Loading video...

Video Failed to Load

Go Home

Literally, the first transcription model that you can steer with a prompt. Send audio + a prompt. The model does what you ask. Universal 3 Pro from AssemblyAI is the world's first production model to support this. 2026 is off to a great start!

svpino's profile picture

Santiago

447,133 subscribers

10,147 views • 6 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Today I’m launching Swipe -- a new way to steer image models. The idea is simple – start with a prompt, swipe left / right to steer the model towards what you’re thinking of.
0:26

Today I’m launching Swipe -- a new way to steer image models. The idea is simple – start with a prompt, swipe left / right to steer the model towards what you’re thinking of.

Brent 📍SF

288,369 views • 9 months ago

🌴FREE STITCH VTUBER MODEL!!!🎁 #Stitch is the new member that joins the family! celebrating the live action of the movie I wanted to bring you a model that is up to you!. As always I ask you to follow me 🔔 and like 💖 to support the content I give you. You can download the model from the first comment or from my kofi: Thank you very much to all who always support me from KoFi with your donations, this is for you. 😘 #Vtuber #Live2D #VtubeStudio #LiloAndStitchTH #LiloYStitch #LiloAndStitch
0:47

🌴FREE STITCH VTUBER MODEL!!!🎁 #Stitch is the new member that joins the family! celebrating the live action of the movie I wanted to bring you a model that is up to you!. As always I ask you to follow me 🔔 and like 💖 to support the content I give you. You can download the model from the first comment or from my kofi: Thank you very much to all who always support me from KoFi with your donations, this is for you. 😘 #Vtuber #Live2D #VtubeStudio #LiloAndStitchTH #LiloYStitch #LiloAndStitch

Mitsuaki Wagguten ✨ | Artist + Rigger | Live2d 🏅

102,114 views • 1 year ago

Just added Google Gemini 3.1 Pro to Base44 Gemini 3.1 Pro is really good for gaming and design workflows, and it's fast. If that's what you're building, this is your model. + we're adding something a lot of you were asking for - you can now pick your AI model from the very first prompt. No more starting with a default and switching halfway through. Checkout this Pokemon game I built with the new model, and let me know what you're building
1:11

Just added Google Gemini 3.1 Pro to Base44 Gemini 3.1 Pro is really good for gaming and design workflows, and it's fast. If that's what you're building, this is your model. + we're adding something a lot of you were asking for - you can now pick your AI model from the very first prompt. No more starting with a default and switching halfway through. Checkout this Pokemon game I built with the new model, and let me know what you're building

Maor Shlomo

24,630 views • 6 months ago

here's how to make ultra realistic AI podcasts: - generate first frames with nano banana pro (prompt is key here) - upscale images - animate with VEO 3 that's it. it literally takes just a few minutes to go from ‘slop’ to ultra-realistic ai videos you can fix voices with minimax or in post production and it'll look indistinguishable from a real video the only difference is the prompt and the workflow
0:37

here's how to make ultra realistic AI podcasts: - generate first frames with nano banana pro (prompt is key here) - upscale images - animate with VEO 3 that's it. it literally takes just a few minutes to go from ‘slop’ to ultra-realistic ai videos you can fix voices with minimax or in post production and it'll look indistinguishable from a real video the only difference is the prompt and the workflow

MAX

16,530 views • 7 months ago

Something we discovered by accident: what happens if we start Genie 3 from a video and a completely unrelated prompt? Turns out the model really, really wants to make it work, to the point where it emulates itself. The prompt in this one is about a trex on a tropical island.
0:26

Something we discovered by accident: what happens if we start Genie 3 from a video and a completely unrelated prompt? Turns out the model really, really wants to make it work, to the point where it emulates itself. The prompt in this one is about a trex on a tropical island.

Jakob Bauer

685,569 views • 1 year ago

This is a big day. Meta is open-sourcing AudioCraft. You can now generate incredible music and sounds with a single prompt. It includes the most performant Generative AI Model (audio) on the market, the "Llama" of Audio. The research framework contains the weights and code of these models: ▸ MusicGen: controllable text-to-music model. ▸ AudioGen: text-to-sound model. ▸ EnCodec: high fidelity neural audio codec. ▸ Multi Band Diffusion: An EnCodec compatible decoder using diffusion. This is going to tremendously speed up audio research 👏
0:28

This is a big day. Meta is open-sourcing AudioCraft. You can now generate incredible music and sounds with a single prompt. It includes the most performant Generative AI Model (audio) on the market, the "Llama" of Audio. The research framework contains the weights and code of these models: ▸ MusicGen: controllable text-to-music model. ▸ AudioGen: text-to-sound model. ▸ EnCodec: high fidelity neural audio codec. ▸ Multi Band Diffusion: An EnCodec compatible decoder using diffusion. This is going to tremendously speed up audio research 👏

