Block 发布语音模型 Dessa,全双工且可在消费级设备本地运行
Block’s new voice model sounds eerily human
- 1Block 发布语音模型 Dessa,全双工可同时说话与倾听,官方称情绪内建于模型而非靠标签驱动
- 2官方称模型完全基于人类语音在单张 NVIDIA GPU 上训练,能在 MacBook M4 Max 等消费级设备本地运行
- 3Dessa 暂无公开入口,Block 招募安全研究人员测试,以防语音智能体误导对话另一端的人
- 4Square 已用语音 AI 处理点单,TechCrunch 认为自研模型本地运行能以更低成本支撑更多业务与消费场景
语音模型正在从文本中转管线转向语音原生并本地运行,但 Dessa 尚未开放,当前仍处在安全测试阶段。
- 影响:语音客服等场景有望以更低成本获得更自然的情绪表达,本地运行也省去云端通话开销;模型知识来自对话数据而非外接大语言模型,知识面可能受限;无公开入口,商用节奏未定。
- 参考:可考虑把语音客服、电话点单这类高频场景列入候选清单,待模型开放测试后先算出本地部署与现有云端语音方案的成本差异,并让安全团队跟进其研究员招募进展。
- 依据:情绪表达与本地运行等关键说法均为 Block 官方口径,暂无独立验证;演示由其研究人员发布,作者未实测。
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 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.
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. https://t.co/r0qFLdvd6c
— 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. 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.
“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.
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.
We made the first AI model you can have a realistic conversation with that was trained entirely on speech!
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.
Another one shows a Block team member playing a game with the voice assistant.
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 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.
When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.
Ivan covers global consumer tech developments at TechCrunch. He is based out of India and has previously worked at publications including Huffington Post and The Next Web.
You can contact or verify outreach from Ivan by emailing [email protected] or via encrypted message at ivan.42 on Signal.
来源:TechCrunch · AI · techcrunch.com