Hume AI, a startup focused on emotional intelligent voice interfaces, has recently launched an experimental feature called 'Voice Control.' This new tool is designed to help developers and users create personalized AI voices without any coding, AI prompt engineering, or sound design skills. Users can easily customize voices to meet their needs by precisely adjusting voice characteristics. This new feature builds on the company's previously launched 'Empathetic Voice Interface 2' (EVI2), which enhances the naturalness of speech.

ElevenLabs is a startup focused on AI voice cloning and text-to-speech APIs, recently announcing a new feature that allows users to build complete conversational AI agents. Users can now customize various parameters of the conversational agent, such as voice tone and response length, according to their needs on ElevenLabs' developer platform. Previously, ElevenLabs mainly offered various voice and text-to-speech services. The company's growth director, Sam Sklar, stated that...

According to AI media outlet 'Digital Life Kazek', WeChat Official Accounts have quietly rolled out a new feature - AI Voice Cloning, aimed at enhancing users' reading experience. This update is reflected in version 2.29.1 of the official accounts, allowing users to read articles in their own voice, greatly enhancing content personalization. Users can find the 'Reading Voice' option in the backend settings to create their own unique voice. The process of creating a voice is relatively simple; users just need to read a piece of text on the spot, and the system will quickly perform voice cloning.

Recently, Oute AI released a novel text-to-speech synthesis method called OuteTTS-0.1-350M. This method utilizes pure language modeling without the need for external adapters or complex architectures, offering a simplified TTS approach. OuteTTS-0.1-350M is based on the LLaMa architecture, using WavTokenizer to directly generate audio tokens, making the process more efficient. The model features zero-shot voice cloning capability, requiring only a few seconds of reference audio.

Recently, a shocking case of AI voice cloning fraud has drawn widespread attention, highlighting the significant risks associated with this technology. Jay Shuster, a well-known consumer protection lawyer, nearly fell victim to this high-tech scam when the fraudster used AI to imitate Jay's voice, claiming he had been arrested for drunk driving and urgently needed $30,000 in 'bail money.' Astonishingly, the scammer was able to create a convincing voice clone using just 15 seconds of TV interview audio. Despite Jay having previously warned his family to be cautious of such scams, they still...

In today's rapidly advancing world of artificial intelligence, voice synthesis and transformation technologies are evolving at an extraordinary pace, providing us with incredibly realistic and natural audio experiences. However, these technological advancements also bring potential security risks, particularly as 'voice cloning' technology could be exploited by malicious individuals, threatening personal privacy and social stability. In response to this challenge, the Intelligent System Security Laboratory of Zhejiang University and Tsinghua University have joined forces to launch a revolutionary audio forgery detection framework - SafeEar. This framework not only efficiently detects forged audio but also ensures privacy protection during the detection process.

In today's rapidly advancing technology, speech synthesis technology is also progressing, especially in the field of restoring lost voices. Recently, Google researchers introduced a new technology called 'Zero-shot Voice Transfer' which can be directly integrated with state-of-the-art Text-to-Speech (TTS) systems to help those who have lost their voices due to illness or accidents regain their 'voice memory'. The core of this technology is its 'zero-shot' capability, meaning that we do not need a large number of samples to achieve this.

Amazon has launched the AI Cloning Narrator project aimed at accelerating audiobook production. The project invites narrators to submit recordings to train AI for 'voice cloning'. Narrators can choose to participate in the project voluntarily, including live performances or AI-generated recordings. Audiobooks using AI cloning will be labeled on the product detail page, and narrators will be compensated through a royalty-sharing model, requiring narrator consent for AI cloning use. After beta testing in the U.S., this feature will expand to rights holders, aiming to provide narrators with more creative opportunities and enhance the audiobook market.

D-ID has recently launched AI Video Translate, an innovative AI video translation tool that can translate video content into multiple languages, clone the speaker's voice, and adjust lip movements to ensure that the translated content perfectly matches the visuals. This tool supports batch rendering in 29 languages and features a user-friendly interface, making it easy for anyone to use. Through this technology, D-ID helps clients promote marketing, entertainment, and social media activities globally, saving on localization costs. The launch of this technology is significant for small creators.

