Introducing "NAMO" Real-Time Speech AI Model: On-Device & Hybrid Cloud

The VideoSDK has launched NAMO-SSLM, a hybrid model that combines on-device and cloud-based speech-to-speech AI agents. This allows for real-time speech capabilities on low-latency devices while leveraging cloud infrastructure for complex tasks, resulting in a 20× cost reduction while maintaining 98% of cloud performance. The engine orchestrates a local-remote workflow, ensuring sensitive data remains on-device by default and delivers enterprise-grade privacy and compliance, meeting the pressing need for robust compliance in highly regulated sectors like BFSI and Healthcare. NAMO-SSLM is open-sourced, offering a lightweight, real-time, multimodal solution that combines speech and vision AI with real-time processing, multilingual capabilities, and CPU-optimized performance.