Open source TTS models Kokoro, Orpheus, and Piper are tested on symbols, abbreviations, and prosody with CER and MOS results.

Mistral launches Voxtral TTS, extending its model family into speech generation and enabling end-to-end voice workflows.

Google just just released Google AI Edge Eloquent, a standalone AI transcription app that has an on-device mode.

Google's AI dictation app can work completely offline, as the app downloads Google's local Gemma-based speech recognition ...

Google's AI Edge Eloquent app uses AI to edit out mid-sentence mistakes to provide you with a polished transcription of your ...

Abstract: This paper introduces a novel deep learning-based system for real-time American Sign Language (ASL) interpretation and translation into speech, aimed at improving communication for ...

Small and fast: only 123M parameters. High-quality voice cloning: state-of-the-art performance in speaker similarity, intelligibility, and naturalness. Multi-lingual: support Chinese and English.

Add Yahoo as a preferred source to see more of our stories on Google. Donald Trump has opened up a new front in his war with the BBC, falsely claiming that the British broadcaster used AI to tamper ...

Google Messages beta (v20260306) is introducing the ability to copy specific parts of a message. Users can now long-press and drag to select text instead of being forced to copy the entire message.

Flash floods are notoriously difficult to predict, but Google might have a novel solution. The company just revealed Groundsource, a prediction tool for flash floods that uses Gemini to source data ...

Google is launching a new chatbot feature called "Ask Maps" inside its popular maps app. The company is tapping its Gemini AI technology to answer complex navigation questions. Google is adding more ...

Abstract: Communication is effortless for hearing individuals when aided by subtitles, but remains a significant challenge for those who are both deaf and mute. While humans naturally convey thoughts ...