Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Really proud to share something we’ve been working on for a while: Magenta RealTime 2 (MTR2), a live music model that is highly interactive (MIDI, audio, text, lots of parameters) and low-latency (~200ms end-to-end), and runs locally on a MacBook!

Ilaria__Manco's profile picture

Ilaria Manco

3,076 subscribers

45,212 Aufrufe • vor 2 Monaten •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Introducing Magenta RealTime 2 (MRT2): the live music model you can play as an instrument. MRT2 offers MIDI and prompt controls, and runs natively on a MacBook with <200ms latency. Open weights. Open source inference engine. Suite of apps and plugins. Hear what it can do and try it out for yourself below 🧵
1:30

Introducing Magenta RealTime 2 (MRT2): the live music model you can play as an instrument. MRT2 offers MIDI and prompt controls, and runs natively on a MacBook with <200ms latency. Open weights. Open source inference engine. Suite of apps and plugins. Hear what it can do and try it out for yourself below 🧵

Google Magenta Project

113,659 Aufrufe • vor 2 Monaten

Introducing Kitten TTS, a SOTA tiny text-to-speech model - Just 15M parameters - Runs without a GPU - Model size less than 25 MB - Multiple high-quality voices - Ultra-fast - even runs on low-end edge devices Github and HF links below
1:00

Introducing Kitten TTS, a SOTA tiny text-to-speech model - Just 15M parameters - Runs without a GPU - Model size less than 25 MB - Multiple high-quality voices - Ultra-fast - even runs on low-end edge devices Github and HF links below

Divam Gupta

348,944 Aufrufe • vor 1 Jahr

good morning /v1/chat/completions This is a test we ran overnight on TensorRT-LLM with modified kernels serving a custom 1B parameter model we trained for a customer ~200ms end-to-end latency (not TTFB, full request). Beats their current Cerebras stack on latency and quality
0:23

good morning /v1/chat/completions This is a test we ran overnight on TensorRT-LLM with modified kernels serving a custom 1B parameter model we trained for a customer ~200ms end-to-end latency (not TTFB, full request). Beats their current Cerebras stack on latency and quality

Sam Hogan 🇺🇸

43,655 Aufrufe • vor 6 Monaten

Realtime interactive generative models FTW! Announcing a new 🌊 of details and features for Magenta RealTime, the open weights live music AI model from GDM! * Live Jamming with audio input 🎤🎸🎵 * Personalize your own models 🔧 * Tech report 📜 Links below in the 🧵...
1:31

Realtime interactive generative models FTW! Announcing a new 🌊 of details and features for Magenta RealTime, the open weights live music AI model from GDM! * Live Jamming with audio input 🎤🎸🎵 * Personalize your own models 🔧 * Tech report 📜 Links below in the 🧵...

Jesse Engel

183,638 Aufrufe • vor 1 Jahr

🔊🔛🔥 ... Groq Inc launched voice generation today. GroqCloud now has realtime transcription, LLMs, *and* text-to-speech. You can build super-responsive, ultra low-latency voice agents end-to-end entirely on Groq! At Daily, we're big fans of Groq's fast, low-latency inference. Pipecat AI supports all the Groq models, including the new voice model. Lately, we've been obsessively playing a voice chat game that Mark Backman wrote. (My high score is 6, so far.) Here's Mark, with Groq's `Celeste-PlayAI` voice.
0:47

🔊🔛🔥 ... Groq Inc launched voice generation today. GroqCloud now has realtime transcription, LLMs, *and* text-to-speech. You can build super-responsive, ultra low-latency voice agents end-to-end entirely on Groq! At Daily, we're big fans of Groq's fast, low-latency inference. Pipecat AI supports all the Groq models, including the new voice model. Lately, we've been obsessively playing a voice chat game that Mark Backman wrote. (My high score is 6, so far.) Here's Mark, with Groq's `Celeste-PlayAI` voice.

kwindla

31,843 Aufrufe • vor 1 Jahr

Also we'd like to take this special occasion to share something we've been working on. There is still a lot of development ahead, but since it's 10th anniversary we'd like to share something exciting for the end of the news!
0:35

Also we'd like to take this special occasion to share something we've been working on. There is still a lot of development ahead, but since it's 10th anniversary we'd like to share something exciting for the end of the news!

Rabi-Ribi

133,209 Aufrufe • vor 7 Monaten

Along with text, images, video and code, Gemini is able to process raw audio signal end-to-end. 🔊 It can listen to and understand speech, making it not only useful for transcription but a model that has a much more nuanced perception of its environment. ↓
3:44

Along with text, images, video and code, Gemini is able to process raw audio signal end-to-end. 🔊 It can listen to and understand speech, making it not only useful for transcription but a model that has a much more nuanced perception of its environment. ↓

Google DeepMind

140,179 Aufrufe • vor 2 Jahren

something i forgot to mention is that this is actually a player model ive been working on and not a mod lol.
1:08

something i forgot to mention is that this is actually a player model ive been working on and not a mod lol.

GoldyBer

13,297 Aufrufe • vor 1 Monat

1/ I’m excited for Speak to be a featured use case for OpenAI’s Realtime API launch today! We’ve been working closely with them on this API for a while. And speech-to-speech is going to be a game changer not just for Speak but for all software.
2:28

1/ I’m excited for Speak to be a featured use case for OpenAI’s Realtime API launch today! We’ve been working closely with them on this API for a while. And speech-to-speech is going to be a game changer not just for Speak but for all software.

