Hey folks, welcome back to another video loaded with groundbreaking updates in AI and robotics! We kick things off with the mysterious Half Moon model, revealed as Re-Image 1.0, showcasing its state-of-the-art text-to-image capabilities. OpenAI introduces a new API for text-to-speech, enabling natural conversational AI agents, and we delve into its features. There's exciting news from Topaz Labs with Gigapixel Recover V2, a new open-source framework for Gemini 2.0, and advancements in AI video generation from Vedo and Creo. Notebook LM gets an update for interactive mind maps, and Sync Labs presents the most natural lip-sync model in the world. We also explore Audio X's anything-to-audio generation and check out Orpheus 3B's emotive text-to-speech. Large language models are making strides with Grok and Perplexity AI, plus a new release from LG AI Research. Finally, we touch on advancements in 3D scene reconstruction with Bolt 3D and end with info about the RTX 4080 Super giveaway! Stay tuned!
GIVEAWAY: ???? How to Enter:
Register for NVIDIA GTC 2025 here: https://nvda.ws/3voJ8LE
ONCE GTC BEGINS - Fill out the quick giveaway entry form linked below.
???? Giveaway Entry Form: https://forms.gle/W8oHZuWDa5EmLjgD6
???? Important Dates:
GTC 2025: March 17–21, featuring CEO Jensen Huang's keynote on March 18th at 10 AM PT.
Giveaway Announcement: Winner announced after GTC concludes! (Mar 25th)
▼ Link(s) From Today’s Video:
Tibopr's halfmoon post: https://x.com/btibor91/status/1902829344914821476
Reve Image Gen: https://preview.reve.art/app
Open AI TTS API: https://x.com/OpenAIDevs/status/1902773579323674710
OpenAI.fm
Open AI TTS Jailbreak: https://x.com/elder_plinius/status/1902792908358521092
Co Draw w/ Gemini 2.0: https://x.com/trudypainter/status/1902066035706011735
Topaz restoration v2: https://x.com/topazlabs/status/1902742856512446490
Major Vidu Character consistency update: https://x.com/ViduAI_official/status/1903016423405871286
Krea AI Wan 2.1 Video Training: https://x.com/krea_ai/status/1902722055759671505
http://krea.ai/train
Wan 2.1 Start and End Frame: https://x.com/SlipperyGem/status/1902320774150496277
NEO Bot at GTC: https://x.com/TheHumanoidHub/status/1902820130234753487
Nvidia Newton: https://x.com/TheHumanoidHub/status/1902091038342484239
Boston Dynamics insane demo: https://x.com/kimmonismus/status/1902381966978171141
Interactive mind maps for NotebookLM: https://x.com/tokumin/status/1902251588925915429
New Lipsyncing: https://x.com/synclabs_so/status/1901780574936957055
Anything to Audio model: https://x.com/_akhaliq/status/1902401998776852512
https://github.com/ZeyueT/AudioX
Open Source Orpheus 3B: https://x.com/reach_vb/status/1902445501427114043
Canary 1B Open Source by Nvidia: https://x.com/reach_vb/status/1902730989811413250
Grok "Deeper Search" https://x.com/cb_doge/status/1902365973396779052
Updated Perplexity Deep Research: https://x.com/AravSrinivas/status/1902876897773760577
LG's Deepseek R1 killer: https://x.com/LG_AI_Research/status/1901803002052436323
https://huggingface.co/LGAI-EXAONE/EXAONE-Deep-32B
https://www.lgresearch.ai/blog/view?seq=543
Hunyuan T-1: https://x.com/TXhunyuan/status/1903121005809373386
https://huggingface.co/spaces/tencent/Hunyuan-T1
Bolt 3D: https://x.com/StanSzymanowicz/status/1902329759918444551
o1 pro api is expensive: https://x.com/kimmonismus/status/1902600481244852286
Motion streamer: https://x.com/dreamingtulpa/status/1903009469321318904
► MattVidPro Discord: https://discord.gg/mattvidpro
► Follow Me on Twitter: https://twitter.com/MattVidPro
► Buy me a Coffee! https://buymeacoffee.com/mattvidpro
-------------------------------------------------
▼ Extra Links of Interest:
General AI Playlist: https://www.youtube.com/playlist?list=PLrfI66qWYbW3acrBQ4qltDBsjxaoGSl3I
AI I use to edit videos: https://www.descript.com/?lmref=nA4fDg
Instagram: instagram.com/mattvidpro
Tiktok: tiktok.com/@mattvidpro
Gaming & Extras Channel: https://www.youtube.com/@MattVidProGaming
Let's work together!
- For brand & sponsorship inquiries: https://tally.so/r/3xdz4E
- For all other business inquiries: mattvidpro@smoothmedia.co
All Suggestions, Thoughts And Comments Are Greatly Appreciated… Because I Actually Read Them.
