server-dependent github transcribe ai tools such as buzz transcribe github or gpt 4o transcribe github, it delivers transcribe audio to text free no sign up entirely client-side, with hardware acceleration and WASM fallbacks for broad browser support. Developers hook into progress events, language options, and model sizes from tiny (64MB) to large (3GB), enabling smooth UIs without backend plumbing. Privacy wins over open ai whisper browser wrappers that leak data.

Who should use this?

Frontend devs building PWAs for transcribe audio file to text in podcast players or meeting recorders. Indie hackers prototyping transcribe youtube video github demos or vibe transcribe github clones without cloud costs. Privacy-focused teams replacing transcribe audio free online google with offline github transcribe whisper alternatives.

Verdict

Solid docs and demo make it usable now despite 33 stars and 1.0% credibility score signaling early maturity—test coverage looks light. Prototype for browser-native transcription, but wait for more adoption before production.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.