←Back to NewsAI News/AudiomodelAudioOpen SourceOpen-Source VieNeu-TTS v3 Turbo Runs 48 kHz Vietnamese Speech on CPUsA from-scratch Vietnamese TTS model ships 48 kHz speech, 23 preset voices, instant cloning, and 16 concurrent real-time streams on a single RTX 3060.SourceAlphaSignalPublishedOct 3, 2026, 9:29 AMAuthorAlphaSignal NewsroomRead1 min readA from-scratch Vietnamese TTS model ships 48 kHz speech, 23 preset voices, instant cloning, and 16 concurrent real-time streams on a single RTX 3060.Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.Read original report ↗Next readskyutai · newsKyutai Retrains PocketTTS With Simpler Loss, Hitting 0.90% Word Error RateAlphaSignal · modelXenova's Whisper Tiny Brings Free Speech Recognition to Any BrowserAlphaSignal · modelYuE2 Now Generates Full Songs Locally Without Python or PyTorch
