你学会了通过倾听说话
也一样
我们相信声音是最自然的与智能互动的方式，所以我们创造了德萨，这是有史以来最真实的全复式语音模型。 说话感觉就像和一个人说话。.. 充满情感，细微，暂停，和自然的粗鲁。
与当前语音AI的交互可以完全吸。 将你的声音变成文字，世界上最强大的AI无法听到你的感受。 我们认为这很荒谬
我们从零开始训练德萨除了人类对话声音！没有文字，没有预先训练过的模型。 它学会了仅仅通过倾听来举行实时对话。 据我们所知，Dessa是世界上第一台人工智能
德萨推进了深层学习模型的前沿，并创造了一个完全不同的类别，有着全新的有趣的行为供研究人员发现。 与文本相比，他们学习语言和事实的效率如何？他们如何能够有效地学习新语言？他们能进行什么样的内文学习？
让我听。..
下方的每段片段都是一个跟德萨说话的人的现场录音。 没人能操纵它德萨选什么话，何时说，如何说，下到自己的声音和个性。 之后增加了字幕。
说到释放
它笑的瞬间，有些东西是可笑的，中度的，人们的做法。 其他模特儿等着你完成然后在提示中笑叫它大声点，声音就大了没人教它
记得电影
电影标题上的人物空白。 德萨结句。 考虑到它来自原始声音的每一个事实，它也知道一个惊人的数量。
一个周年惊喜
一个惊喜。 Dessa喘着“我的天”
表达式对话
进化和速度都很大
生活咨询
这里听起来很冷酷
德萨与GPT-Live-1的谈话
在这里它与ChatGPT Live交谈。
在这个演示中，德萨正与GPT-Live-1，第三方AI模型交谈。 两个声音都是AI生成的。 GPT-Live-1的开发者不隶属于Block，也没有审查或认可Dessa.
不久将在X上分享更多录音。
这是什么？
声音进来，声音出来。 德萨是一个真正的语音对语音模型，它知道的一切来自人类的语音。 这很复杂，所以会同时聆听和交谈，就像你一样。 它从真正的对话中汲取了教训，因此它知道何时可以切入，何时可以反通道(“是的！”、“得到的”、“哦”)来展示它与你在一起。 推论比实时快，它在当地运行在MacBook Pro M4 Max或更好。
它原生地听到并说出情感，讽刺，笑声，令人沮丧的叹息，声音与悲伤的裂缝。 将演讲通过文字进行，所有这一切都消失，这就是为什么大多数声音AI感到闷闷，慢，最糟糕的是烦恼。
太疯狂了！
LLMs需要疯狂的文本量。 德萨从数百倍少的词中学习语言(公平而言，LLMs还需要学习C++和地狱角是什么).
并且它必须学习远远超出语言。 Accents)，暂停，呼吸，讽刺，幽默，inflection，情感，何时切入：每一个都改变某人的意思。 说“我没有说她偷了我的CUDA密码”，同一词，每次都不同的意义。
言论永不重复。 说两句，完全一样，数据仍然会出来。 无论谁打字，文本都是相同的。 一个单词的字节比文本中同一个字节要多数千倍。 人们学会说得那么容易，以至于我们忘记了这有多难。 一台没有文字的机器是残酷的。
但是，我们想通了。 我们想出了如何训练德萨在一个NVIDIA GB200 NVL72。
等等，为什么？
有三个原因：好奇心(aka fun)，人类和AI之间更好的理解，以及安全。
婴儿学着说话，却从未看到一个字写下来。 我们想看看模特儿能不能做它会的。 这很困难。
演说是任何智能最自然的界面，也跟不上人类的时机。
AI不断获得权力与独立，想象一下，当一个声音AI不知道并且继续前进时，会感到很痛苦。 这是安全问题。 德萨是朝修复方向迈出的一步。
谁？
我们是Block的一个(非常)小型的AI研究实验室，自2012年以来，我们建立了深层次的学习模式，我们追寻别人忽视的前沿问题
你可以联系我们
呼叫所有的安全研究人员！
一个只从声音中学会说话的模型是新领域，我们希望外界能够关注它。 我们让一小群AI安全研究者能提前找到我们没有预料到的风险。 如果那是你的话
- 拉加万·图赖拉特南，德萨领队
德萨队
- 研究人员
- Louay Hazami, Hashiam Kadhim, Qi (Alex) Liu, Rayhane Mama, Aydin Polat, Marc Tyndel
- 实习生
- 卡拉吉、吉布兰·伊克巴尔·沙阿、德维尔·扎古里-格林鲍姆
- 前实习生
- 亚利安·夏尔马奥利维亚·燕
*按字母顺序排列
更多样本
艺术家德萨
浴室灾难
喜欢闲谈
懒惰的AI游戏
超级游戏
噪音 GPT 现场直播
在这个演示中，德萨正与GPT-Live-1，第三方AI模型交谈。 两个声音都是AI生成的。 GPT-Live-1的开发者不隶属于Block，也没有审查或认可Dessa.
