ฝัง
- เผยแพร่เมื่อ 20 ส.ค. 2024
- Talk to AI Voice to Voice with Enhanced Speech Recognition on Gemini - Google’s newest and most capable AI model. Watch Google DeepMind Research Scientist Adrià Recasens Continente demonstrate Gemini’s abilities to understand audio in different languages, from multiple speakers and to combine vision, audio and text to offer a helping hand while cooking in the kitchen.
Check out more Gemini demos: goo.gle/4164rNO
Find out more about Gemini: deepmind.googl...
Read the blog post: goo.gle/3uRyug7
Subscribe to our Channel: / google
Tweet with us on X: / google
Follow us on Instagram: / google
Join us on Facebook: / google
![[UNCUT] ชาวบ้านถาม “นายกอุ๊งอิ๊งค์” ประชาชนมีกิน มีใช้ กี่โมง? I คนดังนั่งเคลียร์ I 16 ส.ค. 67](http://i.ytimg.com/vi/tKZvOzLIJJc/mqdefault.jpg)
Not losing nuances by not converting to text is a big improvement indeed. I guess theoretically one could still encode to tone in the text e.g. 'Hi there [sad]", but direct seems more nuanced.
Thats a lot of detail loss anyway, like describing an image into text to turn it back to image later
The examples shown however don't demonstrate any nuance. Nothing would be lost by using an ASR model and operating on text. Music examples would have shown this but they didnt use them.
You mean like their underwhelming tree demo@@FretBuzzLIF
0:47 😢😮😊😅😂🎉❤ 0:53 😊
🎉
This seems like the all in one AI
> Multimodal
@@IN-pr3lw🤭
*AGI
That's the whole point of Gemini.
Its not but we are getting there @@Dominic416_
These Gemini videos are incredible. What a time to be alive
What a time to be alive !!
Hold your papers ...
Hold on to your papers fellow scholars
Glad you're loving these videos!
Only people, who arent creatives themselves and cant see where this is going and how it will deprive people of creative skills, love this crap.
Great, now give it hands to do the actual cooking too.
But don't ask it (or maybe them) what is strangulation.
Will happen soon ...
Hey Google,I am loving these videos
We want the all features of Gemini's vision to be added to Bard 👁️
Does make sense
I don't think we need bard anymore, he was a failure. Gemini looks like the way to go from here.
@@loot6actually Bard now is going to work from Gemini's reasoning underneath it.
@@andregustavo2086 Well if they replace Bard with Gemini underneath that would work although it wouldn't really be Bard anymore.
@@loot6 yes, but that's easier for marketing since they don't need to stop Bard's branding and start Gemini's from scratch.
Wild times ahead.
well I am not sure how to use automatic voice recognition for example when I say something it would automatically stop and then speak because in the website I can press listen and then it can speak but in here I hear automatic speaking first off a sound when pressing the microphone which I didn't hear in the website and a really bad thing is in here I hear a text to speech with a bit of emotions but in the website I hear the normal Google Text-to-Speech so the sound is different there I'm not sure if that's a problem of Gemini ultra and advanced but I really want to check that out just if it's one audio send and receive
they should add an audio decoder to get the audio generating capabilities we need.
Yes, I think it is still using text-to-speech for the output audio
Is this currently available to developers via the Gemini Pro API?
If it is, how good is it at handling non-native English accents, particularly from South and East Asia?
Are these capabilities native to Nano?
Is there any way to try this? Because I can't find any API or even Playground for this...
In coming we can see a plugin or inbuilt to listen any podcast in every language
No live demonstration? Means it's not reliable yet
Gemini is awesome 😱😱😱😱
Glad we're on the same page 📚
This is amazing! Can we please get an update for pixel phones as voice to text is very bad.
I can't wait to use this with my students and enjoy it asking and imagining things with its help. Love Gemini already.
Bard with Gemini Pro is here to help! ✨
Imagining happens in the mind...its about pictures in our head and then putting them into reality with OUR skills. Humans will become less able to imagine and visualize if they let ai garbage do everything. Creative skills will seem less relevant and it will deprive people of so much...also spiritually. Its just awful.
