VoxMark 2.3.2 for Mac

Mac Utilities

Updated Aug 18, 2026

⬇ Download Now

Cutting pictures to a voiceover usually means scrubbing back and forth, hunting for the start of each sentence. VoxMark removes that grind. Point the panel at your composition or sequence and it renders the real audio mix itself, sends it to a transcription provider you choose, and drops the words back onto the timeline as markers or subtitles. Speakers can be identified and colour coded, and a click on any line in the transcript moves the playhead straight to that moment.

Key Features

• Renders your comp or sequence audio mix and transcribes it in one click
• Creates frame accurate markers or subtitles timed to the real timeline
• Supports Groq, OpenAI Whisper and AssemblyAI with your own API key
• Handles 99 languages with automatic detection and Unicode text
• Identifies speakers, colour codes voices and exports SRT files

How to Download

1. Download from the official site and review the trial and licensing options there.
2. Install VoxMark with the aescripts manager app, then restart After Effects or Premiere Pro.
3. Open the panel, add your API key, and scan your first comp.

System Requirements

You need a Mac with After Effects 2022 or later or Premiere Pro 2022 or later, an internet connection, and an API key from a supported provider. Groq offers a free tier.

FAQs

Do I need to export my audio before transcribing?

No. VoxMark finds the audio layers, including nested ones, and renders the mix itself, so nothing needs lining up afterwards.

Is there a monthly subscription for VoxMark itself?

No. It is a single purchase. Transcription runs through your chosen provider with your own key, with no server in between.

Can it tell different speakers apart?

Yes. With AssemblyAI voices are identified automatically and colour coded. On other providers you can assign voices by hand in the panel.