ElevenLabs于周一推出了两款新的语音模型，分别命名为 ElevenLabs v4 和 v4 Turbo。这些新模型提供了更强的表达控制能力、更低的语音交互延迟，并支持超过 90 种语言。
ElevenLabs launched two new speech models on Monday, called ElevenLabs v4 and v4 Turbo, offering more expression control, lower latency for voice agents, and support for more than 90 languages.
该公司去年发布了 v3 版本，并在今年华沙的一场活动中首次展示了 v4 的部分功能。在 v4 版本中，ElevenLabs 采用了全新的架构，使得语音模型的控制更加便捷、克隆速度也更快。该公司表示，用户只需提供 10 秒长的音频文件，即可克隆出一个新的语音模型。
The company released its v3 model last year, and teased the model at an event in Warsaw earlier this year. For the v4 generation of models, ElevenLabs is adopting a new architecture that allows for better control and faster cloning. The company said that with v4, users will be able to clone a voice with just 10 seconds of audio.
在语音表达方面，v4 版本在处理较长文本时能够更准确地还原说话者的身份特征；在朗读文本时，该模型还能根据文本内容调整语音表达方式。ElevenLabs 在 v3 版本中引入了用于定义语音表达的标签系统，并在 v4 中进一步扩展了这一功能，允许用户同时使用多个标签来指导模型的表达行为。
On the creative side, the model handles voice identity better over longer chunks of text. It also keeps the context of the text in mind while reading it aloud to change expressions. ElevenLabs introduced inline tags to define expression with v3, and is expanding those tags in v4, letting users stack multiple tags and having the model follow the sequence.
此前 v3 版本仅支持 70 种语言，而新版本已将这一数字提升至 90 种。该公司指出，日语、巴西葡萄牙语、普通话和粤语的语音质量提升最为显著。
The previous version supported 70 languages, and ElevenLabs has worked to get that number up to 90 languages with the new version. The startup said that it observed the biggest quality jump in Japanese, Brazilian Portuguese, Mandarin and Cantonese.
过去一年中，ElevenLabs 的企业语音服务业务发展迅速，其业务收入的 55% 来自大型企业。新版本的语音模型非常适合用于开发智能语音助手，因为其较低的延迟使得对话更加流畅。此外，当背后的大型语言模型（LLM）开始生成答案时，v4 版本就能立即开始生成相应的语音内容。该模型还能有效处理复杂对话中的冲突和矛盾情况，从而帮助更好地解决问题。
ElevenLabs has scaled its enterprise calling business rapidly over the last year, with more than 55% of its business coming from large companies. The company said that the new model is suited for voice agents, as the new version has lower latency to allow for more fluid conversation. Plus, the v4 can start generating audio as soon as the LLM behind it starts generating answers. What’s more, the model can also handle confrontations, escalations, and holds differently for better issue resolution.
随着 Cartesia、Deepgram、Fish Audio、Boson 和 WellSaid Labs 等初创公司推出更具表现力的语音模型，以及谷歌（Google）和 OpenAI 等大型企业的持续改进，语音模型领域的竞争日益激烈。
Competition in speech models has ramped up as startups like Cartesia, Deepgram, Fish Audio, Boson, and WellSaid Labs have created expressive speech models. Big companies like Google and OpenAI have also improved their voice models.
ElevenLabs今年早些时候从红杉资本筹集了5亿美元，该轮融资由红杉资本领投，公司估值达到110亿美元。目前已有传闻称，公司将进行后续融资，估值将达到220亿美元。ElevenLabs的年化营收运行率已从今年年初的约3.3亿美元攀升至超过6亿美元。该公司在印度、欧洲和巴西等不同市场积极招聘人员，员工总数已超过800人。
ElevenLabs raised $500 million earlier this year from Sequoia earlier this year, in a round led by Sequoia that valued the company at $11 billion. There are already rumors of a followup fundraising round that would value the company at $22 billion. ElevenLabs annualized revenue run rate has climbed from roughly $330 million at the start of the year to over $600 million. The company has aggressively hired personnel in different markets such as India, Europe, and Brazil, as its headcount has reached over 800.
在最近接受TechCrunch采访时，该公司联合创始人兼首席执行官马蒂·斯塔尼谢夫斯基表示，公司目标是在“未来几年内”进行IPO，但并未承诺具体时间表。
In a recent interview with TechCrunch, the company’s co-founder and CEO Mati Staniszewski said that the company is aiming for an IPO “in the next years,” but didn’t commit to a timeline.