Sorry I'm lost. The sample on the homepage sounds absolutely awful. Not one bit of the cadence individually and together, the tonal ranges in responses or the overall structure and feel is comfortable to listen to, it's so far off passing as 'real' that I feel like I must be missing something.
superchicken099 · 2026-10-23 20:30:41 UTC
Sure it definitely had some strange moment but it’s impressive for a small training data set and low compute
kennywinker · 2026-10-23 20:32:04 UTC
That doesn't sound like the same bar as "most authentic full-duplex speech model ever built"
m348e912 · 2026-10-23 23:07:01 UTC
>That doesn't sound like the same bar as "most authentic full-duplex speech model ever built"
It's up there. I think most humans would be convinced they're talking to a human. I assumed you've used other speech models. They are okay, but not as natural and imperfect as Dessa is.
6879346626 · 2026-10-24 01:43:07 UTC
Not really, there are very obvious unnatural pauses that make me want to slap them instead of continuing to talk to them.
Makes me realize how bad being silent really is.
IshKebab · 2026-10-23 20:34:46 UTC
Have you tried the alternatives? This is clearly far far superior in terms of fluidity of conversation.
VulgarExigency · 2026-10-23 20:44:33 UTC
I think it sounds slightly "off" but its cadence certainly sounds way more like a human than other AI voices I've heard.
IshKebab · 2026-10-23 20:33:54 UTC
I'm surprised it took this long! Clearly the next step is joint training on text and audio. The speech realism is very good, but the intelligence is pretty clearly 2024-level.
rafram · 2026-10-23 23:29:41 UTC
Haven’t OpenAI models been trained on text + audio for a year or two now?
opem · 2026-10-23 20:38:23 UTC
crazy, if true!
paxy · 2026-10-23 20:48:49 UTC
These bidi/duplex demos always come off as overly artificial to me. It's cool that the model can speak at the same time as you instead of taking turns, but training it to interrupt as much as possible isn't the way to do it. In the very first example, did anyone here find the laugh after the "winter" answer to be convincing? What was the need for it? Why did the human speaker not get to finish a single sentence or finish a thought before the model took over with a monologue?
switchbak · 2026-10-23 21:17:50 UTC
I'm absolutely going to hate talking to these things as customer service agents, with fake vocal fry and odd amounts of intonation and emotion peppered in.
For sure there's gonna be people falling in love with them though! I find all the anthropomorphization creepy though.
bityard · 2026-10-23 21:39:27 UTC
I've been hearing people talk negatively about vocal fry for ages now with no idea what it meant. But this comment was finally the one that made me go look it up. And today I learned that I speak almost entirely in vocal fry.
KetoManx64 · 2026-10-25 13:41:16 UTC
Time to hit the gym and get the testosterone up
switchbak · 2026-10-26 20:24:12 UTC
I listen to a niche green energy podcast, and the lady has such a creaky voice that I can barely stand it.
I think there's a generational judgement part of it, and some hearing damage that makes it harder to understand their words on the very low/creaky end.
Not to mention, it can cause real problems for your vocal chords. A little bit is entirely natural, and I don't really notice it in most men, but a lot of young(er) women seem to go overboard on it (in my opinion).
bityard · 2026-10-23 21:19:03 UTC
I get irrationally angry when actual people interrupt me while I'm talking, I'll start throwing chairs when AI tech support agents start doing it.
csmoak · 2026-10-24 00:57:23 UTC
Just make sure the agent on the call on your behalf interrupts more.
preuceian · 2026-10-23 22:00:09 UTC
I listened after reading your comment, and in the first half of the example, Dessa sounds drunk to me, or at least tipsy. So weirdly, the laugh made sense to me.
virtualcharles · 2026-10-23 23:22:08 UTC
OpenAI ruined advanced voice mode for me with that. I’m in the middle of a sentence and it goes “uh huh” and it kills my whole train of thought. It does not make me feel like I’m talking to a real person, it makes me feel like I’m talking to a stupid stupid AI that I hate.
fy20 · 2026-10-24 02:05:36 UTC
Maybe it's better with lower latency, but I get really annoyed by this with ChatGPT Voice. I almost always start my chat with "I'm gonna ramble, I'll tell you when it's your turn".