The actors' union SAG-AFTRA has signed an agreement with AI cloning startup Narrativ, allowing actors to legally license their voices for AI-generated audio advertisements. The agreement ensures that actors have the right to understand and reject brand proposals, set prices, and negotiate for fair compensation. SAG-AFTRA's benefit plans will receive a share of the advertising revenue, though the specific percentage has not been disclosed. This agreement aims to address the widespread dissemination of AI-cloned voices without authorization, following ongoing concerns within the AI industry.

微软近期发布了一款零样本文本到语音（TTS）模型VALLE-2，该成果在技术界引发热议，被认为是TTS领域的里程碑。VALLE-2的创新之处在于其零样本学习能力，仅需一小段陌生语音样本，便能模仿声音说任意文本，实现了惊人的即时模仿和编码器分组。它还改进了重复感知采样，提高解码稳定性，并简化了数据需求。在主观评分和客观指标的测试中，VALLE-2超越了前代模型VALLE，几乎达到人类语音水平。然而，强大的语音模仿能力也引发了对Deepfake技术滥用的担忧，特别是关于伦理考量和潜在风险，如模型对非英美口音处理能力及计算效率的改进空间。当前，微软仅将其作为研究项目，并强调了合成语音检测和授权机制的重要性。未来在语音助手、内容创作等领域的应用值得期待，同时需要关注技术的伦理使用与风险防控。更多关于VALLE-2的信息可访问项目页面：Microsoft官网。

Starting from June 20, Baidu Intelligent Cloud's Xiling Digital Human Platform will undergo a major innovative upgrade. This upgrade not only enables the efficient and cost-effective generation of exquisite 2D/3D digital humans but also achieves seamless integration across multiple scenarios such as live streaming, short videos, and dialogue, significantly enhancing user experience. Whether it's for creating corporate IP, designing cultural tourism IP, or developing entertainment IP, the Xiling platform provides one-stop intelligent, convenient, and user-friendly digital human services.

IBM researchers have discovered a relatively simple method for hijacking voice calls using generative AI tools. This finding raises concerns for organizations that rely on phone verification for identity, such as financial institutions. It poses a challenge for chatbots, as low-cost AI tools enable scammers to easily impersonate others’ voices, stealing funds and other sensitive information. Audio hijacking is a new threat, where malicious actors can manipulate large language models using voice cloning during ongoing conversations.

The open-source voice cloning tool OpenVoice, developed in collaboration with MIT, Tsinghua University, and Canadian AI startup MyShell, has garnered attention. OpenVoice employs a simple and efficient method to almost instantly clone a user's voice, significantly reducing computational resource consumption. It boasts powerful features that provide detailed control options, including tone, emotion, rhythm, and pauses, generating personalized voice clones. MyShell's business model plans to offer monthly subscriptions through a web application, along with promotion fees for third-party bot creators and artificial intelligence services.

Microsoft's latest technology, Personal Voice, generates AI voice that perfectly matches the user's voice in one minute. It supports output in 100 languages, including Chinese, Spanish, German, and more. It is widely used in voice assistants, gaming, entertainment, and media. In collaboration with Haier, it brings personalized voices into smart speakers and home appliance products. Prior to launch, it committed to responsible usage, offering limited registration, and adding watermarks to ensure compliance and transparency.

Bilibili UP主 'XiaoChongGe_' released a fan-made video of Genshin Impact, featuring character imitation of Frowning Na, retaining the original voice, with over 1.36 million views. The creator used the VITS speech synthesis model to upload voice text and extract language features, preserving the unique vocal characteristics of the Genshin Impact character. AI voice cloning technology has become widespread, with tools like HeyGen and AI Dubbing lowering the barriers to entry. The upgrade of AI technology has attracted the attention of creators, emphasizing the importance of producing unique works in both content and form. The article discusses the principles of the VITS model and briefly explains speech synthesis.

The Recording Industry Association of America (RIAA) urges the government to add AI voice cloning to the piracy regulation list due to concerns over copyright infringement. Websites like Voicify.AI have been accused of encouraging unauthorized use of celebrity voices for cloning, infringing on copyrights and the right of publicity. AI voice cloning has garnered widespread attention over the past year, sparking debates about copyright status. While AI's impact on the right of publicity raises concerns, legal approaches remain uncertain.