Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Mapping speech to actions in real time. Everything is processed on the robot. Sound on!

uavster's profile picture

Nacho Mellado

2,721 subscribers

108,471 Aufrufe • vor 2 Jahren •via X (Twitter)

Wissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

11 Kommentare

Profilbild von Nacho Mellado
Nacho Melladovor 1 Jahr

You can now join the waitlist to keep the project on your radar:

Profilbild von 𝕏 Kuee replyguy/acc
𝕏 Kuee replyguy/accvor 2 Jahren

that nod was awesome

Profilbild von Nacho Mellado
Nacho Melladovor 2 Jahren

Thank you! I’ll be working on more expressions next, as it starts understanding more subtle stuff. Stay tuned!

Profilbild von Jeff Caldwell
Jeff Caldwellvor 2 Jahren

This is awesome!!!

Profilbild von Nacho Mellado
Nacho Melladovor 2 Jahren

Thank you! I have plans to open source. Stay tuned 😊

Profilbild von Ben Schulz
Ben Schulzvor 2 Jahren

Would get about 100 million more views if you could get it to pass butter.

Profilbild von Nacho Mellado
Nacho Melladovor 2 Jahren

I understood this reference thanks to @LuxArrived 😅

Profilbild von ͓̽𝕁𝕡
͓̽𝕁𝕡vor 2 Jahren

Real life Wall-E. Awesome work, would love to get my hands on a kit to learn robotics!

Profilbild von Nacho Mellado
Nacho Melladovor 2 Jahren

Thanks! Planning to open source and distribute as a DIY kit (or links to parts). Gotta converge to a production version, as some parts are custom-made, and figure out logistics. Would you mind if I dm you in the future to learn more about your expectations?

Profilbild von Ysqander
Ysqandervor 2 Jahren

Pretty cool. Is this with the new Arduino AI chip?

Profilbild von Nacho Mellado
Nacho Melladovor 2 Jahren

Thanks! It has an Arduino-based board for low-level control. ML models run on a Jetson Nano from NVIDIA.

Ähnliche Videos

This robot now carries its own brain — a Qualcomm Dragonwing™ QCS6490 mounted right on its back. No more waiting on the cloud to make sense of the world. Everything processed on the spot, in real time. That's SR Agentic at work.
0:25

This robot now carries its own brain — a Qualcomm Dragonwing™ QCS6490 mounted right on its back. No more waiting on the cloud to make sense of the world. Everything processed on the spot, in real time. That's SR Agentic at work.

Strike Robot

24,948 Aufrufe • vor 4 Tagen

My speech on the steps of the Supreme Court. With better sound this time.
6:31

My speech on the steps of the Supreme Court. With better sound this time.

Jennifer Sey

63,735 Aufrufe • vor 5 Monaten

U.S. Ambassador to NATO Matthew Whitaker: “President Trump is reevaluating everything, NATO involvement, support for Europe in Ukraine, and all U.S. actions. Everything is on the table.”
0:37

U.S. Ambassador to NATO Matthew Whitaker: “President Trump is reevaluating everything, NATO involvement, support for Europe in Ukraine, and all U.S. actions. Everything is on the table.”

Open Source Intel

82,718 Aufrufe • vor 3 Monaten

The attack on free speech is real.
0:56

The attack on free speech is real.

The Matt Walsh Show

12,700 Aufrufe • vor 11 Monaten

Voice‑driven, real‑time arbitrary action generation😁 Using external voice commands, G1 is directly controlled to generate a wide range of actions in real time. This video was recorded in a single take, with on‑site audio recording. Because the actions are autonomously generated by AI in real time, there may be slight latency, and the smoothness of the movements may be somewhat reduced.
2:24

Voice‑driven, real‑time arbitrary action generation😁 Using external voice commands, G1 is directly controlled to generate a wide range of actions in real time. This video was recorded in a single take, with on‑site audio recording. Because the actions are autonomously generated by AI in real time, there may be slight latency, and the smoothness of the movements may be somewhat reduced.

Unitree

29,017,924 Aufrufe • vor 1 Monat

Next generation (DV5) robot in the wild… Sound on for a narrated look
4:57

Next generation (DV5) robot in the wild… Sound on for a narrated look

Elliot Servais, MD, FACS

35,295 Aufrufe • vor 2 Jahren

The Secret Cartel Intel Network on X Explained. What's crazy is the Cartel Community Tracking Everything in Real Time. All Source News
4:06

The Secret Cartel Intel Network on X Explained. What's crazy is the Cartel Community Tracking Everything in Real Time. All Source News

Julian Dorey

21,279 Aufrufe • vor 1 Monat

$AIVA Token is Live. Contract: 0x6B9a58A87A05c4fdCC87b73C52B868bc6996E8de Welcome to the age of Personalized User Interfaces. AIVA is The Composable Interface Protocol. AI that dynamically composing UIs from your intent and executing on-chain actions in real time. → Time to own your interface. Welcome to AIVA.
3:18