JoshTriplett · 2026-10-24 05:50:48 UTC
Likewise; I feel exhausted after trying it for a short time, because it doesn't give any space.
moonu · 2026-10-23 20:50:26 UTC
Can you instruction-train a duplex model like this? How would that look? I also wonder, if a model trained only on speech can develop world knowledge like this, could you train an image model only on images of text to essentially act as an LLM?
k141 · 2026-10-25 16:54:54 UTC
yeah, there are models for that already, some are interesting, some are not. check out PEXEL and DeepSeek-OCR.
in theory this could cut costs pretty well for long contexts + there no tokenisation layer.
actualwitch · 2026-10-23 20:55:55 UTC
The speech is great, but you can see some cracks even in the first sound bit. near the end he asks the model to speak louder and initially the voice is louder but then goes back to the same level, also losing what she was saying just seconds ago and he has to lead back to the topic.
ttul · 2026-10-23 20:56:24 UTC
These full-duplex models are getting very "Her"-ish lately. gpt-live-1 is fantastic. Dessa, though, seems to be aiming at full human parity. There's a huge market for AI girlfriends that they should be looking into in earnest...
M3L0NM4N · 2026-10-23 21:29:17 UTC
Global population collapse imminent.
computerdork · 2026-10-23 21:49:15 UTC
Agreed:) no one’s gonna mate and continue the our human lineage, haha
awakeasleep · 2026-10-23 21:58:10 UTC
Also with people having fewer ties to the rest of humanity, there will probably be some weird effects on morality
computerdork · 2026-10-23 23:10:42 UTC
Agreed, and probably has already started with the high usage of the internet and YouTube
so-gala-massey · 2026-10-24 05:52:18 UTC
There already are. Look how money creates the Epstein class.
adastra22 · 2026-10-24 02:28:26 UTC
Some will, and they will outcompete.
honeycrispy · 2026-10-24 20:45:32 UTC
People keep laughing this off, but population contraction will cause the labor force to contract, causing resources to contract, causing war in order to steal other country's resources. Better hope the promise of that AI robot workforce pays off.
qingcharles · 2026-10-23 22:18:10 UTC
This is why we never heard from the aliens. Invented AI, retired to their Goonspheres.
taneq · 2026-10-23 23:07:50 UTC
Some say they’re still in there to this day.
m4rtink · 2026-10-24 06:20:56 UTC
What else did you think all the Fallen Empires in Stellaris did ? ;-)
phoronixrly · 2026-10-23 22:20:27 UTC
Please let this come sooner...
bvcp · 2026-10-23 23:25:59 UTC
human advancement is a function of population, instead of focusing on population decline to solve our resource problems we should focus on efficiency and technology. i am not rooting to revert to the dark ages i really struggle with this ideology of reduction that seems extremely popular. we really take for granted the fragility of human existence we exist in a pico second of reality and could and most likely will be snuffed out eventually, having our own species rooting for this outcome seems suicidal.
phoronixrly · 2026-10-23 23:39:48 UTC
oh no, I am long past any delusions that any problems will ever be solved, I just want it all to end
pigpop · 2026-10-24 01:42:52 UTC
So homicidal then.
bvcp · 2026-10-24 22:57:24 UTC
you live in the time of human history that is objectively the safest and most comfortable that any population of humans have ever enjoyed, look inward if that cant make you happy or excited for the future
whoanoway · 2026-10-23 23:44:50 UTC
> suicidal
Would the logical opposite be eternity for all, and bring back the deceased? LLM plays the Joker, happily imprisoned?
dsign · 2026-10-24 11:37:15 UTC
Cheers and well said :-)
I'm a professional cynic and I spread the idea of "population decline to solve our resource problems" every time I have a chance; I even write dystopic science fiction with this theme. I do it not because I think it's the solution (yours is), but to jolt people in a reaction like yours. Let's build a bright future; just in our solar system there's easily enough matter and space for a trillion humans, each enjoying many acres of forest[^1].
