Termsslug: voice-cloning

Voice Cloning

声音克隆

Speech synthesis technique that replicates a speaker's timbre from limited recordings.

Curated Intelligence

11 items · Page 1/2
AWS Machine Learning BlogT1·Tools
62 pts
Amazon Polly Launches Gated Voice Cloning in Seven Languages

Amazon Polly voice cloning is now generally available as a gated release. Customers supply a few minutes of consented speaker audio to generate a custom cloned voice running on Polly's generative engine, initially covering English, Spanish, German, French, Italian, Portuguese and Hindi. Cloned voices are automatically encrypted and access-controlled to the creator, and the feature is available in all AWS Regions supported by the generative engine, including GovCloud.

IT之家 · 智能时代T2·Industry
58 pts
Three Charged With Using AI Deepfakes to Defraud Firms of Over $100 Million

The U.S. Department of Justice has charged three men with using AI-generated voice and video impersonations of corporate executives and law-firm attorneys to trick employees at companies worldwide into wiring more than $129 million between 2024 and 2026. Proceeds were converted into cryptocurrency to obscure their origin; the suspects were arrested in Spain and the UK and face wire fraud, money-laundering conspiracy and aggravated identity theft charges.

IT之家 · IT业界T2·Industry
58 pts
China's Cyberspace Regulator Cracks Down on AI Impersonation of Public Figures

China's cyberspace administration carried out a concentrated crackdown on AI-powered impersonation of public figures, removing over 47,000 illegal items and handling 3,961 accounts, targeting fake endorsements, synthesized celebrity audio/video, fabricated rumors and vulgar content. The action is part of the 2026 'Qinglang' special governance campaign, with regulators vowing to hold platforms accountable and intensify enforcement.

IT之家 · 智能时代T2·Models
85 pts
Tencent Open-Sources Hy-SimulMT: 3s Latency Beats Human Interpreters

Tencent has open-sourced Hy-SimulMT, a simultaneous interpretation LLM supporting real-time Chinese-English speech-to-speech translation with voice cloning. With a latency of ~3 seconds, it outperforms the average human interpreter and matches or exceeds expert-level translation quality. The model is now available for free via the Tencent Hy Translation app.

Artificial Analysis (@ArtificialAnlys)T1·Models
78 pts
Ant Group Open-Sources Ming-3.0-tts, Tops Voice TTS Leaderboards

Ant Group released the open-weight text-to-speech model Ming-3.0-tts, ranking #1 among open models in Artificial Analysis's Controlled Voice and Pronunciation Robustness leaderboards. Available under MIT license, it offers a 0.5B dense variant and a 7.9B MoE version with stateless voice cloning capabilities.

IT之家 · IT业界T2·Industry
32 pts
IT Morning Brief: China Warns of AI Voice Cloning Scams; Apple's HomeView Hub Leaked

Today's tech news highlights AI security and consumer electronics. China's Ministry of State Security warned that criminals use brief voice samples for AI voice cloning scams, advising silence on unknown calls. Meanwhile, leaks reveal Apple's first smart home hub, named HomeView, featuring an A18 chip and AI Siri integration. Other reports include the approval of NearLink national standards and a widespread malware infection by 'JianPian Player'.

IT之家 · 智能时代T2·Industry
68 pts
Sony Music Demands Removal of 260k AI-Generated Songs

Sony Music has issued takedown notices to digital platforms demanding the removal of over 260,000 AI-generated tracks impersonating its artists, including Adele. This volume nearly doubled from March levels, highlighting the escalating challenge of AI voice cloning and the industry's intensified enforcement efforts.

Qwen 官方博客 (通义)T1·Models
78 pts
Qwen3.5-LiveTranslate Launches with 60-Language Support and Voice Cloning

The Qwen team released Qwen3.5-LiveTranslate-Flash, a multimodal simultaneous interpretation model built on Qwen3.5-Omni. It expands language coverage to 60 languages (with voice output for 29), achieves an end-to-end latency of 2.8 seconds per word via new 'Readable Unit' streaming technology, and introduces real-time voice cloning and hotword enhancement for improved accuracy in professional scenarios.

Qwen 官方博客 (通义)T1·Models
86 pts
Qwen Open-Sources Qwen3-TTS with Voice Cloning and Real-Time Streaming

Alibaba's Tongyi Qianwen team has open-sourced the Qwen3-TTS series, featuring 1.7B and 0.6B parameter models. Built on a novel 12Hz multi-codebook speech tokenizer and dual-track modeling, it achieves ultra-low latency streaming generation (first packet after one character) along with high-fidelity voice cloning, design, and control across 10 major languages. Code, weights, and demos are now available on GitHub and Hugging Face, with an API option for immediate testing.