Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

ChatGPT with voice is now available to all free users

twitter.com

Post reply on HN
Print view View original

231–240 of 303 posts

Re: ChatGPT with voice is now available to all free users

#231

Post by Tycho »

15457345234 wrote: post #97
Tycho wrote: post #5

I enjoy using the voice mode to learn about subjects when I’m driving.

Does it tell you the truth, or just stuff that sounds right?

Hasn't really been a problem. The way I use it is like

"Explain this concept to me."

"Give examples from the physical world and every day life."

"Elaborate on that last example."

"Give some examples from the domain of ___."

"Tell me about the history of the concept and why it was necessary to invent it."

"How does this concept relate to the concept of ___."

So I'm trying to approach what I want to learn from many different angles and build context and intuition. Sort of like talking to a tireless grad student tutor. Errors would become more obvious due to contradiction. I've caught it making some mistakes but they were sort of trivial and I could see the spirit of what it was getting at. Plus, "truth" tends to "click."

Re: ChatGPT with voice is now available to all free users

#232

Post by d1sxeyes »

gettodachoppa wrote: post #178
lagt_t wrote: post #136

Earlier quoted context omitted.

Why aren't you complaining about what happens to your HN posts?

It's a spectrum, not a binary. They may not care about HN posts because: 1. We're anonymous here (by default) 2. You can't be fingerprinted from your HN posts the way you can be with your unique voice

On point 2, someone posted a tool a while back called Stylometry which is now sadly defunct, but had some interesting feedback and seemed to be pretty successful at identifying “alts”. I’m sure that the tech has improved since then and would be only more accurate than it was a year ago.

https://news.ycombinator.com/item?id=33755016

Re: ChatGPT with voice is now available to all free users

#233

Post by Sakos »

jmccarthy wrote: post #106
lkozloff wrote: post #7

Interesting - this was actually a feature that got me to convert. I have some slight annoyances with how it handles natural pauses as I collect my thoughts and speak, but overall it's been great. I've had some interesting discussions and it's helped me structure some thoughts by asking questions and follow-ups, then summarizing our conversation... all while I'm on a walk. One fun thing I did with my family was have i…

While walking the dog today, it talked me through some trade-offs between DBSCAN and isolation forests. Walking + verbalizing the problem is a very different and positive experience for me. I've also used it several times on ~15-20min drives to memorize something I wanted to have available for immediate recall. I had it chunk & quiz me, and by the end of the drive I had it down pat. Fun use of drive time.

> I had it chunk & quiz me

Can you go a bit into how this works? How do you prompt it? This is the first use of ChatGPT I've heard of that would directly benefit me.

Re: ChatGPT with voice is now available to all free users

#235

Post by dgunay »

madmod wrote: post #140

I just used this to practice my Japanese and it was really helpful having a judgement free correction of my grammar. It definitely takes longer than English because it’s using more tokens but the feedback is very thorough. I wish I could make the pause before sending automatically a bit longer. (I know I can hold to do it manually but the automated send is nice.)

I tried telling it to speak slowly but it just kept rattling off at full speed while saying things like "I understand. I'll slow down. How is this for you?" Etc

An unfortunately absent bit of accessibility that would really help second language learners

Re: ChatGPT with voice is now available to all free users

#236

Post by moffkalast »

superhuzza wrote: post #179
jmccarthy wrote: post #106

Earlier quoted context omitted.

While walking the dog today, it talked me through some trade-offs between DBSCAN and isolation forests. Walking + verbalizing the problem is a very different and positive experience for me. I've also used it several times on ~15-20min drives to memorize something I wanted to have available for immediate recall. I had it chunk & quiz me, and by the end of the drive I had it down pat. Fun use of drive time.

A word of caution - I've asked ChatGPT 3.5 to generate quizzes based on books before and while most answers were right, a few were technically wrong, and some were outright fabrications (presented very confidently!)

LLMs fabricating things? Well I never!

Re: ChatGPT with voice is now available to all free users

#237

Post by moffkalast »

modeless wrote: post #57

It's possible to run a voice AI similar to this entirely locally on a normal gaming PC with a good GPU using open source AI models. I have a standalone demo I've been working on that you can try if you have a 12GB+ Nvidia GPU: https://apps.microsoft.com/detail/9NC624PBFGB7 It's still very much a demo and not as good as GPT-4, but it responds much faster. It's fun to play with and it shows the promise. Open models hav…

> if you have a 12GB+ Nvidia GPU

Doesn't that seem a bit excessive for Whisper and Coqui? Or does it also run an LLM for a full local stack?

Re: ChatGPT with voice is now available to all free users

#238

Post by d1sxeyes »

Mandelmus wrote: post #25

Can somebody who knows their stuff about voice synthesis explain to me why chatGPT sounds like it's speaking German with an American accent when I speak to it in German? It's really surprising how believably it sounds like a native American-speaker speaking excellent, just not accent-free, German. I would imagine that voice synthesis models would somehow be trained on data from native speakers, so why the accent?

It’s a good question. I’m not sure of exactly the answer, but I suspect the answer is similar to the answer “why do Americans speak German with an American accent?”

If you learn how to pronounce specific vowels, consonants, etc. in a particular way, it takes a LOT of effort to learn how to pronounce these in a different way. You can approximate to a good extent, but most researchers say that if you don’t develop this skill as a child, you won’t ever be able to pronounce things in a way that sounds like a native speaker.

Presumably, the models have been exposed to significantly more American accents than other accents, and learning how to pronounce phonemes with subtle differences without accepting a “close enough” approximation is a big challenge, especially given that there is already a threshold for acceptability at which level you can still sound like a native English speaker.

Re: ChatGPT with voice is now available to all free users

#239

Post by controversy187 »

superultra wrote: post #114

I’ve been using this for several weeks now and it’s replaced podcasts for me. I’ll just pick a topic and then ask for a summary and then ask clarifying questions. Other times I’ll just goof off. In one chat, I’m rewriting the Star Wars sequels movie by movie with ChatGPT. I’ve realized that I’m built to learn socially, and ChatGPT never tires of my questions or gets annoyed. One interesting story. My 15 year old kid…

> "I’ve realized that I’m built to learn socially"

That sentence really resonated with me and sums up a bunch of ideas that have been swirling in my head recently. I've been "interviewing" ChatGPT about world history for a few months now and even turned it into an unsuccessful podcast! I really enjoy learning and creating much more than I would enjoy listening to my own podcast, though :)

Re: ChatGPT with voice is now available to all free users

#240

Post by konschubert »

chamoda wrote: post #122
nier wrote: post #100

App Store on iOS 17.1.1 in Europe has ChatGPT app version 1.2023.319 (14269) released three days ago. No sign of ChatGPT Voice. No headphone icon to be found. There’s also no «New Features» entry in Settings on the mobile app and so no way to opt into voice conversations as the blog article suggests. https://openai.com/blog/chatgpt-can-now-see-hear-and-speak Edit: The headphone icon appeared on Nov 22, 2023 around 6a…

Anyone having trouble getting this working, just close the app and reopen.

thank you!!!
Post reply on HN