Connor Zwick

60,705 Aufrufe • vor 1 Jahr

Transformer Explainer Really cool interactive tool to learn about the inner workings of a Transformer model. Apparently, it runs a GPT-2 instance locally in the user's browser and allows you to experiment with your own inputs. This is a nice tool to learn more about the different components inside the Transformer and the transformations that occur. Tool:
0:29

Transformer Explainer Really cool interactive tool to learn about the inner workings of a Transformer model. Apparently, it runs a GPT-2 instance locally in the user's browser and allows you to experiment with your own inputs. This is a nice tool to learn more about the different components inside the Transformer and the transformations that occur. Tool:

elvis

121,973 Aufrufe • vor 2 Jahren

Low key World Building™ Reference Guide drop. I've been working on this for a while. Trying to get something unique out there that can help people create and expand worlds. Coming soon. Completely free. Comment, share and bookmark 🖤
0:28

Low key World Building™ Reference Guide drop. I've been working on this for a while. Trying to get something unique out there that can help people create and expand worlds. Coming soon. Completely free. Comment, share and bookmark 🖤

Ivan Flugelman — VVSVS™

11,717 Aufrufe • vor 9 Monaten

Excited to share a new humanoid robot platform we’ve been working on. Berkeley Humanoid is a reliable and low-cost mid-scale research platform for learning-based control. We demonstrate the robot walking on various terrains and dynamic hopping with a simple RL controller.
0:49

Excited to share a new humanoid robot platform we’ve been working on. Berkeley Humanoid is a reliable and low-cost mid-scale research platform for learning-based control. We demonstrate the robot walking on various terrains and dynamic hopping with a simple RL controller.

Qiayuan Liao

80,436 Aufrufe • vor 2 Jahren

hanbin: to give you a quick update on what we’ve been up to lately, you know how our personal color content dropped recently? along with that, we’ve been working hard on a bunch of other things for you guys~ gunwook: we’ve really gone back to our roots and are working super hard. lately it feels like we’re trainees again. we’re taking a lot of lessons, working late nights on music, and growing in so many ways ♡ fighting 🫶
0:26

hanbin: to give you a quick update on what we’ve been up to lately, you know how our personal color content dropped recently? along with that, we’ve been working hard on a bunch of other things for you guys~ gunwook: we’ve really gone back to our roots and are working super hard. lately it feels like we’re trainees again. we’re taking a lot of lessons, working late nights on music, and growing in so many ways ♡ fighting 🫶

𝐬𝐮𝐧𝐠._.𝐦𝐞𝐨𝐰

22,749 Aufrufe • vor 5 Monaten

I'm *very* excited to share something we’ve been working on for a while now... It's a set of AI agents tailor-made for founders and built around each founder's specific workflows. Here’s an early look at some of the things the agents can do:
2:52

I'm *very* excited to share something we’ve been working on for a while now... It's a set of AI agents tailor-made for founders and built around each founder's specific workflows. Here’s an early look at some of the things the agents can do:

Ran Aroussi

30,170 Aufrufe • vor 1 Jahr

Its just a prototype but here Cloudtable - every table gets its own Durable Object for realtime sync, D1 for storage. Runs end-to-end on Cloudflare Developers
0:25

Its just a prototype but here Cloudtable - every table gets its own Durable Object for realtime sync, D1 for storage. Runs end-to-end on Cloudflare Developers

Fayaz Ahmed

20,326 Aufrufe • vor 24 Tagen

Hey everyone, excited to share a sneak-peak into something we’ve been working on Introducing Hype - a mobile app that makes it easy to trade memecoins and crypto Comment HYPE or DM me for early access to the testflight
2:02

Hey everyone, excited to share a sneak-peak into something we’ve been working on Introducing Hype - a mobile app that makes it easy to trade memecoins and crypto Comment HYPE or DM me for early access to the testflight

ravi

42,032 Aufrufe • vor 2 Jahren

We’ve been busy! — Original Stories by Antibody, Aug 30 on — Really excited to see these go out into the world. Telling our own stories, building our own worlds is something Pat and I have been wanting to do for some time now. Live-action, animation, motion graphics: it’s a bit of a mix’n’mash. The first 3 go live on youtube and at the end of the month. Head over to and follow to catch them when they go live.
1:00

We’ve been busy! — Original Stories by Antibody, Aug 30 on — Really excited to see these go out into the world. Telling our own stories, building our own worlds is something Pat and I have been wanting to do for some time now. Live-action, animation, motion graphics: it’s a bit of a mix’n’mash. The first 3 go live on youtube and at the end of the month. Head over to and follow to catch them when they go live.

raoulmarks

13,017 Aufrufe • vor 2 Jahren

I’ve been working hard on my game engine, which supports real-time AI rendering even on low-end computers. Here’s an early alpha preview: it can transform a simple 3D scene into something highly realistic and detailed in real time.
0:59

I’ve been working hard on my game engine, which supports real-time AI rendering even on low-end computers. Here’s an early alpha preview: it can transform a simple 3D scene into something highly realistic and detailed in real time.

Alex

97,673 Aufrufe • vor 27 Tagen