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

Most people will experience an occasional sore throat related to a cold or after a loud event, but for millions of people ...

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

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

Ever-rising tourism-related visitation and economic numbers and continued widespread recognition more and more underscore the ...

Cohere has released Transcribe, a 2-billion-parameter open-source speech recognition model that tops the Hugging Face Open ...

The Industry Asked. We Delivered. The Recognition Followed. Customers demand better ways to deploy voice AI in production. Cloudonix’s infrastructure makes it happen – fast, simple and economical, ...

Oura Health Oy is buying a gesture-recognition startup, setting up the company to eventually add such controls to its popular line of smart rings. Oura said it is acquiring Helsinki-based Doublepoint ...

A former NPR radio host has sued Google and its parent company Alphabet, alleging that the tech giant used his voice for its NotebookLM AI product. David Greene, former host of NPR's Morning Edition ...