Sir Patrick Stewart, in a forthcoming audiobook, reads all of William Shakespeare's 154 sonnets and provides his personal reflections of the works.

The best audio processing library built on Apple's MLX framework, providing fast and efficient text-to-speech (TTS), speech-to-text (STT), and speech-to-speech (STS) on Apple Silicon. Kokoro Fast, ...

The app reads your email inbox and your meeting calendar, then gives you a short audio summary. It can help you spend less ...

Abstract: Neural network-based speech recognition models are widely used in various acoustic systems and have achieved significant success. However, they are vulnerable to adversarial attacks. Current ...

Popular radio show host David Greene has sued Google, alleging the tech giant of ‘stealing’ his voice for its NotebookLM tool, which uses AI to create on-demand podcasts. The lawsuit, filed in Santa ...

Abstract: Despite breakthroughs in audio generation models, their capabilities are often confined to domain-specific conditions such as speech transcriptions and audio captions. In a real-world ...