Sensory Releases TrulyNatural Embedded Speech-to-Text 2.0

Sensory, a provider of voice artificial intelligence and speech recognition technology, has launched TrulyNatural Embedded Speech-to-Text (STT) 2.0 with a new software development kit offering smaller models with more accuracy, new language coverage, and enhanced compatibility for Windows platforms.

New features and enhancements include the following:

• Windows compatibility for developers and integrators working on a variety of applications, including consumer electronics, medical, industrial, automotive, enterprise, government and more.
• Enhanced accuracy and speed with advanced acoustic and language models that use transformer-like architectures to deliver improved word error rates (WER) and robustness in noisy environments.
• Flexible deployment options, supporting a wider range of hardware configurations, including GPUs, high-performance multicore CPUs, or accelerators like Arm Neon and Helium technologies.
• Voice assistant capabilities, combining Sensory's wake word technology and domain-specific small language models.
• Support for nearly 40 languages and regional variations, including Afrikaans, Arabic, Belarusian, Bengali, Bulgarian, Catalan, Croatian, Czech, Danish, Dutch, U.S. and U.K. English, Finnish, French, German, Greek, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Mandarin Chinese, Norwegian, Polish, Portuguese, Romanian, Russian, Spanish, Swahili, Swedish, Thai, Turkish, Ukrainian, and Vietnamese.