Honestly I think that people who want to fuck a clanker not passing their genes on is probably for the best.
tarpitt · 2026-10-24 02:51:57 UTC
so pretty much anyone who isn't amish?
In the future you won't be able to tell.
Drupon · 2026-10-24 06:15:01 UTC
No most of us are keen on developing human relationships and intimacy, but it sounds like you view women as a warm fleshlight so I hope that you and your genetic line wind up as dead ends with dry humping a robot as your greatest life accomplishment. Good job lil fella. Give that Claude session your 3.5 inches of American steel.
tarpitt · 2026-10-24 09:36:05 UTC
What do you think human relationships and intimacy entail and why can't some sort of high-tech robot legitimately emulate that?
>it sounds like you view women as a warm fleshlight
I think most people accept the fact that women and men are sexual objects. If you view me as a mysoginist for believing that, then I think I understand why you might think our society is still patriarchal or something.
In fact, I can't say that most straight men expect something cerebral or spiritual out of their partners. But even if it was the case, you could expect that a hyper-inteligent machine would exceed human capabilities in this regard.
The only types of people who aren't going to be humping robots are members of isolated societies who have a grudge against technology. Hence the amish.
There are an increasing number of loser men and women who have these AI partners. I think we may see a tipping point where "genetic dead ends" comprise the majority of the population.
With this level of sexual competition, who can blame them? If you're not at the apex you can put in the effort to reproduce but then your offspring are just faced by the same problem, one generation removed.
The majority of men born in this generation won't reproduce. For the average man, there is no sense in doing anything but devoting your life to some high-risk/high-reward strategy. I don't even know what that entails these days, but apparently it involves a lot of sports betting.
I'm normally endowed, as are like 90% of men (so I think these types of baseless insults fall flat). But if I wasn't, would you rather I pass on 3.5 inches of american steel to the next generation? Your insult stands regardless and reveals your underlying preference. If I was endowed well enough, I'm sure you would see my point.
It makes no difference personally, as a gay man who is uninterested in exploring robosexuality. I prefer to work my clankers.
katzenq · 2026-10-24 16:37:59 UTC
God, this is bleak and sad to read.
nostrebored · 2026-10-23 22:29:37 UTC
they are, I believe the third clip is dystopian AI girlfriend
a34729t · 2026-10-24 02:53:29 UTC
does it speak Japanese, tho? What exactly is the point of a waifu if you understand it?
63 · 2026-10-23 21:10:32 UTC
Both speakers in the examples sound unnatural. The human doesn't know what to talk about and seems to have little confidence. The robot says things that only mostly make sense and draws on, saying ultimately very little. "How's the winter stuff?" e.g. is not a sentence a person would say. I might say "How are you dealing with the snow?" or "Are you looking forward to winter?," but not "How's the winter stuff?" And there's just so many examples like this. Also, I'm not convinced that this "human-like" conversation with filler words and interruptions and pauses is actually what anyone wants, especially in absence of a face to interpret or a real human being to understand behind it. Even if it worked perfectly, it would feel uncanny and artificial because I know the person isn't real.
Mallory_Ringess · 2026-10-23 21:18:42 UTC
They sound just as unnatural als the annoying actors in the 'Gilmore Girls' series my daughter keeps on watching and re-watching, i.e. stupid valley girl or whatever it is called witless drivel. In that sense this model is tailor-made to create direct script-to-screen voice-overs for pabulum like that.
ricardobeat · 2026-10-23 21:13:49 UTC
> we figured out how to train Dessa on only one NVIDIA GB200 NVL72.
