OpenAI has introduced a public beta of the Realtime API, an API that allows paid developers to build low-latency, multi-modal experiences including text and speech in apps.. Introduced October 1 ...

aiOla, a leader in speech recognition technology, has announced today the release of its new open-source AI model, Whisper-Medusa. The new model, based on a multi-head attention architecture ...

To develop Whisper-Medusa speech recognition model, aiOla modified Whisper’s architecture to add a multi-head attention mechanism. Skip to main content. Events Video Special Issues Jobs ...

Gladia, an AI transcription and audio intelligence provider, launched Solaria, a next-gen automatic speech recognition (ASR) model designed to redefine real-time communications for call centers ...

TEL AVIV, Israel, March 31, 2025 /PRNewswire/ -- aiOla, a leading conversational AI lab, today announced the launch of Jargonic, its enterprise-grade speech recognition model that outperforms all ...

CNTXT AI has also released a detailed research paper, outlining the model’s architecture, training methodology and evaluation results. “Munsit is more than just a breakthrough in speech recognition — ...