Alibaba’s Qwen Audio 3.0 TTS Tops the Speech Leaderboard
Alibaba released Qwen Audio 3.0 TTS, a speech model that ranks first on an independent text-to-speech leaderboard, clones voices across 16 languages and costs a third of ElevenLabs.
Explore AIstify's latest reporting, research, and expert analysis tagged with "ai voice cloning", collected in one continuously updated archive.
Alibaba released Qwen Audio 3.0 TTS, a speech model that ranks first on an independent text-to-speech leaderboard, clones voices across 16 languages and costs a third of ElevenLabs.
ElevenLabs has introduced Dubbing v2, a new AI dubbing model that preserves a speaker’s tone, pacing, and emotional delivery across more than 90 languages.
NPR host David Greene alleges that Google’s NotebookLM AI uses a male podcast voice modeled on him, prompting a lawsuit against the company.
Tavus launches its improved AI Santa with face recognition, memory, and autonomous actions — sparking debate over kids’ interactions with AI.