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

Roughly two weeks ago, Google Docs gained a key feature that should make absorbing swaths of information an easier task. The ...

VibeVoice is a new open-source AI tool that can generate a full 90 minute audio podcast recording with multiple speakers from ...

The president wants to prosecute protesters who desecrate the American flag, but his order concedes that such protests are typically covered by the First Amendment.

To most people, chatbots such as ChatGPT and Google’s Gemini are best known for answering questions, summarising verbose emails and allowing lazy students to cheat on homework. Useful, though more of ...

A new brain prosthesis can read out inner thoughts in real time, helping people with ALS and brain stem stroke communicate fast and comfortably ...

Text-to-speech models from ElevenLabs, Hume AI, and Descript are all pushing the limits of AI-generated voice technology.

Roblox has been dabbling in many new features to make things better for their players, and that includes those who don't like to talk.

Use the Speech framework to recognize spoken words in recorded or live audio. The keyboard’s dictation support uses speech recognition to translate audio content into text.

Google is enhancing Gemini's text-to-speech (TTS). On Tuesday at Google I/O 2025, the company previewed a new TTS feature, built on native audio output, that can "converse in more expressive ways ...

AI Is Deciphering Animal Speech. Should We Try to Talk Back? As scientists use machine learning to decode the sounds of whales, dogs, and dolphins, opinions vary on how best to deploy the technology.

With a focus on expressive quality, reproducibility, and open access, Dia adds a distinctive new voice to the landscape of text-to-speech.