This is the crazy part. It seems pretty smart, and LLMs require 1000x more compute to train. Can this kind of efficiency somehow be achieved with text too?
freeone3000 · 2026-10-23 21:51:12 UTC
Not if you want the same model that debugs your C++ to also be able to sort objects by shape and generate a description of a video and pick out a good birthday gift for your cousin
mortenjorck · 2026-10-23 23:34:45 UTC
"Oh, uh, yeah, pointers and stacks and stuff, uh – lemme spin up Minimax. Just a sec. Ohhh – ok, see where you're casting that float to a double there, uh, line 72..."
bityard · 2026-10-23 21:17:29 UTC
Not bad, but I guess I lack the imagination to envision the use cases for such casual conversation. Other than... I suppose a certain demographic would be lining up to use this as the voice for their AI girlfriend.
Also I seem to be missing where/how they are selling this.
robotresearcher · 2026-10-23 22:50:35 UTC
Video game NPCs that can hold a plausible conversation while getting the plot points in could be amazing.
andoando · 2026-10-24 17:18:09 UTC
Creating better AI media like movies/shorts/ads
haarts · 2026-10-23 21:20:32 UTC
Ok. Sounds cool.
Now what? Open source weights? An API somewhere? Available on Openrouter? Are they just testing?
Where is this going?
ByteAtATime · 2026-10-23 21:26:55 UTC
> 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).
Now that a larger proportion of text is AI, I'm appreciating human-written text more and more; this got a good chuckle out of me.
AndrewKemendo · 2026-10-23 22:44:35 UTC
I wouldn’t be so sure that that’s human text
I can reliably get my custom models to output a 95% perfect replication of my tone and voice
AspireOne · 2026-10-23 22:59:36 UTC
As somebody who attempted that recently, I seriously doubt that percentage :D
nomel · 2026-10-23 23:55:17 UTC
Maybe you just have a voice that's, shall we say, in sparse latent space? ;)
adastra22 · 2026-10-24 02:26:02 UTC
New insult dropped!
AndrewKemendo · 2026-10-24 01:02:18 UTC
I have an insane amount of writing output as training data going back a loooong time so it all comes down to how much training data do you have
throwup238 · 2026-10-24 02:23:31 UTC
Many of us can do it on just our hacker news comments (been there, done that).
sshine · 2026-10-24 00:25:35 UTC
What do you mean by your custom models? Do you mean custom prompting?
AndrewKemendo · 2026-10-24 00:58:28 UTC
Couple things:
I have a “style guide” markdown that is pretty expansive
I run an RLHF style loop with me in the middle for all my writing now where I give a voice rant that is over expressive (aka redundant samples of concepts that I want to express clearly) in order to manage lossy compression steps
Then I will manually clean up that last 5% after a half dozen rounds
That sequence goes into the style guide to be referenced as a reasoning chain of thought to map rant > output
It’s been three years of tuning I’d suspect at this point
sshine · 2026-10-24 03:22:01 UTC
How did you train your style guide, though?
I have a somewhat expansive style guide, and it still reeks of Claude.
My cleanup is much closer to 40%, which still makes it worth the effort, but sometimes when speed matters, I'll apologize for the slop.
ipkstef · 2026-10-24 05:14:52 UTC
I've recently been using gemini argon as a voice judge. so it goes claude ( with style guide) -> voice judge with argon -> claude adjusts. I do that in a few loops before it hard stops if it can't reconcile, and pushes to me for review.
sheepscreek · 2026-10-24 00:59:23 UTC
Guessing - finetuned? Or LoRA?
EDIT: Nevermind, see below. I would definitely go with a LoRA though.
AndrewKemendo · 2026-10-24 01:04:22 UTC
That’s if I was going to build my own model on myself, which I’m not planning on doing at this point
sigmar · 2026-10-24 01:49:22 UTC
>and whatever the hell Angular is
I've definitely seen LLMs compose jokes with this structure a lot where "whatever the hell ___ is" is in parenthesis. Not saying this is AI generated tho
delegate · 2026-10-23 21:29:01 UTC
I actually thought it sounds really good and natural and it freaked me out in a good way.
