{"id":893342,"date":"2026-10-24T19:16:11","date_gmt":"2026-10-24T19:16:11","guid":{"rendered":"https:\/\/www.newsbeep.com\/us\/893342\/"},"modified":"2026-10-24T19:16:11","modified_gmt":"2026-10-24T19:16:11","slug":"blocks-new-voice-model-sounds-eerily-human","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/us\/893342\/","title":{"rendered":"Block’s new voice model sounds eerily human"},"content":{"rendered":"

Jack Dorsey\u2019s Block released<\/a> a new voice model out of the company\u2019s 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 rack. <\/p>\n

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<\/a>. Typically, speech models are paired with a large language model for knowledge retrieval. Block said that Dessa\u2019s knowledge stems from the conversational data it has. <\/p>\n

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\u2026full of emotion, nuance, pauses, and a natural cadence. https:\/\/t.co\/r0qFLdvd6c<\/a><\/p>\n

\u2014 jack (@jack) October 23, 2026<\/a><\/p>\n

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<\/a> or Fish Audio Drama 3 <\/a>use voice tags to drive emotion in speech generation. Dorsey\u2019s company claims that emotion is built into its model. It\u2019s not clear if that emotion is being steered by some kind of tags. <\/p>\n

\u201cInteracting 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\u2019t carry. The most powerful AIs in the world can\u2019t hear how you feel. We think that\u2019s ridiculous, leads to a worse experience, and is potentially dangerous,\u201d the company said in a blog post<\/a>. <\/p>\n

The company\u2019s 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. <\/p>\n

We made the first AI model you can have a realistic conversation with that was trained entirely on speech!<\/p>\n

Dessa is a full-duplex speech-to-speech model that you can run on consumer GPUs.<\/p>\n

This is a GPT3 moment for speech. pic.twitter.com\/XVD8sSyJn8<\/a><\/p>\n

\u2014 Ragavan Thurairatnam (@RagavanThurair) October 23, 2026<\/a><\/p>\n

In the example below, the bot was talking about the person making it comfortable while sounding emotional and almost breaking down. <\/p>\n

Another one shows a Block team member playing a game with the voice assistant. <\/p>\n

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. <\/p>\n

Block is in the business of finance and selling its solutions to small businesses. Square already uses voice AI to handle ordering<\/a>. 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. <\/p>\n

When you purchase through links in our articles, we may earn a small commission<\/a>. This doesn\u2019t affect our editorial independence.<\/p>\n