$AIVA Token is Live. Contract: 0x6B9a58A87A05c4fdCC87b73C52B868bc6996E8de Welcome to the age of Personalized User Interfaces. AIVA is The Composable Interface Protocol. AI that dynamically composing UIs from your intent and executing on-chain actions in real time. → Time to own your interface. Welcome to AIVA.

aiva

14,527 Aufrufe • vor 1 Jahr

we’re lying on the moon. here are a few models glued together — speech to text (OpenAI whisper) to text (OpenAI gpt-3.5-turbo) to speech () — to recreate samantha from “her” in real-time.
1:18

we’re lying on the moon. here are a few models glued together — speech to text (OpenAI whisper) to text (OpenAI gpt-3.5-turbo) to speech () — to recreate samantha from “her” in real-time.

harley turan

506,190 Aufrufe • vor 3 Jahren

Bill Maher is right: Defending free speech means defending speech you hate. Thanks for the shout out Bill Maher on Real Time with Bill Maher.
1:22

Bill Maher is right: Defending free speech means defending speech you hate. Thanks for the shout out Bill Maher on Real Time with Bill Maher.

FIRE

585,384 Aufrufe • vor 1 Jahr

"Everything I've learned... has brought me to The Wild Robot." Director Chris Sanders looks back on the legacy that led him to Roz. #TheWildRobotMovie is back in theaters and now streaming only on Peacock.
3:46

"Everything I've learned... has brought me to The Wild Robot." Director Chris Sanders looks back on the legacy that led him to Roz. #TheWildRobotMovie is back in theaters and now streaming only on Peacock.

DreamWorks Animation

15,970 Aufrufe • vor 1 Jahr

Self driving real-time mapping
0:24

Self driving real-time mapping

Gleb Kuznetsov

29,068 Aufrufe • vor 1 Jahr

internetVin on the broken fundamentals in Toronto. I'm learning in real time. Thank you for everything so far.
4:59

internetVin on the broken fundamentals in Toronto. I'm learning in real time. Thank you for everything so far.

internetVin

13,195 Aufrufe • vor 1 Jahr

Words are words. Violence is violence. Conflating the two, licences the idea that real violence is a legitimate response to free speech. If there has been a rise in hate in Canada, it is not because we fail to police speech. It is because we fail to police actions.
1:38

Words are words. Violence is violence. Conflating the two, licences the idea that real violence is a legitimate response to free speech. If there has been a rise in hate in Canada, it is not because we fail to police speech. It is because we fail to police actions.

Shuv Majumdar

47,388 Aufrufe • vor 8 Monaten

Speech Carries Its Own Hidden Geometry in Phase Space Speech is usually shown as a waveform of amplitude changing in time. Phase-space reconstruction gives a different view by pairing the signal with a delayed version of itself, so the voice is seen as a path rather than just a trace. On the left is the raw sound signal. On the right is the geometric structure formed by rhythm, syllables, and emphasis as the voice unfolds. * Real human speech data from the public GitHub repository voxserv/audio_quality_testing_samples, using the 16 kHz file test01_20s.wav.
0:30

Speech Carries Its Own Hidden Geometry in Phase Space Speech is usually shown as a waveform of amplitude changing in time. Phase-space reconstruction gives a different view by pairing the signal with a delayed version of itself, so the voice is seen as a path rather than just a trace. On the left is the raw sound signal. On the right is the geometric structure formed by rhythm, syllables, and emphasis as the voice unfolds. * Real human speech data from the public GitHub repository voxserv/audio_quality_testing_samples, using the 16 kHz file test01_20s.wav.

Mathelirium

18,725 Aufrufe • vor 3 Monaten

DID YOU KNOW: There's an official Spanish Streamer Awards broadcast? Streaming live all night over on Quackity's second channel, everything on the main broadcast is being translated to Spanish in real-time 🤩 👈
0:44

DID YOU KNOW: There's an official Spanish Streamer Awards broadcast? Streaming live all night over on Quackity's second channel, everything on the main broadcast is being translated to Spanish in real-time 🤩 👈

The Streamer Awards

212,277 Aufrufe • vor 7 Monaten

3/ Robot use - 🥇1st place Combining Claude computer use with a robot arm and have the LLM perform real world actions Amazon robot controlled just by uploading the instruction manual to Claude
2:46

3/ Robot use - 🥇1st place Combining Claude computer use with a robot arm and have the LLM perform real world actions Amazon robot controlled just by uploading the instruction manual to Claude

Alex Reibman 🖇️

60,741 Aufrufe • vor 1 Jahr

Introducing Toggle for OpenClaw🦞 For the first time ever your Agent can see everything you do on the web. This is real-time context on your work day. Toggle AI analyses all browser actions, clicks, work, meetings and documents -> into AI context of what Projects / Tasks / Tools you are working on. Check it out👇
0:26

Introducing Toggle for OpenClaw🦞 For the first time ever your Agent can see everything you do on the web. This is real-time context on your work day. Toggle AI analyses all browser actions, clicks, work, meetings and documents -> into AI context of what Projects / Tasks / Tools you are working on. Check it out👇

PeLpA

52,282 Aufrufe • vor 4 Monaten