00:00 Introduction and Video Overview
00:30 New Text-to-Image Model: Re Image 1.0
03:33 OpenAI's New Text-to-Speech API
05:36 Gemini 2.0 and Topaz Labs Innovations
07:24 Advancements in AI Video Generation
10:39 AI and Robotics: The Future is Here
15:07 Interactive Mind Maps with Notebook LM
17:04 Sync Labs' Revolutionary Lip Sync Model
18:34 Audio X: The Future of Audio Generation
21:52 Orpheus 3B: Emotive Text-to-Speech
24:35 Nvidia's Open Source Speech Recognition
25:02 Advancements in Large Language Models
29:29 Bolt 3D: Interactive 3D Scenes
32:11 Nvidia GTC Giveaway Announcement
GIVEAWAY: ???? How to Enter:
Register for NVIDIA GTC 2025 here: https://nvda.ws/3voJ8LE
ONCE GTC BEGINS - Fill out the quick giveaway entry form linked below.
???? Giveaway Entry Form: https://forms.gle/W8oHZuWDa5EmLjgD6
???? Important Dates:
GTC 2025: March 17–21, featuring CEO Jensen Huang's keynote on March 18th at 10 AM PT.
Giveaway Announcement: Winner announced after GTC concludes! (Mar 25th)
▼ Link(s) From Today’s Video:
Tibopr's halfmoon post: https://x.com/btibor91/status/1902829344914821476
Reve Image Gen: https://preview.reve.art/app
Open AI TTS API: https://x.com/OpenAIDevs/status/1902773579323674710
OpenAI.fm
Open AI TTS Jailbreak: https://x.com/elder_plinius/status/1902792908358521092
Co Draw w/ Gemini 2.0: https://x.com/trudypainter/status/1902066035706011735
Topaz restoration v2: https://x.com/topazlabs/status/1902742856512446490
Major Vidu Character consistency update: https://x.com/ViduAI_official/status/1903016423405871286
Krea AI Wan 2.1 Video Training: https://x.com/krea_ai/status/1902722055759671505
http://krea.ai/train
Wan 2.1 Start and End Frame: https://x.com/SlipperyGem/status/1902320774150496277
NEO Bot at GTC: https://x.com/TheHumanoidHub/status/1902820130234753487
Nvidia Newton: https://x.com/TheHumanoidHub/status/1902091038342484239
Boston Dynamics insane demo: https://x.com/kimmonismus/status/1902381966978171141
Interactive mind maps for NotebookLM: https://x.com/tokumin/status/1902251588925915429
New Lipsyncing: https://x.com/synclabs_so/status/1901780574936957055
Anything to Audio model: https://x.com/_akhaliq/status/1902401998776852512
https://github.com/ZeyueT/AudioX
Open Source Orpheus 3B: https://x.com/reach_vb/status/1902445501427114043
Canary 1B Open Source by Nvidia: https://x.com/reach_vb/status/1902730989811413250
Grok "Deeper Search" https://x.com/cb_doge/status/1902365973396779052
Updated Perplexity Deep Research: https://x.com/AravSrinivas/status/1902876897773760577
LG's Deepseek R1 killer: https://x.com/LG_AI_Research/status/1901803002052436323
https://huggingface.co/LGAI-EXAONE/EXAONE-Deep-32B
https://www.lgresearch.ai/blog/view?seq=543
Hunyuan T-1: https://x.com/TXhunyuan/status/1903121005809373386
https://huggingface.co/spaces/tencent/Hunyuan-T1
Bolt 3D: https://x.com/StanSzymanowicz/status/1902329759918444551
o1 pro api is expensive: https://x.com/kimmonismus/status/1902600481244852286
Motion streamer: https://x.com/dreamingtulpa/status/1903009469321318904
► MattVidPro Discord: https://discord.gg/mattvidpro
► Follow Me on Twitter: https://twitter.com/MattVidPro
► Buy me a Coffee! https://buymeacoffee.com/mattvidpro
-------------------------------------------------
▼ Extra Links of Interest:
General AI Playlist: https://www.youtube.com/playlist?list=PLrfI66qWYbW3acrBQ4qltDBsjxaoGSl3I
AI I use to edit videos: https://www.descript.com/?lmref=nA4fDg
Instagram: instagram.com/mattvidpro
Tiktok: tiktok.com/@mattvidpro
Gaming & Extras Channel: https://www.youtube.com/@MattVidProGaming
Let's work together!
- For brand & sponsorship inquiries: https://tally.so/r/3xdz4E
- For all other business inquiries: mattvidpro@smoothmedia.co
All Suggestions, Thoughts And Comments Are Greatly Appreciated… Because I Actually Read Them.
00:00 Introduction and Video Overview
00:30 New Text-to-Image Model: Re Image 1.0
03:33 OpenAI's New Text-to-Speech API
05:36 Gemini 2.0 and Topaz Labs Innovations
07:24 Advancements in AI Video Generation
10:39 AI and Robotics: The Future is Here
15:07 Interactive Mind Maps with Notebook LM
17:04 Sync Labs' Revolutionary Lip Sync Model
18:34 Audio X: The Future of Audio Generation
21:52 Orpheus 3B: Emotive Text-to-Speech
24:35 Nvidia's Open Source Speech Recognition
25:02 Advancements in Large Language Models
29:29 Bolt 3D: Interactive 3D Scenes
32:11 Nvidia GTC Giveaway Announcement
- Category
- Artificial Intelligence
- Tags
- mattvidpro, mattvidpro ai, ai news
Comments