Guide

How to use Whisper in Premiere Pro

Whisper isn't built into Premiere Pro — here's what it takes to actually use it in a real editing workflow, manually or via a plugin.

Get CaptionLab — $39 once → See how it works
🛡 14-day refund · 🔒 100% offline · ⚡ One-time payment, no subscription

The manual route

You can technically use Whisper with Premiere Pro today, without any plugin, in a roundabout way.

1️⃣

Export audio from your sequence

File → Export → Media, audio only, from the clip or sequence you want transcribed.

2️⃣

Run Whisper on the exported file

Via the command line (pip install openai-whisper), or a standalone Whisper app.

3️⃣

Import the SRT back into Premiere

File → Import, then drag the resulting SRT onto your timeline as a caption track.

The plugin route

CaptionLab automates the steps above into one action: select a clip in Premiere, click Generate Subtitles, and the SRT lands on your timeline — audio export, Whisper transcription, and import all happen automatically, without leaving Premiere Pro.

Frequently asked questions

Is the manual route free?
Yes, Whisper itself is open-source and free to run — the cost is your own time setting it up and doing the export/import steps for every clip.
Which Whisper model size should I use manually?
large-v2 or large-v3 for the best accuracy if your hardware can handle it; smaller models (base, small) are faster but noticeably less accurate, especially for non-English audio.
Does the plugin route lose any control compared to the manual route?
CaptionLab fixes the model at large-v2 for the best accuracy/speed balance across supported hardware — if you specifically need a different model size or custom parameters, the manual route offers more control.

Skip the export/import loop entirely

One-time $39. Works offline. 14-day money-back guarantee.

Get CaptionLab →