VOXEDGE
Compact models
Acoustic models sized for wearable memory and power budgets.
SOLUTIONS / SMARTWATCHES
Voice AI,
on the wrist.
Quick notes and reminders from your wrist. The watch records speech; the phone turns it into text.
04 / SMARTWATCHESON-DEVICE
VOICE → TEXTVOXSENSE
01 / SCENARIOS
What people do with it.
01
Capture
Record speech on the wrist with a low-power detector.
02
Note
Dictate quick notes, transcribed on the paired phone.
03
Remind
Turn spoken commitments into timely reminders.
04
Memory
Keep local notes of meetings and conversations.
02 / PRODUCTS INSIDE
Built from VoxNexus products.
VOXSENSE
Low-power capture
Always-on capture on the watch, transcribed on the phone.
The watch records speech and syncs it to the paired phone, where the models run. Footprint and power vary by model and configuration.
03 / INTEGRATION
From the wrist
to experience, via the phone.
The watch runs voice detection, records speech to flash and syncs it to the phone in batches. The models run on the phone.
- YOU BUILD YOUR PRODUCT UNDERSTAND · ASSIST. Not in the SDK.
- VOXNEXUS SDK ON THE PHONE Acoustic front-end and ASR on recorded speech. No cloud round trip.
- YOU BRING THE PHONE The phone that runs the models.
- YOU BRING THE WATCH Microphone, a low-power chip with flash that runs VAD and records, and a wireless link.
Illustrative architecture. Where processing runs is evaluated per device and configuration.
04 / EVALUATE
Bring your device. We bring the models.
Start with the phone’s chip, the wireless link, languages and power budget. Then create an application, download the SDK and validate latency, power and memory on your own hardware.
Developer documentation ↗- Target device
- Smartwatches, with a phone
- Bring
- Phone, wireless link, microphone, low-power chip with flash
- Define
- Languages and scenarios
- Budget
- Power, memory, latency
- Integration model
- SDK + licensing