Microsoft’s VibeVoice is an open-source text-to-speech model for podcast-length, multi-speaker audio that captures the ...

Stanford and UC Santa Cruz launch a benchmark for audio-language models; Gemini 2.5 Pro leads, ASR-plus-LLM pipelines stay ...

Google’s Gemini AI has become smarter with its latest update, it can now analyse audio files in addition to text, images, and ...