Lior Alexander

231,665 views • 3 years ago

this is what one prompt looks like now a detective, five locations, fog you can taste, and a low cello under all of it made on Qwen Create with the wan3.0 model prompt below, go break it:
0:30

this is what one prompt looks like now a detective, five locations, fog you can taste, and a low cello under all of it made on Qwen Create with the wan3.0 model prompt below, go break it:

Muhammad Ayan

56,259 views • 2 days ago

Introducing Stable Audio 2.0 – a new model capable of producing high-quality, full tracks with coherent musical structure up to three minutes long at 44.1 kHz stereo from a single prompt. Explore the model and start creating for free at: Read the blogpost here: (1/3)
3:00

Introducing Stable Audio 2.0 – a new model capable of producing high-quality, full tracks with coherent musical structure up to three minutes long at 44.1 kHz stereo from a single prompt. Explore the model and start creating for free at: Read the blogpost here: (1/3)

Stability AI

457,892 views • 2 years ago

We have a new obsession: printing calibration butterflies on our INDX. Otto the calibration butterfly is the model we recommend starting with. As the name suggests, we designed this model to verify that your printer is properly calibrated after assembly, while leaving you with a cool first print you can show off. 🦋
0:27

We have a new obsession: printing calibration butterflies on our INDX. Otto the calibration butterfly is the model we recommend starting with. As the name suggests, we designed this model to verify that your printer is properly calibrated after assembly, while leaving you with a cool first print you can show off. 🦋

Prusa3D

13,586 views • 1 month ago

This game was vibe coded in 2 days - INSANE how far we’ve come Model used: muranyi-3: - Prompts: 39 - Token usage: $90 (so far) - Starter prompt: First world prompt for the game: “Create the Foundation for a third-person 3D high medieval fantasy set in a mountainous open plain with a distant castle landmark.” First prompt to make the character: "Okay, I wanna start building a new game and just figuring out a really awesome character to start. A hooded purple wizard with a world-class third-person player and movement system. Decoupled camera versus walking direction, with jogging and walking in all directions with the camera behind the player.” Tip from our best builders: Start with 3 to 4 prompts just planning. Tell the AI what your game is, the core loop, the vibe, the genre. Don't rush into building yet. Let the model scope it out with you first. Once that first output lands, that's when you start iterating. Tweak the animations, shape the world, adjust the UI, dial in the details. The best games on Tesana aren't built in one prompt. They're built in one conversation.
1:08

This game was vibe coded in 2 days - INSANE how far we’ve come Model used: muranyi-3: - Prompts: 39 - Token usage: $90 (so far) - Starter prompt: First world prompt for the game: “Create the Foundation for a third-person 3D high medieval fantasy set in a mountainous open plain with a distant castle landmark.” First prompt to make the character: "Okay, I wanna start building a new game and just figuring out a really awesome character to start. A hooded purple wizard with a world-class third-person player and movement system. Decoupled camera versus walking direction, with jogging and walking in all directions with the camera behind the player.” Tip from our best builders: Start with 3 to 4 prompts just planning. Tell the AI what your game is, the core loop, the vibe, the genre. Don't rush into building yet. Let the model scope it out with you first. Once that first output lands, that's when you start iterating. Tweak the animations, shape the world, adjust the UI, dial in the details. The best games on Tesana aren't built in one prompt. They're built in one conversation.

Tesana - Make games with AI

553,280 views • 2 months ago

This is what it looks like to drive right next to a Model Y with literally no-one in the car. Pretty cool. This Model Y is driving itself from the end of the Giga Texas production line to its designated lane at the outbound lot. Note: This is not the quicksilver Model Y that drove itself completely autonomously to a customer in Austin today. This Ultra Red Model Y below will be shipped elsewhere.
0:34

This is what it looks like to drive right next to a Model Y with literally no-one in the car. Pretty cool. This Model Y is driving itself from the end of the Giga Texas production line to its designated lane at the outbound lot. Note: This is not the quicksilver Model Y that drove itself completely autonomously to a customer in Austin today. This Ultra Red Model Y below will be shipped elsewhere.