Real time translation is $1 trillion company think about it guys.
There are several other companies who have accomplished this right around the same time... I think that will probably bring the value to a more reasonable level. Certainly it is revolutionary.
Value wise ya but it’ll be free!
If it's free, you're the product.
@@joshuaritter1880 ill pay the price
@@joshuaritter1880 not necessarily if it’s an open source version running locally.
Voice for English a sounds ight, i fell for inflection PI natural voice processing. But the multimodel capabilities are welcomed 😮.
They’ll completely works documents before sending 3:45
Very nice ❤️
Never been a Fan of A.I until now, can't wait to meet GEMINI😫😫
Wow... Love it.
Late but stronger than before!
Where is the documentation to be able to use the speak with audio
I am here for the history
Is Gemini capable of understanding "any" raw sound (like the sound of the Rain for example) or just speech?
Ladies and gentlemen-welcome to the future 🔥
Thank you!
0:51 @@groundcrewz
Something about his feels staged. It's interesting that he keeps uploading clips of speech rather than speaking to it himself. Does it not accurately recognise his speech because of his accent? Have those files been specifically curated?
Interesting Concept
Did you use TH-cam data to train ?
So how and where can i use this now?
Welcome to jamshedpur
If this is deployed to mobile phones, everyone owns an AI assistant.
I wish you could use it with Android 9 or 10 because mine is 10 and I can't use it the program says the program is not supported on this device and even on Android 14 it says unavailable and on Android 8 it says you need to update your Google App because eventually I think Android 8 has an old Google and it doesn't support it
Amazing
Adrià, do you think Gemini will understand catalan? As google assistant don't. 😉
How can Gemini assist in refining and enhancing a monolingual Haitian dictionary that already contains 160,000 words? How can I have access and training on it ?
Just take my money, can't wait
Hopefully it'll be able to transcribe the lyrics from the songs in my doomblackdeathgrindcore playlist.
When will multimodal input to speech be added to the Android Gemini API?
Hello Google, can you make a video on how to add Gemini to nocode pages like bubble?
This is so cool I just though about it recently that speech recognition is not enough for lesson learning because it ignores pronunciation. It may be used in so many ways! Will it recognize by voice when person is sad or irritated? It seems not so hard now.
That's really great google comes back with the greatest worrier demonstrations step up to AI.
Valor auriculares?
0:49 0:50
Nice... I just don't like how it sounds like a robot speaking.... ChatGPT sounds more natural
It is the easiest thing to improve.
Lets see what will happen in future
My aunt teached me how to make an omelet.
Just take my money
When will we have the android app version of it with out having to use browsers
It'll probably hit America first before it goes global.
It seems like this is going to be quite helpful for those with a disability.🎉
Si , und warum zum Geier funktioniert genau das jetzt noch nicht. Das wär doch Mal der Hammer wenn es das gäbe
Ok, but I see Bard being a good adildition, time will tell
google gemini and youtube collab
Amazing!
dude I can just look at my omelette myself to see if it's cooked or not
I wish it can also speak in my language, Tagalog...
Can Gemini do life and earth science exercises based on viewing documents with cells , in Arabic
Rapture is imminent. Jesus loves you. Don’t take the mark of the beast.
Is this based on python?
It's probably based from Python cuz Google has TensorFlow, a machine learning frame to train AI models.😁🤖🤖🤖🤖🤖
🙌🙌🙌🙌
Sounds a bit aggressive. At least now I'll finally able to make an omelette!
When this technology evolves, and it has text to speech, my plan is to speak to it in a language I'm learning so I can improve my language skills.
This monstrous crap will ruin so many skills and it will render your language skills useless one day, like so many other things. Its not here to assist you, its meant to deprive people of all ambition to master something and deprives creative drive.
Its over for us humans
Where can I try this? Bard on my computer doesn't have the "add chunk" button
That's seems like AGI. 🤔
Why are you people messing with my phone and me
This is pro version 😢
Cool
🥰🥰🥰
Future of music feedback is coming soon for music producers? Also anime voice responds?? Possible?
🎯 Key Takeaways for quick navigation:
00:00 🎙️ *Processing raw audio with Gemini*
- Gemini can process raw audio end-to-end without converting it to text.
