Speaking is fast. Writing is slow.
An inventory: 8 hours. Or just 2.
Photograph your stock, a property, a job site — and describe out loud instead of typing everything. KontexVoX enriches your photos: it's the tedious part, made fast. Then you turn them into a spreadsheet or a report yourself, with our free prompt library and the AI agent of your choice — we walk you through it, step by step. The time you save pays for the subscription on the very first job.
From inventory to field reports. One app.
For your inventory
List, describe, find. Every item documented by speaking — then a spreadsheet, with our prompts and your AI agent.
For your inspections
Timestamped photos, your voice on site. Enough to back up your version, in one pass.
For your evidence
Timestamped photos, your voice on site. The case builds itself as you speak.
For your videos PRO mode · soon
Review your footage, speak. Your editing instructions, at the right timecode.
How it works
Photograph & describe
In the field, in Capture Mode: you photograph and describe out loud. Your voice is transcribed to text, engraved in the photo.
Export your enriched photos
Each photo carries its context in its EXIF metadata. Nothing in the cloud — it all stays with you.
Your turn — we guide you
KontexVoX stops at the enriched photo. For the deliverable, you use the AI agent of your choice (Claude, ChatGPT…) with our free prompts and the blog that explains everything: it produces your spreadsheet, your report, your field record. That's where the hours are saved.
And also
For your memories
The same gesture serves memory. Speak over your family photos: the anecdote, the names, what was said — engraved in the photo. To reread in ten years, when the image alone is no longer enough to remember.
Your data stays with you.
KontexVoX stores nothing in the cloud. The context lives in the photo file itself, in the EXIF metadata. 100% on-device transcription on your iPhone.
- No cloud on our side
- The app sends nothing to our servers. Everything happens locally on your phone.
- On-device transcription
- Speech recognition runs on your iPhone. We compared local and online: equivalent quality. See the test →
- EXIF = source of truth
- The transcription is written into each photo's metadata. Inseparable. Searchable in the Photos app.
The story
I didn't set out to build a photo app. I just externalized the way I work — and that's how KontexVoX was born. The real story, no shortcuts.