⭐ 14-Day Free Trial — No Credit Card Required

The Professional Subtitle Editor
Built for Video Editors

Transcribe audio and video locally. Edit subtitles with professional typography controls. Export SRT, VTT, and native Premiere Pro JSON files — all free to start.

Start Transcribing Free → Start 14-Day Free Trial
🔒 Audio never uploaded ⚡ Powered by Whisper AI 🎬 Works with Premiere Pro ∞ No file size limits

Everything a video editor needs

🎵

Audio & Video Transcription

Upload MP3, WAV, M4A, MP4, MOV, WebM. Whisper AI transcribes locally on your device — no cloud upload, no queue, no waiting.

✏️

Professional Subtitle Editor

Edit transcript word by word. Adjust timestamps. Split and merge lines. Custom fonts, stroke, shadow, and position controls — all in real time.

👁️

Live Preview Window

See your subtitles on a real video preview as you edit. Switch between 16:9 and 9:16 canvas sizes. Preview exactly what your audience will see.

🎨

Typography Controls

Upload your own brand fonts (.ttf, .otf). Control stroke width, shadow opacity, blur, X/Y offsets. Bold, position, color — full creative control.

📦

Export for Any NLE

Download frame-accurate SRT, VTT, plain text, and native Adobe Premiere Pro JSON — imports directly into Premiere's Text-Based Editing panel.

🔒

100% Private

All processing happens in your browser using Web Workers and WebGPU. Your video and audio data never leaves your device. Zero cloud storage.

Simple, transparent pricing

Start with the free plan. Upgrade when you need more power.

Free
$0/forever
No signup required. Start immediately.
  • Audio file transcription (MP3, WAV, M4A)
  • Full transcript text editor
  • Subtitle timestamp editor
  • Waveform timeline
  • Live video preview window
  • SRT subtitle export
  • Plain text (.txt) export
Start for free →
Pro
$16/month
For power users and agencies.
  • Everything in Starter
  • Cloud transcription via Groq (instant)
  • 45-min audio transcribed in under 60 seconds
  • AI Viral Segment Finder
  • Animated caption templates
  • Auto video clipping by AI timestamps
  • Priority support
Coming soon →

How it works

01

Upload your file

Drop any audio or video file. MP3, WAV, M4A, MP4, MOV, WebM. Any file size. Processed entirely on your device.

02

AI transcribes locally

Whisper AI runs in your browser using Web Workers. No upload. No queue. Results appear in real time as each chunk completes.

03

Edit, style and export

Fix words, adjust timestamps, style subtitles, preview on video. Export SRT, VTT, plain text, or Premiere Pro JSON — ready to import.

Frequently Asked Questions

Does my audio or video get uploaded to a server?

No. AudioSRT processes everything locally in your browser using asynchronous Web Workers. Your files never leave your device. Zero cloud storage, zero upload latency, zero privacy risk.

How do I import subtitles into Adobe Premiere Pro?

Export the Premiere Pro JSON file from AudioSRT. In Premiere Pro, open the Text panel → click (...) → Import → Import Static Transcript. Your subtitles will load frame-accurately onto your timeline.

How accurate is the transcription?

AudioSRT uses OpenAI's Whisper model — one of the most accurate open-source speech recognition systems available. It handles multiple languages, accents, background noise, and technical vocabulary well.

Will my browser freeze on large video files?

No. We use asynchronous Web Workers and WebGPU memory-chunking that completely separates AI processing from the browser UI thread. Long files process in chunks so you can edit earlier sections while later sections are still transcribing.

What is the difference between Free and Starter?

Free supports audio-only transcription with SRT and TXT export — no signup needed. Starter ($3/month or ₹99/month) adds video uploads, custom font injection, advanced typography controls, VTT export, and Premiere Pro JSON. Start with a 14-day free trial — no credit card required.

Is there a desktop app?

Yes — coming soon. Our free Tauri desktop app bypasses browser memory limits and uses your system's native GPU for 15-20x faster transcription. Available for Windows and Mac.

Under the Hood: Client-Side Media Processing Architecture

AudioSRT is a browser-native subtitle editor and NLE companion utility supporting MP3, WAV, M4A, MP4, MOV, and WebM. All processing executes inside local browser runtime environments using asynchronous Web Workers and WebGPU memory-chunking pipelines. Files never transmit to external cloud networks. The platform generates frame-accurate SRT, VTT, plain text, and Adobe Premiere Pro JSON session files compatible with Premiere Pro Text-Based Editing, DaVinci Resolve, and Final Cut Pro. Custom brand typography is injected via the HTML5 FontFace API with real-time canvas rendering. The Web Worker architecture separates Whisper AI inference from the browser's primary UI thread — guaranteeing zero freezes during multi-hour podcast transcription.