You can tell that the robots have no idea of what they're talking about, but the voicing, the emotions, etc, really good.. Like talking to a friend on the phone.
Also creepy, because of the potential for abuse of this technology.
But the interesting part to me is that training on voice only is what allows models to learn emotions - voice transmits a lot of emotional information which text doesn't capture. Language has words for a very limited number of emotions - maybe only the peaks - but there's so many more which we can't describe or transmit via text.
You could determine the phonetic tokens which express different kinds of emotions or 'render' text+emotion using a DSL, etc. Exciting stuff.
sgarrity · 2026-10-23 21:32:30 UTC
Now that a robot can speak over people on Zoom calls for me, I’m finally free to write poems all day!
hypfer · 2026-10-23 21:33:19 UTC
Interesting tech, but if these are the hand-picked examples that best represent it, I suppose we're not quite there yet.
The intelligence sounds lacking. At this point, anyway.
But the idea of learning through voice instead of written text might prove fruitful. After all, text isn't strictly native to humans. It's just a tool we've invented.
ajam1507 · 2026-10-23 21:35:12 UTC
This feels like a parlor trick where the AI was trained to mimic informal telephone mannerisms. The actual conversations were pretty bad. Lots of style, not much substance basically.
bushido · 2026-10-23 21:45:10 UTC
I was expecting to run into some uncanny valley-esque. It was surprisingly good.
It is kinda scary that we're here already, I can see this being pretty problematic for seniors/public prone to getting scammed.
computerdork · 2026-10-23 21:51:44 UTC
Agreed, it’s incredible and scary how natural and human it sounds. It’s gonna be pretty much impossible for almost anyone to tell if they’re talking to AI
lrvick · 2026-10-23 21:45:22 UTC
Open weights or it didn't happen.
SwellJoe · 2026-10-23 21:47:26 UTC
So, I tolerate the "ums" and "ahs" and "uhs" in conversation from humans because they're human. If an AI is going to speak to me (gods forbid), it better be concise and clear and focused, or I'm throwing it out the fucking window.
It is interesting that they've done this reasonably successfully, impressive technology. Novel ideas can have inherent value, absent direct uses they may have, as they can be a stepping stone toward other inventions. But, I'm having a hard time coming up with a use case that isn't predatory or intentionally misleading. Company support agents pretending to be human, for instance. Or, taking the next step on AI girlfriend/boyfriend type interactions. Or, outright scams. Models already do an excellent job with voice cloning, at least for intonation and timbre, adding realistic conversational tics makes it even more likely grandma is going to fall for it when her "nephew" calls needing help.
But, that seems to be extremely common with new tech these days. There's always an angle that is unsavory. Marketing, scams, propaganda, surveillance, killing, that's where the money is, so everything bends toward them.
LluisGerard · 2026-10-23 22:16:31 UTC
I also don't get the need for all these imperfections. In some examples it sounds like "she" is half asleep or even tipsy. If I want to talk to an all powered machine that knows my codebase inside out, or that can discuss about technical topics like the universe, science, or a specific technical book, etc... I expect it to be an eloquent speaker, capable of a good cadence, and that's easy to understand. I don't need it to mimic all the imperfections, I want it to be like when I'm talking to a really smart person that keeps me engaged and makes me feel smart.
Especially when you keep in mind that not everyone knows english as their first language. I know he's a bit controversial sometimes but Neil deGrasse Tyson is easy to understand and explained interesting topics in his podcast (I could still understand most of it when I was still getting used to listening to english 15+ years ago).
