AI Audio News

Adobe Firefly adds Generate Speech, a native text to speech tool that creates voiceovers directly…

NVIDIA NemotronLabs VoiceChat 11B brings streaming speech to speech in a single, full duplex model…

Google’s Lyria 3.5 is arriving across Gemini experiences with longer song generation, better tempo and…

Suno Studio now supports stem export, giving paying users the ability to separate AI generated…

Google adds DeepMind Lyria 3 music generation inside the Gemini app, letting creators produce 30…

Google has added audio uploads to SynthID Detector, making it possible to check whether voice,…

Googles Gemini app now generates 30 second music clips with DeepMinds Lyria 3, using text…

NVIDIA open-released PersonaPlex-7B-v1, a speech-to-speech model designed for real full-duplex conversation that can listen and…