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

Microsoft has launched VibeVoice, a new open-source AI model capable of generating up to 90 minutes of multi-speaker audio ...

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

At the Aircraft Interiors Expo (AIX) 2025 in Hamburg, Germany, Boeing demonstrated a speech-to-text transcription (STT) ...

In contrast, IndexTTS-2.0 introduces a mechanism for precise duration control, achieving efficient duration management for the first time within an autoregressive framework. This innovation makes the ...

One of the reasons to buy smart home appliances, such as those from the Samsung Bespoke line, are for the little improvements ...

As generative AI models move from massive cloud servers to phones and cars, they’re stripped down to save power. But what ...

Two hundred and fifty years after Americans declared independence from Britain and began writing the first state constitutions, it’s not the Constitution that’s dead. It’s the idea of amending it.

As generative AI models move from massive cloud servers to phones and cars, they're stripped down to save power. But what ...

Artificial Intelligence - Catch up on select AI news and developments from the past week or so. Stay in the know.

SAN FRANCISCO, Sept. 09, 2025 (GLOBE NEWSWIRE) -- Today, MLCommons ® announced new results for its industry-standard MLPerf ® ...

Thinking about making your home a bit smarter without getting locked into expensive subscriptions? You’ve probably heard ...