If conversation is the new interface then we will need UX designers to take care of this.
driverdan · 2026-10-23 23:25:05 UTC
I came here to say the same thing. I don't want a computer constantly inserting stop words, pauses, laughing unnecessarily and interrupting me. This seems technically impressive but is not something I'd want to interact with.
andoando · 2026-10-24 17:15:59 UTC
Could be useful for creating media dont you think? AI movies have gotten pretty good. Visually there stunning and its the voice now I mostly find unnatural
SwellJoe · 2026-10-24 21:39:42 UTC
I consider that among the unsavory use cases, I think. I'm not sure how I feel about its use in art, exactly, but I'm confident this tech will most often be used for propaganda (because that's how it has already been used most broadly). It is currently possible to detect AI video and audio, with reasonable confidence. I mean, unless you're a facebook boomer, in which case nothing is too ridiculous to be believed.
But, a world where billionaires can make ads showing candidates saying and doing things they've never said or done is a very dangerous world, and being able to fabricate a podcast or whatever very convincingly is going to empower the very worst people. Blurring the line between fact and fiction, so nothing one sees or hears is really believable anymore, serves fascists and autocrats, exclusively.
Call me a skeptic, obviously the voice sounds plausible and very realistic and human-level but where does the intelligence come from if it's only trained on human speech datasets? LLMs are powerful because they can do anything, if you only have a voice corpus I doubt it is as powerful as all written human knowledge. Like when it says "My day was good", what does it actually mean? Or is it just generating plausible slop.
GodelNumbering · 2026-10-23 22:13:16 UTC
It sounds like it is trained on a lot of podcasts, judging by a quick few second skims over their demo tracks.
Also, the trend of posting on HN with much more sensationalist title first, getting to the front page, then getting the title adjusted by a moderator should probably be penalized; how is 'most authentic ever' not a marketing term? (not just this post, but a bunch of posts recently got to frontpage by making unreasonable claims)
chrismarlow9 · 2026-10-23 22:34:16 UTC
It also seems like it trained on dialog in plays and novels. Some of these responses seem way too "perfect", like a response you would hear in a dramatic soap opera. Honestly it might be using that too. Just my take from listening to first minute or two of dialog.
Comments
It's up there. I think most humans would be convinced they're talking to a human. I assumed you've used other speech models. They are okay, but not as natural and imperfect as Dessa is.
Makes me realize how bad being silent really is.
For sure there's gonna be people falling in love with them though! I find all the anthropomorphization creepy though.
I think there's a generational judgement part of it, and some hearing damage that makes it harder to understand their words on the very low/creaky end.
Not to mention, it can cause real problems for your vocal chords. A little bit is entirely natural, and I don't really notice it in most men, but a lot of young(er) women seem to go overboard on it (in my opinion).
in theory this could cut costs pretty well for long contexts + there no tokenisation layer.
Would the logical opposite be eternity for all, and bring back the deceased? LLM plays the Joker, happily imprisoned?
I'm a professional cynic and I spread the idea of "population decline to solve our resource problems" every time I have a chance; I even write dystopic science fiction with this theme. I do it not because I think it's the solution (yours is), but to jolt people in a reaction like yours. Let's build a bright future; just in our solar system there's easily enough matter and space for a trillion humans, each enjoying many acres of forest[^1].
[^2]: https://claude.ai/share/bbab0507-109d-4b4b-b5bb-2a44afad901a
In the future you won't be able to tell.
>it sounds like you view women as a warm fleshlight
I think most people accept the fact that women and men are sexual objects. If you view me as a mysoginist for believing that, then I think I understand why you might think our society is still patriarchal or something.
In fact, I can't say that most straight men expect something cerebral or spiritual out of their partners. But even if it was the case, you could expect that a hyper-inteligent machine would exceed human capabilities in this regard.
The only types of people who aren't going to be humping robots are members of isolated societies who have a grudge against technology. Hence the amish.
There are an increasing number of loser men and women who have these AI partners. I think we may see a tipping point where "genetic dead ends" comprise the majority of the population.
With this level of sexual competition, who can blame them? If you're not at the apex you can put in the effort to reproduce but then your offspring are just faced by the same problem, one generation removed.
The majority of men born in this generation won't reproduce. For the average man, there is no sense in doing anything but devoting your life to some high-risk/high-reward strategy. I don't even know what that entails these days, but apparently it involves a lot of sports betting.
