Skip to content Skip to footer
0 items - $0.00 0

Crossing the uncanny valley of conversational voice by monroewalker

Crossing the uncanny valley of conversational voice by monroewalker

Crossing the uncanny valley of conversational voice by monroewalker

33 Comments

  • Post Author
    monroewalker
    Posted March 2, 2025 at 6:16 am

    This was already posted here: https://news.ycombinator.com/item?id=43221377 but I’m really surprised at the lack of attention this model is getting. The responsiveness and apparent personality are pretty mind blowing. It’s similar to what OpenAI had initially demoed for advanced voice mode, at least for the voice conversation portion.

    The demo interactions are recorded, which is mentioned in their disclaimer under the demo UI. What isn't mentioned though is that they include past conversations in the context for the model on future interactions. It was pretty surprising to be greeted with something like "welcome back" and the model being able to reference what was said in previous interactions. The full disclaimer on the page for the demo is:

    "
    1. Microphone permission is required. 2. Calls are recorded for quality review but not used for ML training and are deleted within 30 days. 3. By using this demo, you are agreeing to our
    "

    edit: Actually this has been posted quite a few times already and had good visibility a couple days ago:
    https://news.ycombinator.com/item?id=43200400
    Others: https://hn.algolia.com/?q=sesame.com

  • Post Author
    drvladb
    Posted March 2, 2025 at 6:30 am

    Definitely an improvement over your normal Text-To-Speach model, and to some degree really different, but the subtle imperfections do appear and ruin the overall perception. A move in the right direction, though, I suppose.

  • Post Author
    kats
    Posted March 2, 2025 at 6:33 am

    AI voice is an overwhelmingly harmful technology. It's biggest use will be to hurt people.

  • Post Author
    bobosha
    Posted March 2, 2025 at 6:36 am

    Very impressive. well done team sesame!

  • Post Author
    tobr
    Posted March 2, 2025 at 6:38 am

    I asked it if it could whisper, and it replied in full voice, ”I’m whispering to you right now”.

  • Post Author
    thekevan
    Posted March 2, 2025 at 6:41 am

    It's good, but it still sounds fake to me, but in a different way. The voice itself sounds like a human, undoubtedly.

    But the cadence and the rhythm of speaking are off. It sounds like someone who isn't a podcaster trying to speak in the personality of a podcaster. It just sounds like someone trying too hard and speaking in an unnatural way.

  • Post Author
    bloomingkales
    Posted March 2, 2025 at 6:43 am

    This is so good that it's disarming. People are going to blabber everything to it, so we need a local private model. It's a lot to ask, I know. Incredible tech.

  • Post Author
    singularity2001
    Posted March 2, 2025 at 6:51 am

    pretty impressive demo but not my style I mean the constant jabbing and kind of unintelligent behavior. so yeah it feels pretty uncanny but unfortunately in a negative annoying way. I don't think this is a limitation of the model they could just adopt to more scientific users in a more cooperative way, similar to how ChatGPT has this very sophisticated aura. I don't like how systems which have no emotions constantly pretend to have emotions but maybe that's just me.

  • Post Author
    pulkitsh1234
    Posted March 2, 2025 at 6:52 am

    This is mind blowing

  • Post Author
    rendall
    Posted March 2, 2025 at 6:53 am

    Well done. My first impression:

    Cons: they are just a bit too casual with their language. The casualness came off somewhat studied and inauthentic. They were just a bit too eager to fill silence: less than a split second of silence, and they were chattering. If they were humans I would think they were a bit insecure and trying too hard to establish rapport. But those flaws are relatively minor, and could just be an uncanny valley thing.

    Pros: They had such personalities that I felt at moments that I was talking to a person. Maya was trying to make me laugh and succeeded. They took initiative in conversation; even if that needs some tweaking, it feels huge.

  • Post Author
    razemio
    Posted March 2, 2025 at 6:58 am

    I asked if speaking in German would be possible and the result was if someone is trying to speak German without knowing any word. However, I asked if a german sentence could be repeated after me and it was insanely good. Impressive tech!

  • Post Author
    mohsen1
    Posted March 2, 2025 at 7:02 am

    The intelligence of the model is very low though. I asked it about catcalling and it started to talk about cats!

  • Post Author
    TZubiri
    Posted March 2, 2025 at 7:16 am

    Or don't, revert course and give me robo-voice!

  • Post Author
    kaizenb
    Posted March 2, 2025 at 7:20 am

    Glad to have my HER moment!

  • Post Author
    names_are_hard
    Posted March 2, 2025 at 7:23 am

    I must be doing something wrong, but the demo seems to be the voice having a conversation with itself? It doesn't let me interject, and it answers its own questions. There's some kind of feedback loop here, it seems.

  • Post Author
    karimf
    Posted March 2, 2025 at 7:30 am

    This might be a game changer for learning English.

    I'm from a developing country and it's sad that most English teachers on public schools here can't speak English well. There are good English teachers, but they are expensive and they are not affordable for the average people.

    OpenAI realtime models are good, but we can't deploy it to masses since it's very expensive.

    This model might be able to solve the issue since it's better or on par with the OpenAI model, yet it's significantly cheaper since it's a fairly small model.

  • Post Author
    wewewedxfgdf
    Posted March 2, 2025 at 7:31 am

    Yeah that's remarkable.

    Trying asking it to be dungeon master and play dungeons and dragons style role playing game.

  • Post Author
    habosa
    Posted March 2, 2025 at 7:36 am

    The first thing it said to me was that I should read the “looong looong” post about how it works and it pronounced that as “loon-g” not “lawn-g” which was a weird own goal.

