Tether releases on-device speech model for smart glasses and robots
Tether says its 254M-parameter TranscribePsy model runs locally on phones, glasses and robots, with benchmark claims and open-source weights.
xAI Launches Grok Speech APIs Undercutting Competitors by 60%
Elon Musk's xAI releases Grok Speech to Text and Text to Speech APIs at $0.10/hour, claiming lowest error rates across enterprise transcription benchmarks.
Meta's Omnilingual ASR to Revolutionize Speech Recognition for 1,600 Languages
Meta introduces Omnilingual ASR, a cutting-edge suite of models enhancing automatic speech recognition for over 1,600 languages, leveraging extensive multilingual datasets.
NVIDIA Launches Granary Dataset to Enhance Multilingual Speech AI
NVIDIA introduces the Granary dataset and models designed to improve speech recognition and translation across 25 European languages, addressing data scarcity in AI language models.
Evaluating Speech Recognition Models: Key Metrics and Approaches
Explore how to evaluate Speech Recognition models effectively, focusing on metrics like Word Error Rate and proper noun accuracy, ensuring reliable and meaningful assessments.
Exploring Python Speech Recognition Solutions in 2025
Discover the latest advancements in Python speech recognition, comparing open-source libraries and cloud-based solutions for efficient implementation in 2025.
Universal-2: Revolutionizing Speech Recognition with Advanced Accuracy
Universal-2 enhances speech-to-text accuracy by addressing real-world demands, focusing on structured data and critical details over traditional Word Error Rate metrics.
NVIDIA NeMo Achieves 10x Speed Boost for ASR Models
NVIDIA NeMo's latest enhancements speed up ASR models by up to 10x, optimizing both performance and cost-efficiency for speech recognition tasks.
Harnessing Universal-1 for Ruby: Advanced Speech Recognition with AssemblyAI
Discover how to integrate AssemblyAI's Universal-1 speech recognition model into Ruby applications for superior accuracy and efficiency.
NVIDIA Introduces NIM Microservices for Enhanced Speech and Translation Capabilities
NVIDIA NIM microservices offer advanced speech and translation features, enabling seamless integration of AI models into applications for a global audience.