I'm normally endowed, as are like 90% of men (so I think these types of baseless insults fall flat). But if I wasn't, would you rather I pass on 3.5 inches of american steel to the next generation? Your insult stands regardless and reveals your underlying preference. If I was endowed well enough, I'm sure you would see my point.
It makes no difference personally, as a gay man who is uninterested in exploring robosexuality. I prefer to work my clankers.
This is the crazy part. It seems pretty smart, and LLMs require 1000x more compute to train. Can this kind of efficiency somehow be achieved with text too?
Also I seem to be missing where/how they are selling this.
Where is this going?
Now that a larger proportion of text is AI, I'm appreciating human-written text more and more; this got a good chuckle out of me.
I can reliably get my custom models to output a 95% perfect replication of my tone and voice
I have a “style guide” markdown that is pretty expansive
I run an RLHF style loop with me in the middle for all my writing now where I give a voice rant that is over expressive (aka redundant samples of concepts that I want to express clearly) in order to manage lossy compression steps
Then I will manually clean up that last 5% after a half dozen rounds
That sequence goes into the style guide to be referenced as a reasoning chain of thought to map rant > output
It’s been three years of tuning I’d suspect at this point
I have a somewhat expansive style guide, and it still reeks of Claude.
My cleanup is much closer to 40%, which still makes it worth the effort, but sometimes when speed matters, I'll apologize for the slop.
EDIT: Nevermind, see below. I would definitely go with a LoRA though.
I've definitely seen LLMs compose jokes with this structure a lot where "whatever the hell ___ is" is in parenthesis. Not saying this is AI generated tho
But the interesting part to me is that training on voice only is what allows models to learn emotions - voice transmits a lot of emotional information which text doesn't capture. Language has words for a very limited number of emotions - maybe only the peaks - but there's so many more which we can't describe or transmit via text.
You could determine the phonetic tokens which express different kinds of emotions or 'render' text+emotion using a DSL, etc. Exciting stuff.
The intelligence sounds lacking. At this point, anyway.
But the idea of learning through voice instead of written text might prove fruitful. After all, text isn't strictly native to humans. It's just a tool we've invented.
It is kinda scary that we're here already, I can see this being pretty problematic for seniors/public prone to getting scammed.
It is interesting that they've done this reasonably successfully, impressive technology. Novel ideas can have inherent value, absent direct uses they may have, as they can be a stepping stone toward other inventions. But, I'm having a hard time coming up with a use case that isn't predatory or intentionally misleading. Company support agents pretending to be human, for instance. Or, taking the next step on AI girlfriend/boyfriend type interactions. Or, outright scams. Models already do an excellent job with voice cloning, at least for intonation and timbre, adding realistic conversational tics makes it even more likely grandma is going to fall for it when her "nephew" calls needing help.
But, that seems to be extremely common with new tech these days. There's always an angle that is unsavory. Marketing, scams, propaganda, surveillance, killing, that's where the money is, so everything bends toward them.
Especially when you keep in mind that not everyone knows english as their first language. I know he's a bit controversial sometimes but Neil deGrasse Tyson is easy to understand and explained interesting topics in his podcast (I could still understand most of it when I was still getting used to listening to english 15+ years ago).
If conversation is the new interface then we will need UX designers to take care of this.
But, a world where billionaires can make ads showing candidates saying and doing things they've never said or done is a very dangerous world, and being able to fabricate a podcast or whatever very convincingly is going to empower the very worst people. Blurring the line between fact and fiction, so nothing one sees or hears is really believable anymore, serves fascists and autocrats, exclusively.
https://www.usatoday.com/story/news/state/texas/2026/09/09/k...
Also, the trend of posting on HN with much more sensationalist title first, getting to the front page, then getting the title adjusted by a moderator should probably be penalized; how is 'most authentic ever' not a marketing term? (not just this post, but a bunch of posts recently got to frontpage by making unreasonable claims)