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

The new API features will help enterprises build autonomous, multimodal voice agents with remote tool access, PBX integration, and enhanced context awareness.

In its initial announcement, Google didn't say if and when the feature would make its way to the Google Docs app. Code sleuth AssembleDebug, however, found that support for the Android app is imminent ...

VibeVoice can produce up to 90 minutes of synthetic dialogue with as many as four distinct speakers.

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 ...

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

Google Text-to-speech is part of Android's accessibility suite. It reads text aloud for those who are blind or live with low vision.

Speech recognition technology is evolving rapidly. Automatic Speech Recognition (ASR) engines are no longer just simple tools to turn voice into text. They are now smarter, faster and more accurate ...

AI text-to-speech programs could “unlearn” how to imitate certain people New research shows models can be directly edited to hide selected voices, even when users specifically ask for them.