your-next-story.mp4
.mp4.wav.mov
Start with your story.
Create a project from a video or audio file. Keep everything organized in a local library, ready to pick up again.
YOUR WORDS. FRONT AND CENTER.
Good stories deserve
great captions.
From the first spoken word to the final frame.
Transcribe, edit, and style your captions in one thoughtful
desktop workspace. Powered by Whisper. Entirely on your device.
Windows 10 / 11 · macOS (Apple Silicon) Local processing v0.2.0
Less busywork.
More storytelling.
More storytelling.
THE WHISPERSTUDIO WORKSPACELOCAL. FOCUSED. YOURS.
A full workspace. A very focused workflow.
FROM RAW RECORDING
TO READY TO SHARE.
BRING YOUR STORY.
TO READY TO SHARE.
MP4 MOV MKV WAV MP3 M4A
VIDEO OR AUDIO.BRING YOUR STORY.
01 / FIND YOUR FLOWBig ideas.
Big ideas.
Small learning curve.
No complicated handoffs. Just a clear path from
your recording to captions that feel like you.
01 — BRING IT IN
Whisper, working locally
02 — LET IT LISTENSpeech becomes text.
Choose your Whisper model and transcribe. Start with natural phrases or word-by-word captions, then refine the timing.
Make it yours.
VideoSRTTXT
A little polish. A big difference.
Shape the look, review your captions, and export a captioned video, subtitle file, or clean transcript.
02 / GIVE WORDS CHARACTERThe same words.
The same words.
A different feeling.
Quiet and cinematic. Bold and unmissable. Start with a caption preset, then make every detail your own.
Fonts, weight, fill, outline, shadow, and highlights.
All adjustable inside the app.
All adjustable inside the app.
CAPTION PLAYGROUNDTRY A STYLE ↙
PREVIEW
Interactive style illustration. Edit your full video in the desktop app.
03 / ROOM FOR THE DETAILSCreative control.
Creative control.
Without the clutter.
The useful things, right where you need them.
Built around the way you finish a project.
Every word. Every beat.
Edit the text, adjust the timestamps, and watch your changes alongside the video. Your captions stay in your hands.
01
00:01 — 00:03
A story starts with a moment.
02
00:03 — 00:05
EDITINGGive that moment a voice.
03
00:05 — 00:07
Make every word count.
Your machine.
Your model.
Go light for a quick draft, or choose a larger model for more demanding audio. Download and manage models in one place.
Tiny
Base
Small
Medium
Large
Leave. Come back. Keep creating.
Local projects and autosaved edits keep your work together. Moved your source file? Relink it and carry on.
One project. More possibilities.
Burn your styled captions into an MP4, export an SRT for your next edit, or keep the words as a TXT transcript.
ON YOUR DEVICEaudio → captions → export
LOCAL BY DESIGNYour footage.
Your footage.
Your business.
Your audio stays on your computer for transcription. Your projects live on disk. Your exports are processed locally. Download a model once, then settle into your own offline workflow.
No cloud upload for transcriptionDoes WhisperStudio work offline?
Yes. Transcription, caption editing, and video export run on your computer. You need an internet connection to download the app and your chosen Whisper model first. Once the model is downloaded, you can work offline.
Which video and audio files can I use?
Import common video formats including MP4, MKV, MOV, and WebM, or audio files such as WAV, MP3, and M4A. WhisperStudio uses FFmpeg to prepare audio for transcription.
Can I export subtitles without rendering a video?
Yes. Export captions as an SRT subtitle file or a TXT transcript. You can also export an MP4 with styled captions burned directly into the video.
Which Whisper model should I choose?
Start with Tiny for quick drafts or a smaller machine. Larger models can improve transcription accuracy, but require more memory and processing time. The built-in model library lets you compare and download models, including quantized variants.
What are the system requirements?
WhisperStudio supports Windows 10 and Windows 11 (64-bit), and macOS on Apple Silicon (aarch64). You need at least 4 GB of RAM; 8 GB or more is recommended for longer videos and larger models. Leave extra disk space for downloaded models and exported media.
Are my projects saved automatically?
Caption edits, styles, layout, and generation preferences autosave to your local project. Your original media stays linked to its location on disk. If you move that file, use Relink to reconnect it without losing your captions.
Can I transcribe languages other than English?
The model library includes multilingual Whisper models as well as English-specific options. Choose a model that supports your audio language. Results depend on the model, language, recording quality, and your hardware.
YOUR NEXT STORY STARTS HERELet your words
take the spotlight.
A focused desktop studio for captions that feel like you.
Windows 10 / 11 (x64) · macOS Apple Silicon · 4 GB RAM minimum · v0.2.0
View v0.2.0 release & installation details