Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

1-Click Vibevoice-Realtime for ALL machines Finally a Realtime TTS that is ACTUALLY realtime, thanks to its tiny size! (0.5B params) This video is from my Windows machine, recorded in realtime. All you need is around 2.5GB VRAM, it even works on Macs!

cocktailpeanut's profile picture

cocktail peanut

32,991 subscribers

37,149 Aufrufe • vor 8 Monaten •via X (Twitter)

Wissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Overworld Waypoint 1.5 Low VRAM 1 Click Launcher Found this gem yesterday at the top of Huggingface leaderboard. This recording is running on my Windows PC, realtime. Not sped up. 1X speed. Crazy. Try with 1-click launcher (Requires NVIDIA around 8GB VRAM)
3:40

Overworld Waypoint 1.5 Low VRAM 1 Click Launcher Found this gem yesterday at the top of Huggingface leaderboard. This recording is running on my Windows PC, realtime. Not sped up. 1X speed. Crazy. Try with 1-click launcher (Requires NVIDIA around 8GB VRAM)

cocktail peanut

12,394 Aufrufe • vor 3 Monaten

This is crazy, I can talk to OpenAI's realtime API, and it'll respond back with voice, and then help call Codex to help me code! Got curious about Codex and its realtime integration, and found codex's feature flag `realtime_conversation` integrated for the codex app-server. How it works: - launch codex app-server with realtime - connect a client to realtime through WebRTC voice connection - Codex app-server is also attached on the side - talk to realtime - realtime decides whether coding is needed, and responds back with events - Codex app-server takes these events and runs codex agent turns - codex writes code like your codex cli exp Keep in mind OpenAI hasn't released this officially, they're still actively working on it, I just created a fork. This is a completely new UX than the usual chat interface for agentic coding. For example, when the agent responds back in voice, it's actually faster for me to read the response, and I don't actually find voice response that useful unless it does so in the background. But image realtime working in the background, you can talk to it, realtime keeps track of the different agents working on your tasks and your status. More to come on demo side, i'll make a more polished version and include voice, but thought this was cool to share. You can see in the responses the distinction between my voice input, realtime response, and realtime calling Codex to do work!
0:28

This is crazy, I can talk to OpenAI's realtime API, and it'll respond back with voice, and then help call Codex to help me code! Got curious about Codex and its realtime integration, and found codex's feature flag `realtime_conversation` integrated for the codex app-server. How it works: - launch codex app-server with realtime - connect a client to realtime through WebRTC voice connection - Codex app-server is also attached on the side - talk to realtime - realtime decides whether coding is needed, and responds back with events - Codex app-server takes these events and runs codex agent turns - codex writes code like your codex cli exp Keep in mind OpenAI hasn't released this officially, they're still actively working on it, I just created a fork. This is a completely new UX than the usual chat interface for agentic coding. For example, when the agent responds back in voice, it's actually faster for me to read the response, and I don't actually find voice response that useful unless it does so in the background. But image realtime working in the background, you can talk to it, realtime keeps track of the different agents working on your tasks and your status. More to come on demo side, i'll make a more polished version and include voice, but thought this was cool to share. You can see in the responses the distinction between my voice input, realtime response, and realtime calling Codex to do work!

Matthew Lam

17,674 Aufrufe • vor 2 Monaten

This actually makes Gemma 4 26B-4A usable for a coding agent @ 72tk/s on my MacBook Pro M1 Max. This video is realtime, running completely locally.
0:57

This actually makes Gemma 4 26B-4A usable for a coding agent @ 72tk/s on my MacBook Pro M1 Max. This video is realtime, running completely locally.

Kyle Howells

119,153 Aufrufe • vor 1 Monat

Just dropped my entry for the Freebeat AI Realtime Creator Challenge! 🔥 Made this entire music video live in Realtime. Watching the AI sync visuals to the beat as the track played. From concept to final cut in one seamless flow. This is the future of music video creation.
1:00

Just dropped my entry for the Freebeat AI Realtime Creator Challenge! 🔥 Made this entire music video live in Realtime. Watching the AI sync visuals to the beat as the track played. From concept to final cut in one seamless flow. This is the future of music video creation.

Sharon Riley

60,085 Aufrufe • vor 23 Tagen

Super excited to share this realtime canvas inspired by Tomáš Procházka This is built using flux 2 klein realtime powered by fal! Github Code link 👇🏽 Thanks for the inspiration Tomáš Procházka ! Note: The video isn't sped up or trimmed while processing, what you are seeing is the speed / latency you'll see when you run this project! PS: My poor drawing skills are exposed in this video 😂
0:47

Super excited to share this realtime canvas inspired by Tomáš Procházka This is built using flux 2 klein realtime powered by fal! Github Code link 👇🏽 Thanks for the inspiration Tomáš Procházka ! Note: The video isn't sped up or trimmed while processing, what you are seeing is the speed / latency you'll see when you run this project! PS: My poor drawing skills are exposed in this video 😂

1LittleCoder💻

30,041 Aufrufe • vor 5 Monaten

One of the very interesting challenges with AI models for robotics is the constraints you're working with when deploying models that need to run in realtime on-device.
1:05

One of the very interesting challenges with AI models for robotics is the constraints you're working with when deploying models that need to run in realtime on-device.

