Applied Brain Research (ABR) has announced the general availability of its speech AI software development kit (SDK) for Zephyr RTOS on the Alif Semiconductor Ensemble family of edge AI processors. The software enables streaming automatic speech recognition and text-to-speech synthesis to run entirely on-device, without requiring a cloud connection. It is designed for low-power embedded applications, including battery-operated and air-gapped products. The SDK combines two speech technologies. Niagara ASR (automatic speech recognition) provides low-latency, full-vocabulary streaming speech recognition, continuously converting spoken input into text as it is received. Nith TTS (text-to-speech) provides natural-sounding, low-latency streaming speech synthesis. Native support for Zephyr RTOS allows developers to integrate both capabilities into embedded systems while retaining the benefits of a real-time operating system. The platform also supports ongoing model updates and expansion. According to ABR, its state space model technology makes advanced speech processing feasible within the power and memory constraints of microcontroller-class devices. This addresses a key limitation of conventional embedded voice interfaces, which have often relied on cloud-based processing or more powerful application processors. On the Alif Ensemble E8 processor, Niagara ASR achieves an average first-audio-to-first-token latency of 133 ms. The recognition engine consumes just 15 mW of active power above the processor's baseline consumption. These characteristics enable responsive, continuously available voice interfaces while limiting the impact on battery life and system power budgets. Running speech recognition and synthesis locally also removes the need to transmit audio to remote services for processing. This is particularly relevant for applications that require offline operation, reduced dependence on network connectivity, or local handling of voice data. The ABR speech AI SDK for Zephyr RTOS on the Alif Ensemble family is available now. Developers can register for an account and obtain a free evaluation license through ABR's developer portal . ABR and Alif Semiconductor will also demonstrate Niagara ASR running live on the Ensemble E8 at electronica 2026 , November 10-13 at Messe München in Germany. The demonstration will be hosted at the Alif Semiconductor booth, C5.170. The post ABR Launches Speech AI SDK for Alif Processors appeared first on Embedded .