TECH·July 21, 2026Alibaba’s Tongyi Lab Releases Qwen-Audio-3.0-TTS, a Hosted Text-to-Speech Model in Flash and Plus Tiers Across 16 LanguagesMarkTechPost
TECH·May 20, 2026Alibaba Qwen Team Introduces Qwen3.5-LiveTranslate-Flash: Real-Time Multimodal Interpretation Across 60 Languages at 2.8-Second LatencyMarkTechPost
GAMING·May 9, 2026Darkest Dungeon Dev Would Never Use AI to Copy Deceased Narrator’s Iconic VoiceKotaku
TECH·May 6, 2026Closing the ‘Expressivity Gap’: How Mistral’s Voxtral TTS is Redefining Multilingual Voice Cloning with a Hybrid Autoregressive and Flow-Matching ArchitectureMarkTechPost
TECH·May 4, 2026How to use the local AI “Irodori-TTS” that lets you make a voice say any line you want; it’s specialized for Japanese and runs locally, so you can generate as much as you wantGIGAZINE
PAPER·May 4, 2026LASE: Language-Adversarial Speaker Encoding for Indic Cross-Script Identity PreservationHugging Face Papers