AI at Meta

47,377 Aufrufe • vor 1 Jahr

Voice is the OG modality. So excited for image inputs, function calling & MCP support in the Realtime API GA! `gpt-realtime` is a lot more natural and expressive, and every time a SOTA voice model is released, you know what I gotta do... Here is the new voice Marin, on KaraokeBench! scores 3 out of 7 again from me
10:41

Voice is the OG modality. So excited for image inputs, function calling & MCP support in the Realtime API GA! `gpt-realtime` is a lot more natural and expressive, and every time a SOTA voice model is released, you know what I gotta do... Here is the new voice Marin, on KaraokeBench! scores 3 out of 7 again from me

swyx

51,219 Aufrufe • vor 11 Monaten

If you want to know what is ailing our politics, this is a big, big part of it. Watch David French join Bill Maher and Dan Jones on #RealTime HBO:
1:14

If you want to know what is ailing our politics, this is a big, big part of it. Watch David French join Bill Maher and Dan Jones on #RealTime HBO:

Real Time with Bill Maher

64,300 Aufrufe • vor 2 Monaten

Adelabu storms Jogor Centre to engage APC stakeholders across all 351 wards grassroots connection, realtime consultation, and leadership in action. This is how you build momentum. 🔥🔥🔥
2:00

Adelabu storms Jogor Centre to engage APC stakeholders across all 351 wards grassroots connection, realtime consultation, and leadership in action. This is how you build momentum. 🔥🔥🔥

shevy

10,913 Aufrufe • vor 3 Monaten

It’s like Bloomberg meets the world monitor Elie Habib I put Virat Singh financial dataset api to cross reference all the realtime data to make realtime financial decisions and executions. Got multiple agents already inside Convex style and even got Grok with xAI feed This is one of the most powerful GitHub’s I have ever forked in my life brother
0:22

It’s like Bloomberg meets the world monitor Elie Habib I put Virat Singh financial dataset api to cross reference all the realtime data to make realtime financial decisions and executions. Got multiple agents already inside Convex style and even got Grok with xAI feed This is one of the most powerful GitHub’s I have ever forked in my life brother

8Bit🦞

20,161 Aufrufe • vor 5 Monaten

I've been working with Jakub Červený to integrate our #GaussianSplatting renderer with #threejs, I created this infinite portal demo as a feature showcase! You can play with it live here This is captured in realtime on my mac, here's how it works: 🧵
1:09

I've been working with Jakub Červený to integrate our #GaussianSplatting renderer with #threejs, I created this infinite portal demo as a feature showcase! You can play with it live here This is captured in realtime on my mac, here's how it works: 🧵

🌈 George Corney

101,648 Aufrufe • vor 2 Jahren

This new demo is running on the Dreamcast using the new raylib port. The system really is quite capable and is rendering this 3D scan along with multiple realtime point lights moving around it. This demo would’ve blown my mind in 1999.
0:39

This new demo is running on the Dreamcast using the new raylib port. The system really is quite capable and is rendering this 3D scan along with multiple realtime point lights moving around it. This demo would’ve blown my mind in 1999.

Brielle Garcia

135,711 Aufrufe • vor 2 Jahren

Stacy is my FAVORITE new housewife across all franchises right now. This is so needed - a reality star figuring out the ropes in realtime like this. Love her down. Refill her flute for 3 seasons minimum! 🥂😂 #rhop
0:37

Stacy is my FAVORITE new housewife across all franchises right now. This is so needed - a reality star figuring out the ropes in realtime like this. Love her down. Refill her flute for 3 seasons minimum! 🥂😂 #rhop

CourtneyRevolution 💡

195,663 Aufrufe • vor 1 Jahr

I've been building voice agents for the last 6mo and I think the chat-supervisor pattern is a game changer. Stitched model (STT-LLM-TTS) is slow, but realtime audio models aren't (yet) as smart as text. This has the best of both worlds. Here's how it works:
4:41

I've been building voice agents for the last 6mo and I think the chat-supervisor pattern is a game changer. Stitched model (STT-LLM-TTS) is slow, but realtime audio models aren't (yet) as smart as text. This has the best of both worlds. Here's how it works:

Noah MacCallum

73,462 Aufrufe • vor 1 Jahr

This entire music video was created live while the music was playing. 🤯 I just entered the Freebeat AI Realtime Creator Challenge. The video also shows my complete workflow—from idea to beat-synced visuals—all generated in one seamless realtime session. Seeing every scene synchronize instantly with the soundtrack feels like editing in the future. Try it yourself: Mira Sterling Eshal Natalia #freebeatRealtime
2:38

This entire music video was created live while the music was playing. 🤯 I just entered the Freebeat AI Realtime Creator Challenge. The video also shows my complete workflow—from idea to beat-synced visuals—all generated in one seamless realtime session. Seeing every scene synchronize instantly with the soundtrack feels like editing in the future. Try it yourself: Mira Sterling Eshal Natalia #freebeatRealtime

Jessica Collins

881,344 Aufrufe • vor 22 Tagen

Let's talk numbers, the original 2D video is 7.3Mb; the needed data to play it in this 3D volumetric way, which allows you to change the camera position and focus realtime is just an extra 11Mb.
0:32

Let's talk numbers, the original 2D video is 7.3Mb; the needed data to play it in this 3D volumetric way, which allows you to change the camera position and focus realtime is just an extra 11Mb.

patricio gonzalez vivo

116,842 Aufrufe • vor 2 Jahren

CCP IS WATCHING THE AMERICAN WAR MACHINE: UNDERSTANDING OUR TACTICS "They are filming everything we do with their eyes in the sky, in realtime. They are working to understand how we fight, how we refuel, resupply, all of it"
3:39

CCP IS WATCHING THE AMERICAN WAR MACHINE: UNDERSTANDING OUR TACTICS "They are filming everything we do with their eyes in the sky, in realtime. They are working to understand how we fight, how we refuel, resupply, all of it"

Jack Posobiec

77,840 Aufrufe • vor 5 Monaten