    Extremely impressive overall though.

  • Post Author
    bradley13
    Posted March 2, 2025 at 7:41 am

    Maybe I'm weird, but I have zero desire to talk with an AI model. I use them a lot, in a browser or a console. But talking? No. Just…no. Why would I?

  • Post Author
    jonplackett
    Posted March 2, 2025 at 7:49 am

    My end-of-the-world AI prediction is everyone gets a phone call all at the same time and the voice on the end of the phone is so perfect they never put the phone down again. Maybe they do whatever it asks them to, maybe it’s just lovely.

  • Post Author
    swang
    Posted March 2, 2025 at 7:51 am

    i turned it on while i was heating some hot chocolate

    told it, "hold on" as i was putting on my headset, they said "no problem". but then i tried to fill the empty airtime by saying, "i'm uhh heating some hot chocolate?"

    the ai's response was something like, "ah.. (something) (something). data processing or is it the real kind with marshmallows"

    not 100% on the exact dialog but 100% would not have been fooled by this. closed it there. no uncanny valley situation for me.

  • Post Author
    rjpruitt16
    Posted March 2, 2025 at 7:52 am

    "I hate to say this, but I was deeply offended by this model. It sounds more human-like, but it has a strong bias toward political views. I don’t want to talk about the topic that was discussed. However, I would never allow my children to listen to this. I’m surprised that AI is capable of making me this mad. At first, I was excited about a tremendous leap into the future, but now I’m worried about the level of mind control this technology could have over children."

  • Post Author
    radley
    Posted March 2, 2025 at 8:00 am

    The inflection was quite good. The only thing off seemed to be when she was thinking on something new. Instead of pausing to think, her next thought actually started too quickly, cutting off the very end of what she was saying before.

    I am curious how easy it would be to adjust the inflection and timing. She was over-complimentary, which is fine for a demo. But I'd love something more direct, like a brainstorming session, and almost talking over each other. And then a whiteboard…

  • Post Author
    brendanfinan
    Posted March 2, 2025 at 8:16 am

    all chat models seem enraptured by what I have to say. The first one to feign disinterest will pass the Turing test

  • Post Author
    ChrisArchitect
    Posted March 2, 2025 at 8:18 am
  • Post Author
    gorgoiler
    Posted March 2, 2025 at 9:09 am

    I would say most command and control voice interactions are going to be like buying a coffee — the parameters of the transaction are well known, so it’s just about fine tuning the match between what the user wants and what the robot has to do.

    A small minority of these interactions are going to be like a restaurant server — chit chat, pleasantries, some information gathering, followed by issuing direct orders.

    The truly conversational interactions, while impressive, seem to be focused on… having a conversation. When am I going to want to have a conversation with an artificial person?

    It’s precisely this kind of boundary violation of DMV clerks being chatty and friendly and asking about my kids that feels so uncanny, imho, when I’m clearly there for, literally, a one hundred percent transactional purpose. Do people really want to be asked how their day is going when sizing up an M5 bolt order?

    In fact the humanising of robots like this makes it feel very uncomfortable when I have to interrupt their patter, ask them to be quiet, and insist they stay on topic.

  • Post Author
    35mm
    Posted March 2, 2025 at 9:17 am

    Seems like they’re going to make a hardware product based on their open positions. A universal translator earbud would be nice.

  • Post Author
    taylorius
    Posted March 2, 2025 at 9:30 am

    It's very good, really impressive demo. My feedback would be, Maya needs to keep quiet a little longer after asking a question. She would ask something, then as I thought about my reply, already be on to the next thing. It left me with the impression she was a babbler (which is not an unrealistic model of how humans are, but it would be cool to be able to dial such traits up or down to taste).

    I suppose the lack of visual cues probably hinders things in that regard.

  • Post Author
    oezi
    Posted March 2, 2025 at 9:49 am

    Text-To-Speech models still aren't trained on rich enough data to have all the nuances we need to be fully expressive. For example, most models don't have a way to change accents separately from language (e.g. English with a slight French accent) or have an ability to set emotions such as excitement or sleepiness.

    We aren't even talking about adding laughing, singing/rap or beatboxing.

  • Post Author
    daniel-ash
    Posted March 2, 2025 at 10:07 am

    Miles is the first AI I’ve met that is way cooler than me

    Incredible!

  • Post Author
    diimdeep
    Posted March 2, 2025 at 10:14 am

    Some comedy skilled guys made radio play like impro with this AI and it is beyond hilarious.

    Miles gets Arrested: Sesame.ai https://youtu.be/cGMO2hRNnv0

  • Post Author
    richrichardsson
    Posted March 2, 2025 at 10:28 am

    Still suffers the same problem that all Voice Recognition seems to suffer; cannot reliably detect that the speaker has finished speaking.

    This was almost worse though because it did feel like a rude person just interrupting instead of a dumb computer not being able to pick up normal social cues around when the person they're listening to has finished.

  • Post Author
    forgotmysn
    Posted March 2, 2025 at 10:34 am

    a lot of comments are dismissive of these generated convos because of out how obvious it is that these convos are generated. i feel like that's a high bar. you can tell that GTA5 is generated, but it's close enough to be fun. i imagine that's as close as we'll get with conversational AI

Leave a comment

In the Shadows of Innovation”

© 2025 HackTech.info. All Rights Reserved.

Sign Up to Our Newsletter

Be the first to know the latest updates

Whoops, you're not connected to Mailchimp. You need to enter a valid Mailchimp API key.