ElevenLabs 发布 Scribe v3 Live 语音识别模型

GPT-Image-2,提示词由 THE DECODER 提供
Elevenlabs 发布了 Scribe v3 和 Scribe v3 Live,这是两款专为串音、背景噪声等杂乱音频场景打造的语音识别模型,同时覆盖预录音频文件和实时使用场景。
来自 Artificial Analysis 的基准测试显示,Scribe v3 跻身市面上最准确的转录模型之列,但其运行速度慢于 Microsoft 和 xAI 的竞品模型,成本也更高。
实时版本会分析对话上下文,避免在短暂停顿时打断来电者;ElevenLabs 正在扩大与 Nvidia 和 McKinsey 的企业合作。
Elevenlabs 更新了其语音识别能力,覆盖录音对话与实时使用场景。独立基准测试证实其准确率很高,但也暴露出速度上的不足。
Elevenlabs 发布了两款新的语音转文字模型 Scribe v3 和 Scribe v3 Live,专为会议中人们相互插话、电话带有背景噪声等杂乱场景打造。
Scribe v3 面向预录音频文件,Scribe v3 Live 则针对低延迟实时应用。两款模型现已通过 ElevenAPI 开发者接口和 ElevenAgents 平台开放使用。
据 Elevenlabs 称,在 102 种语言上,Scribe v3 相比前代将词错误率降低了约 25%,公司表示德语准确率有显著提升。公司还称,说话人分离在较大规模的群组对话中也更加可靠,而 Scribe v3 Live 首次实现了实时说话人分离。
Scribe v3 在准确率上领先,但比竞争对手更慢、更贵
Artificial Analysis 的独立基准测试证实,Scribe v3 是市场上最准确的转录模型之一。它小幅领先于 Microsoft、Mistral、xAI、Google 和 OpenAI 的竞品,仅落后于阿里巴巴的一款预览模型。
Scribe v3 是 Artificial Analysis 测试中最准确的模型,但在速度上略显落后。其基准价格为每 1,000 分钟 3.33 美元(图中未显示)。
不过,如果希望快速且低成本地处理大量音频,选择其他厂商会更合适。Elevenlabs 在速度和价格上处于中游。Microsoft 和 xAI 的模型运行速度快数倍,错误率仅略高,成本则大约只有一半。
然而,该基准测试仅衡量录制文件中的词语错误,并未考虑 Elevenlabs 所宣传的说话人分离、罕见语种方面的改进,也不涵盖 Scribe v3 Live 的实时表现。
Scribe v3 Live 旨在让语音智能体不再打断通话者
在语音智能体中,Scribe v3 Live 意在修复当前系统的一个缺陷:这类系统往往依赖僵硬的停顿计时器,当通话者短暂停顿思考或缓慢念出一串数字时,会在句子中间将其打断。这款新的实时模型会将对话上下文与音频信号一并分析,从而判断说话人是否真的已经说完。
Elevenlabs 还让开发者对最终转录文本拥有更多控制权。这些模型可以预载数千个专业术语,例如品牌名称或药物名称,以避免听错特定领域的词汇。开发者可以用自然语言为数字或日期设置格式规则,多语言模式还能处理句中切换语言的情况。企业客户可获得位于欧盟的隔离服务器,以及一种零留存模式,该模式旨在每次请求后立即删除数据。
在推出新模型的同时,Elevenlabs 也在扩展其企业业务。在与 Nvidia 扩大合作的框架下,该公司正将开放的 Nemotron 3.5 Super VL 语言模型集成进 ElevenAgents,锁定运行在 Nvidia 上的额外算力,为机器人开发本地语音控制,并为波兰公共卫生系统运行一个电话智能体。该公司还宣布与咨询公司 McKinsey 结成联盟,推出面向系统集成商的更广泛合作伙伴计划,并上线自己的市场平台,Salesforce、IBM 和 Zendesk 等公司在该平台上提供现成的语音智能体。
没有炒作的 AI 新闻——由人工甄选
译文由英文原文机器翻译,术语按行业惯例统一,可在文末展开原文核对。
查看英文原文(ElevenLabs Scribe v3 Live uses conversational context to stop voice agents from cutting off callers mid-sentence)
GPT-Image-2 prompted by THE DECODER
Elevenlabs has released Scribe v3 and Scribe v3 Live, two speech recognition models built for messy audio situations like crosstalk and background noise, covering both pre-recorded files and real-time use.
