杰克·多西（Jack Dorsey）旗下的 Block 公司从其研究实验室发布了一款新的语音模型，该模型可在本地运行，其表现出的笑声、停顿和哭声等表达听起来异常真实。公司表示，这款名为 Dessa 的模型完全基于人类语音训练，且仅使用单张 NVIDIA GPU。
Jack Dorsey’s Block released a new voice model out of the company’s research lab that runs locally and sounds strangely human with its expressions like laughs, pauses, and cries. The company said the model, called Dessa, is trained fully on human speech and a single NVIDIA GPU.
Dessa 是一款全双工模型，意味着它能像 OpenAI 今年早些时候发布的 GPT-Live 模型一样，同时进行说话和聆听。通常，语音模型会与大语言模型配对以实现知识检索。Block 称，Dessa 的知识源自其所拥有的对话数据。
Dessa is a full-duplex model, which means it can talk and listen at the same time, just like the GPT-Live model OpenAI released earlier this year . Typically, speech models are paired with a large language model for knowledge retrieval. Block said that Dessa’s knowledge stems from the conversational data it has.
“我们认为语音是与智能交互最自然的方式，因此我们创建了 Dessa，这是有史以来最真实的全双工语音模型。与它交谈感觉就像与真人交谈……充满情感、细微差别、停顿和自然的语调节奏。” jack (@jack) 2026 年 10 月 23 日Block 表示，当前的模型听起来可能不自然且令人恼火，因为其流程中包含驱动语音生成的文本环节。
We believe voice is the most natural way to interact with intelligence, so we created Dessa, the most authentic full-duplex speech model ever built. Talking with it feels like talking with a person…full of emotion, nuance, pauses, and a natural cadence. — jack (@jack) October 23, 2026 Block said that the current models can sound unnatural and annoying because they have text in the pipeline that drives speech generation.
许多模型（如 ElevenLabs v4 或 Fish Audio Drama 3）使用语音标签来驱动语音生成中的情感。多西的公司声称，情感已内置于其模型中。目前尚不清楚该情感是否由某种标签进行引导。
A lot of models like ElevenLabs v4 or Fish Audio Drama 3 use voice tags to drive emotion in speech generation. Dorsey’s company claims that emotion is built into its model. It’s not clear if that emotion is being steered by some kind of tags.
“与当前的语音 AI 互动简直糟糕透顶。它将你的声音转为文本，并丢弃了文本无法承载的海量信息。世界上最强大的 AI 都听不出你的感受。我们认为这很荒谬，会导致更差的体验，且潜在危险，”公司在一篇博客文章中表示。
“Interacting with current voice AI can just plain suck. It turns your voice into text and throws away an incredible amount of information text alone can’t carry. The most powerful AIs in the world can’t hear how you feel. We think that’s ridiculous, leads to a worse experience, and is potentially dangerous,” the company said in a blog post .
公司研究人员发布了多个与 Dessa 对话的示例，其中智能体展现了不同的声音、语速和情感。例如，在对话中，机器人说它下班累了，此时它听起来确实很疲惫。
The company’s researchers posted multiple examples of conversations with Dessa where the agent had different voices, cadences, and emotions. For instance, in the conversation, the bot said it was tired from work, and at that point it sounded tired.
我们训练出了首个完全基于语音训练、能与你进行真实对话的 AI 模型！
We made the first AI model you can have a realistic conversation with that was trained entirely on speech!
Dessa 是一款全双工语音到语音模型，可在消费级 GPU 上运行。这是语音领域的“GPT-3 时刻”。pic.twitter.com/XVD8sSyJn8— Ragavan Thurairatnam (@RagavanThurair) 2026年10月23日在下面的示例中，机器人谈论的是让制作它的人感到舒服，听起来很有情感，甚至差点崩溃。Dessa=全双工语音模型 vs Human=我， pic.twitter.com/zlZfxH2BA5— Aydin Polat (@AydinPolatDessa) 2026年10月23日另一个示例展示了一位 Block 团队成员与语音助手玩游戏。为热爱而玩。
Dessa is a full-duplex speech-to-speech model that you can run on consumer GPUs. This is a GPT3 moment for speech. pic.twitter.com/XVD8sSyJn8 — Ragavan Thurairatnam (@RagavanThurair) October 23, 2026 In the example below, the bot was talking about the person making it comfortable while sounding emotional and almost breaking down. Dessa=full-duplex speech model vs Human=me, pic.twitter.com/zlZfxH2BA5 — Aydin Polat (@AydinPolatDessa) October 23, 2026 Another one shows a Block team member playing a game with the voice assistant. For the love of the game.
看 Cara 与 Dessa 玩猜谜游戏。模型第一个马上猜对，第二个也没花多长时间。 pic.twitter.com/I9f8saduEA— Block (@blocks) 2026年10月23日该公司表示，该模型可在消费级电脑（如 MacBook M4 Max 或更高配置）上本地运行。不过，Dessa 目前尚未向公众开放，Block 已发出呼吁，邀请安全研究人员测试该模型。这很可能是为了测试语音代理可能欺骗通话另一端人员的情况。
Watch Cara play a guessing game with Dessa. The model guesses the first one right straight away, and the second doesn’t take long either. pic.twitter.com/I9f8saduEA — Block (@blocks) October 23, 2026 The company said that the model can run locally on a consumer-grade computer such as a MacBook M4 Max or better. However, there is no public access to Dessa at the moment, and Block has put out a call for safety researchers to test the model. This is likely to test out cases where a voice agent could trick people on the other end.
Block 从事金融业务，向小企业销售解决方案。Square 已使用语音 AI 处理点单。但有了可在设备端运行的自有语音模型，它能以更低成本支持更多商业和消费者体验。
Block is in the business of finance and selling its solutions to small businesses. Square already uses voice AI to handle ordering . But with its own voice model that can run on-device, it can power a lot more business and consumer experiences at a lower cost.