本文由 AI图鉴自动抓取并翻译，版权归原作者所有；如需查看原文请点下方链接。
You learned to talk by listening.
So did
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.
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.
We trained Dessa from scratch on nothing but human conversation. Sounds! No text, no pretrained models. It learned to hold a real-time conversation simply by listening. As far as we know, Dessa is the world’s first AI you can have a realistic live conversation with that was trained only from human speech.
Dessa advances the frontier of deep learning models and creates a different category with entirely new and interesting behaviors for researchers to discover. How efficiently do they learn language and facts compared to text? How efficiently can they learn new languages? What sorts of In-context learning can they perform?
Let me listen…
Every clip below is a live recording of a person talking to Dessa. Nobody steers it. Dessa picks what to say, when to say it and how, down to its own voice and personality. Subtitles were added afterward.
Talking about the release
It laughs the moment something’s funny, mid-sentence, the way people do. Other models wait for you to finish, then laugh on cue. Ask it to speak up and it gets louder. Nobody taught it that.
Remembering a movie
The person blanks on a movie title. Dessa finishes the sentence. It also knows a surprising amount, considering every fact it has come from raw sound.
An anniversary surprise
A surprise. Dessa gasps “oh my god” under its breath, then answers with what sounds like teary gratitude.
Expressive conversation
Huge range in intonation and speed.
Life advice
Here it sounds genuinely empathetic.
Dessa in conversation with GPT-Live-1
And here it talks to ChatGPT Live.
In this demo, Dessa is talking with GPT-Live-1, a third-party AI model. Both voices are AI-generated. The developer of GPT-Live-1 is not affiliated with Block and has not reviewed or endorsed Dessa.
More recordings will be shared on X soon.
What is this?!
Audio in, audio out. Dessa is a true speech-to-speech model, and everything it knows came from human speech. It’s full-duplex, so it listens and talks at the same time, like you do. It learned from real conversation, so it knows when to cut in and when to backchannel (“yeah!”, “got it!”, “ooh”) to show it’s with you. Inference runs faster than real time, so there’s no awkward wait. And it runs locally on a MacBook Pro M4 Max or better.
It natively hears and speaks emotion, sarcasm, laughter, a frustrated sigh, a voice cracking with sadness. Run speech through text and all of that is gone, which is why most voice AI feels stilted, slow and, worst of all, annoying.
This is crazy!
LLMs need an insane amount of text. Dessa learned language from hundreds of times fewer words (in fairness, LLMs also have to learn C++ and whatever the hell Angular is).
And it had to learn far more than language. Accents, pauses, breathing, sarcasm, humor, inflection, emotion, when to cut in: every one changes what someone means. Say “I didn’t say she stole my CUDA code” out loud, stressing a different word each time. Same words, different meaning every time.
Speech never repeats. Say a sentence twice, exactly the same way, and the data still comes out different. Text is identical no matter who types it. And a single spoken word takes thousands of times more bytes than the same word in text. People learn to talk so easily that we forget how hard it is. For a machine with no text to lean on, it’s brutal.
But, we figured it out. And we figured out how to train Dessa on only one NVIDIA GB200 NVL72.
Wait but why?
Three reasons: curiosity (aka fun), better understanding between humans and AI, and safety.
Babies learn to talk without ever seeing a word written down. We wanted to see if a model could too. It can. It’s just very hard.
Speech is the most natural interface to any intelligence, super or otherwise, and today’s voice AI wastes it. It flattens what we say into text and can’t keep up with human timing.
AI keeps gaining power and independence, and it’s still nearly deaf to the emotion in our voices. Imagine being in serious pain while a voice AI has no idea and just keeps going. That’s the safety problem. Dessa is a step toward fixing it.
Dessa who?
We’re a (very) small AI research lab at Block, founded by former members of Dessa, the Toronto deep learning startup. We’ve built deep learning models since 2012 and generative speech models for over eight years. We chase frontier problems others ignore, and we report directly to Jack Dorsey, Block’s cofounder, Chairman and Block Head.
You can reach us here.
Calling all safety researchers!
A model that learned to talk from sound alone is new territory, and we want outside eyes on it. We’re giving a small group of AI safety researchers early access to find the risks we haven’t anticipated. If that’s you, .
— Ragavan Thurairatnam, Dessa lead
Team Dessa
- Researchers
- Louay Hazami, Hashiam Kadhim, Qi (Alex) Liu, Rayhane Mama, Aydin Polat, Marc Tyndel
- Interns
- Cara Ji, Jibran Iqbal Shah, Dvir Zagury-Grynbaum
- Former interns
- Aryan Sharma, Olivia Yan
*in alphabetical order
More samples
Artist Dessa
Bathroom disaster
Hobbies talk
Lazy AI gaming
Marvel gaming
Noisy GPT live
In this demo, Dessa is talking with GPT-Live-1, a third-party AI model. Both voices are AI-generated. The developer of GPT-Live-1 is not affiliated with Block and has not reviewed or endorsed Dessa.
Auto-fetched and translated by AI Atlas. All rights belong to the original author.