Speaks Your Language, No Internet Needed: VoxNexus Brings On-Device Voice Artificial Intelligence (AI) in 100+ Languages to Affordable Android Devices

VoxNexus’ new on-device audio intelligence solution understands, translates and speaks Swahili, Hausa, Yorùbá and dozens of other languages without internet access or mobile data

VoxNexus released VoxEdge, an on-device voice stack that brings speech recognition, translation and speech synthesis to affordable Android devices, entirely offline. VoxEdge supports speech recognition in 36 languages, translation in 103 languages, and speech synthesis in 45 languages—all running with no connection, no data bundle, and no cloud token bills.

AI should work for everyone, not just for speakers of a handful of mainstream languages. Yet across much of Africa, voice AI has been held back by scarce training data and the lack of targeted fine-tuning. Everyday speech also includes code-switching and dialect variation, while cloud-based inference costs can make deployment at scale expensive.

VoxNexus’s solutions run entirely on device, and every query is free once the model is installed on the device. Its speech recognition model has as few as 65 million parameters and achieves a lower word error rate than open-source models nearly ten times its size.

“Under-resource languages aren’t small languages. Hundreds of millions of people speak them. Until now, AI models just haven’t learned them yet,” said Charles Shi, CEO of VoxNexus.

VoxNexus also launched VoxSense, an on-device ambient listening solution that uses only 162 mAh for 12 hours of continuous listening, around 2.5% of a 6,500 mAh phone battery. By keeping all processing on device, VoxSense makes always-on listening practical without draining the battery and without sending any audio to the cloud. Developers and device makers can easily integrate it through a license and a simple SDK. Developers can request a free trial here: www.VoxNexus.ai.