Photo and voice become one meal.
The video shows the spread of ingredients. VoCal combines what the camera sees with what you say is hidden, mixed in, or customized.
1 / 3
Carrots
Cucumbers
Broccoli
Greens
Protein
+ Rice Underneath
+ Lentils Underneath
VoCal result
Chicken rice bowl
742
kcal
38g
protein
+22g
vs photo
Photo-only logs miss hidden layers. Voice context turns the same image into a meal you can actually trust.
Why VoCal
4-5x faster than the dominant alternative.
Manual logging takes 2-3 minutes. CalAI-style photo logging is about 90 seconds. VoCal captures the meal in roughly 20 seconds, while voice adds the hidden details photos miss.
20s
VoCal log time
4.5x
400-500% speedup
Average meal logging time
Seconds per complete log
Manual entry2-3 min
CalAI~90s
VoCal~20s
7.5x faster than manual
Compared with a 150-second manual midpoint.
More accurate context
Voice captures buried, mixed, off-frame, and customized ingredients.
Why VoCal
Every feature earns its place in the log.
Any food, any description.
Talk like a normal person. VoCal turns messy voice notes into structured food, portions, modifiers, and confidence signals.
Voice note
"Half a Cava bowl, extra chicken, dressing on the side."
BaseRice bowl, 1/2
ProteinChicken +60g
ModifierDressing separate
Restaurant lookup, matched automatically.
Name the place or dish and VoCal can search restaurant foods, compare likely menu items, and anchor the estimate to a real meal.
chipotle chicken bowl, no cheese
Best match
Chicken burrito bowl
640 kcal
44g pro
menu fit
Follow-up questions when it matters.
If the camera and voice still leave ambiguity, VoCal asks one or two targeted questions before locking the log.
VoCal asks
Was the chicken grilled or fried, and did you use all of the sauce?
You answer
Grilled chicken, about half the sauce, and rice underneath.
sauce adjusted
prep method set
91% confidence
A progress tab that shows movement.
Weight, protein consistency, calories, and check-ins sit together so the user sees trend, not just today's log.
Weight trend
181.4 -> 178.9
Body composition, treated as a trend.
Progress photos can estimate body-fat direction over time, while the interface keeps it framed as guidance, not a diagnosis.
scan
Estimate range
17-19%
trend confidence rising
Wearables feed the next step.
Apple Watch, Whoop, Apple Health, and other fitness trackers help VoCal adjust coaching to recovery and output.
Apple WatchLog by voice
WhoopRecovery synced
Health dataSteps + sleep
Three seconds
From plate to proof.
The photo gives VoCal a starting point. Your voice fills in what the lens cannot know, then the app turns both into a cleaner nutrition record.
-
01
Snap the plate
VoCal identifies what is visible on the surface: rice, greens, sauce, drink, package, or restaurant dish.
-
02
Add the missing context
Say what is underneath, mixed in, customized, or from a restaurant so the estimate is not limited to the photo.
-
03
Answer any smart follow-up
If something is uncertain, VoCal asks about the exact thing that changes the estimate: sauce amount, prep method, hidden base, or portion size.
Pricing
Honest, and quietly priced.
VoCal Pro
Most loved$4.99/month
Unlimited history, nutrition coach, progress imaging, wrist app, full export.
Go ProQuestions
The things people ask.
A photo can only see the surface. VoCal uses voice to add hidden ingredients, restaurant details, cooking methods, and rough portions, then reconciles that context with the image.
Yes. Capture works fully offline and syncs when you reconnect. The Apple Watch flow is voice-first, so you can add context mid-walk without your phone.
Audio is transcribed on-device and discarded immediately — only the structured meal is stored. Nothing is sold or used for advertising.
Stop guessing from a flat photo. Start adding context.
Free on iOS and Android. Snap the meal, say what the camera missed, and keep your progress moving.
Scan for beta
TestFlight invite