- This approach retains nuances like voices and pronunciation.
00:57 🗣️ *Pronunciation example*
- Gemini accurately differentiates between pronunciations in a foreign language.
- It provides detailed responses based on audio input.
02:02 🗨️ *Multimodal understanding*
- Gemini goes beyond transcription, understanding conversation content.
- It seamlessly integrates vision, audio, and text for nuanced comprehension.
03:14 🔄 *Simultaneous processing of three modalities*
- Gemini demonstrates the ability to process audio, vision, and text simultaneously.
- It can provide step-by-step guidance based on audio input, enhancing user interactions.
Made with HARPA AI
How long till the singularity?
Is this spanish or greek?
The ai voice still looks artificial. The chatgpt voice to android looks like a real person speaking.
But the bowl has holes..... 🤣 crack the egs and whisk them.... well.... someone has never used bowl with holes .... for sure 😁
omg how many people will die from eating raw eggs!
Can gemini help me understand your accent?
Seem better than Claude 😂
I wonder if the Ai has perfect pitch?
🌑🌒
เราจะมีการวิจัยพืชทดแทนยาเสพติดเราจะปรับปรุง
❤🎉😂😮
❤
Ali Noor😂
Sounds like another excuse for Google to collect personal information
❤❤❤🤤🤤🤤👄
😢😮h
agi
Software engineer jobs are.GONE
Even if you show a program code to copilot, chatgtp and bard, they can't do anything
This wont help people
Meanwhile, Google Assistant getting worse and worse to the point of being a glorified table decoration.
wow! this would have been super impressive last year!
This is literally the best publicly available model you dolt 😂
@@Cagrst publicly available available? Show me its API docs. Go ahead, I'll wait. And it's the best, based on what exactly? I'll bet you can't answer either of these questions coherently.
publicity stunt hhaaa
°•°• I believe we are meant to be like Jesus in our hearts and not in our flesh. But be careful of AI, for it is just our flesh and that is it. It knows only things of the flesh (our fleshly desires) and cannot comprehend things of the spirit such as peace of heart (which comes from obeying God's Word). Whereas we are a spirit and we have a soul but live in the body (in the flesh). When you go to bed it is your flesh that sleeps but your spirit never sleeps (otherwise you have died physically) that is why you have dreams. More so, true love that endures and last is a thing of the heart (when I say 'heart', I mean 'spirit'). But fake love, pretentious love, love with expectations, love for classic reasons, love for material reasons and love for selfish reasons that is a thing of our flesh. In the beginning God said let us make man in our own image, according to our likeness. Take note, God is Spirit and God is Love. As Love He is the source of it. We also know that God is Omnipotent, for He creates out of nothing and He has no beginning and has no end. That means, our love is but a shadow of God's Love. True love looks around to see who is in need of your help, your smile, your possessions, your money, your strength, your quality time. Love forgives and forgets. Love wants for others what it wants for itself. Take note, true love works in conjunction with other spiritual forces such as patience and faith (in the finished work of our Lord and Savior, Jesus Christ, rather than in what man has done such as science, technology and organizations which won't last forever). To avoid sin and error which leads to the death of our body and also our spirit in hell fire, we should let the Word of God be the standard of our lives not AI. If not, God will let us face AI on our own and it will cast the truth down to the ground, it will be the cause of so much destruction like never seen before, it will deceive many and take many captive in order to enslave them into worshipping it and abiding in lawlessness. We can only destroy ourselves but with God all things are possible. God knows us better because He is our Creater and He knows our beginning and our end. Our prove text is taken from the book of John 5:31-44, 2 Thessalonians 2:1-12, Daniel 7-9, Revelation 13-15, Matthew 24-25 and Luke 21. Let us watch and pray... God bless you as you share this message to others.
So far, it can't understand me
sorry. For overdoing. youtu.b 1:33 1:33
3เหรียญทองคำขายให้บริษัท google ดีกว่าเขามีวิสัยทัศน์เทคโนโลยีแห่งอนาคตมันจะเป็นต้นแบบ
I wish it can also speak in my language, Tagalog...