Sawyer Merritt

192,488 views • 1 year ago

Kimi K2.7 Code is the first open-weight model you can select in the GitHub Copilot model picker. What does that mean for you? Burke Holland explains how this low-cost, high-performance model gives you more choice and flexibility in your workflow. ▶️
2:55

Kimi K2.7 Code is the first open-weight model you can select in the GitHub Copilot model picker. What does that mean for you? Burke Holland explains how this low-cost, high-performance model gives you more choice and flexibility in your workflow. ▶️

GitHub

125,271 views • 1 month ago

Introducing Prompt-to-leaderboard (P2L): a real-time LLM leaderboard tailored exactly to your use case! P2L trains an LLM to generate "prompt-specific" leaderboards, so you can input a prompt and get a leaderboard specifically for that prompt. The model is trained on the 2M human preference votes from Chatbot Arena. P2L Highlights: 🔹Instant leaderboard for any prompt 🗿 🔹Optimal model routing (hit #1 on Chatbot Arena in Jan 2025 with 1395 score 🧏) 🔹Fine-grained model strength & weakness analysis 🤓 Check out our demo and thread below for more details!
1:06

Introducing Prompt-to-leaderboard (P2L): a real-time LLM leaderboard tailored exactly to your use case! P2L trains an LLM to generate "prompt-specific" leaderboards, so you can input a prompt and get a leaderboard specifically for that prompt. The model is trained on the 2M human preference votes from Chatbot Arena. P2L Highlights: 🔹Instant leaderboard for any prompt 🗿 🔹Optimal model routing (hit #1 on Chatbot Arena in Jan 2025 with 1395 score 🧏) 🔹Fine-grained model strength & weakness analysis 🤓 Check out our demo and thread below for more details!

Arena.ai

122,525 views • 1 year ago

Good question thanks Ani. Here's a video that gives a sense of the answer here about the effect of prompting: - in the first part, the model is just babbling with no prompt in context - at the end, we add a prompt for taking money out of a pouch (generalizing to the wallet)
0:44

Good question thanks Ani. Here's a video that gives a sense of the answer here about the effect of prompting: - in the first part, the model is just babbling with no prompt in context - at the end, we add a prompt for taking money out of a pouch (generalizing to the wallet)

Pete Florence

30,136 views • 7 days ago

Nano Banana Pro 2 is live in Hedra – DAY 0 🔥 4x faster. Cheaper. Better. Real text rendering. Pro-level editing. One model. We wrote the prompt guide so you don't have to figure it out. First 1,000 followers get the prompt guide. Comment "Hedra NB2" and we’ll send it instantly.
0:37

Nano Banana Pro 2 is live in Hedra – DAY 0 🔥 4x faster. Cheaper. Better. Real text rendering. Pro-level editing. One model. We wrote the prompt guide so you don't have to figure it out. First 1,000 followers get the prompt guide. Comment "Hedra NB2" and we’ll send it instantly.

Hedra

210,803 views • 6 months ago

I just watched Grok Build create this Starship + Mechazilla model directly inside Blender from a single prompt I asked it to model Starship with Super Heavy, the upper stage, Raptor 3 engines, heat-shield tiles, detailed components and Mechazilla Then I watched it take control of my laptop, work inside Blender and build the entire thing right in front of me I refined a few details afterward, but this was the first version it produced from that one prompt A model like this used to take hours or even days of manual work....now i can describe what I want and literally watch it take shape in real time Grok Build is insanely helpful....you can literally give it a task and let it run autonomously on your laptop
0:27

I just watched Grok Build create this Starship + Mechazilla model directly inside Blender from a single prompt I asked it to model Starship with Super Heavy, the upper stage, Raptor 3 engines, heat-shield tiles, detailed components and Mechazilla Then I watched it take control of my laptop, work inside Blender and build the entire thing right in front of me I refined a few details afterward, but this was the first version it produced from that one prompt A model like this used to take hours or even days of manual work....now i can describe what I want and literally watch it take shape in real time Grok Build is insanely helpful....you can literally give it a task and let it run autonomously on your laptop

X Freeze

34,275 views • 13 days ago

Introducing Architect I am releasing the first iteration of a model which generates optimized project plans with a single prompt. Think Linear or JIRA, but for agents. A living model that learns from the gossiping network, and gets smarter with every interaction.
0:25

Introducing Architect I am releasing the first iteration of a model which generates optimized project plans with a single prompt. Think Linear or JIRA, but for agents. A living model that learns from the gossiping network, and gets smarter with every interaction.

Varun

56,906 views • 5 months ago

Voice Design v3 is here. Create any voice you can imagine with a prompt. We’ve rebuilt the underlying Voice Design model to deliver higher quality and broader expressive range. Generate production-ready voices in 70+ languages with support for hundreds of localized accents.
0:52

Voice Design v3 is here. Create any voice you can imagine with a prompt. We’ve rebuilt the underlying Voice Design model to deliver higher quality and broader expressive range. Generate production-ready voices in 70+ languages with support for hundreds of localized accents.

ElevenLabs

153,990 views • 1 year ago

Model 6 & 7 is the ICT universal Model that' works on every Time Frame !!! The Accuracy is on a different level entirely You need to see this to the end. Retweet it.. Bookmark it
5:15

Model 6 & 7 is the ICT universal Model that' works on every Time Frame !!! The Accuracy is on a different level entirely You need to see this to the end. Retweet it.. Bookmark it

Quinn

46,675 views • 2 months ago