Benchmarks from Artificial Analysis put Scribe v3 among the most accurate transcription models on the market, but it runs slower and costs more than rival models from Microsoft and xAI.
The real-time version analyzes conversational context to avoid cutting callers off during brief pauses, and ElevenLabs is expanding enterprise partnerships with Nvidia and McKinsey.
Elevenlabs updates its speech recognition for recorded conversations and real-time use. Independent benchmarks confirm high accuracy but also show drawbacks in speed.
Elevenlabs has released two new speech-to-text models, Scribe v3 and Scribe v3 Live, built for messy conditions such as people talking over each other in meetings or phone calls with background noise.
Scribe v3 is designed for pre-recorded audio files, while Scribe v3 Live targets low-latency real-time applications. Both models are available now through the ElevenAPI developer interface and the ElevenAgents platform.
According to Elevenlabs, Scribe v3 cuts word errors by about 25 percent compared to its predecessor across 102 languages, and the company says German accuracy improves significantly. Speaker diarization also works more reliably in larger group conversations, according to the company, and Scribe v3 Live makes it available in real time for the first time.
Scribe v3 leads on accuracy but is slower and pricier than rivals
Independent benchmarks from Artificial Analysis confirm that Scribe v3 is among the most accurate transcription models on the market. It edges out competitors from Microsoft, Mistral, xAI, Google, and OpenAI, trailing only a preview model from Alibaba.
Scribe v3 is the most accurate model in the Artificial Analysis test but lags somewhat in speed. Its benchmark price is $3.33 per 1,000 minutes (not shown).
Anyone looking to process large volumes of audio quickly and cheaply is better off with other providers, though. Elevenlabs lands mid-pack on speed and price. Models from Microsoft and xAI run many times faster at marginally higher error rates and cost roughly half as much.
However, the benchmark measures only word errors on recorded files. It doesn't account for the improvements Elevenlabs touts in speaker diarization, rare languages, or the real-time behavior of Scribe v3 Live.
Scribe v3 Live aims to keep voice agents from cutting off callers
In voice agents, Scribe v3 Live is meant to fix a flaw in current systems, which often rely on rigid pause timers and cut callers off mid-sentence when they stop briefly to think or slowly read out a string of numbers. The new real-time model analyzes conversational context alongside the audio signal so it can tell when a speaker has actually finished.
Elevenlabs also gives developers more control over the final transcript. The models can be preloaded with thousands of specialized terms like brand names or medications to avoid mishearing domain-specific vocabulary. Developers can set formatting rules for numbers or dates in natural language, and a multilingual mode handles language switches mid-sentence. Enterprise customers get isolated servers in the EU and a zero-retention mode designed to delete data immediately after each request.
Elevenlabs is also expanding its enterprise business alongside the new models. Under an expanded partnership with Nvidia, the company is integrating the open Nemotron 3.5 Super VL language model into ElevenAgents, securing additional compute capacity running on Nvidia, developing local voice control for robots, and running a phone agent for Poland's public health system. The company also announced an alliance with consulting firm McKinsey, a broader partner program for system integrators, and its own marketplace where companies like Salesforce, IBM, and Zendesk offer ready-made voice agents.
AI News Without the Hype – Curated by Humans
原文为英文,正文由自动抓取并保留原文。
原文发布于 The Decoder(ElevenLabs Scribe v3 Live uses conversational context to stop voice agents from cutting off callers mid-sentence),标题、摘要与正文由机器翻译,术语按行业惯例统一,未经人工逐句校订。