AI Demos bg mobile
AI Demos bg desktopAI Demos kv desktop scaled

AI Demos

Ultra-Low Power in Action

AI Demos kv mobile

End-to-end demos run on Ambiq evaluation boards, trained and deployed with our ADKs, integrated with front-end sensors, and built using the neuralSPOT SDK. These demos demonstrate that advanced models can operate in real time on battery power—showcasing Apollo’s ultra-low-energy performance.

Highlights

01

End-to-End, On-Device

Trained and deployed with Ambiq ADKs, wired to front-end sensors, and built with neuralSPOT firmware—real-time inference running entirely on the board.

02

Ultra-Low-Power

Advanced models on battery power. Each demo is tuned to showcase Apollo’s minimal latency, small footprint, and ultra-efficient energy use.

03

Open Source on GitHub

All demo code, ADK recipes, and neuralSPOT firmware are open-source—clone, fork, and customize. Contribute, report issues, and reuse in your product workflow.

04

Powerful Dashboards

Tileio brings live charts, interactive tiles, and device controls together—right in your browser. Connect via WebUSB/ WebBLE, tweak parameters, and visualize results in real time—no installs, no drivers.

Available Demos

Speech Enhancing Demo

  • NNSE is Ambiq’s AI speech denoiser, a real-time model that removes background noise (such as hair-dryer noise) from human speech.

PPG Codec Demo

  • Ambiq’s PPG Codec demo is a real-time AI model that compresses PPG data up to 16× while preserving signal quality, enabling longer battery life and continuous monitoring in smartwatches, smart rings, fitness bands, and remote patient devices.

Ready to Build the Next Generation of Edge AI?

See how ultra-low power AI performs in real-world applications—and partner with Ambiq to bring battery-powered intelligence to your products.

Video Library

hqdefault
hqdefault
hqdefault

Frequently Asked Questions (FAQ)

  • Ambiq AI Demos are real-world demonstrations that showcase how advanced AI models can run efficiently on ultra-low-power edge devices using Ambiq’s hardware and software platforms. 

  • The demos cover a variety of applications, including speech enhancement, health monitoring, sensor intelligence, wearable devices, and real-time on-device AI processing. 

  • The AI Demos run on Ambiq evaluation boards powered by the Apollo family of ultra-low-power SoCs and supported by Ambiq development tools and software frameworks. 

  • Each demo shows how AI models can process data directly on-device, enabling real-time insights and decision-making without relying on continuous cloud connectivity. 

  • Yes. Many AI Demos are built using Ambiq’s development ecosystem, including the neuralSPOT SDK and related software resources available to developers. 

  • AI Demos help developers evaluate performance, power efficiency, hardware integration, and deployment strategies before building commercial edge AI products. 

  • Yes. The demos are designed to showcase how AI applications can operate efficiently on battery-powered devices while maintaining low energy consumption and responsive performance. 

  • By providing proven reference implementations and practical examples, AI Demos help developers reduce development time, validate concepts faster, and bring edge AI solutions to market more efficiently. 

Preparing to download