正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Vibecoding is great for prototypes. But what about building real components you can plug into production systems? We used Claude Opus 4.6 to build a custom TTS plugin (Kitten TTS) and hook it into Vision Agents. Here's how it works 🧵

Stream

12,278 subscribers

3,552,195 次观看 • 3 个月前 •via X (Twitter)

教育科学技术

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

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:

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

73,415 次观看 • 1 年前

We are thrilled to announce a massive update to our Text-To-Speech (TTS) model for Twi! We are confident it is the best Twi TTS there now! Give it a listen and see if you agree! Sign up for our API and incorporate it into your products today! 🙏🏾 (link in bio)

We are thrilled to announce a massive update to our Text-To-Speech (TTS) model for Twi! We are confident it is the best Twi TTS there now! Give it a listen and see if you agree! Sign up for our API and incorporate it into your products today! 🙏🏾 (link in bio)

Ghana Natural Language Processing (NLP)

94,204 次观看 • 2 年前

My Figma to AI Code plugin is live Turn your designs into production-level code generated by Claude AI. Create React components, SwiftUI prototypes, HTML+CSS pages, Tailwind styles with custom prompts. Preview for responsiveness and export fully working code to Cursor and Xcode. It's free with your own API keys

My Figma to AI Code plugin is live Turn your designs into production-level code generated by Claude AI. Create React components, SwiftUI prototypes, HTML+CSS pages, Tailwind styles with custom prompts. Preview for responsiveness and export fully working code to Cursor and Xcode. It's free with your own API keys

Meng To

76,017 次观看 • 1 年前

feedback is the bottleneck for building with AI Inflight fixes that now designers can get structured feedback on their prototypes which loops back into Claude/Codex as next steps how it works in ~60s 👇

feedback is the bottleneck for building with AI Inflight fixes that now designers can get structured feedback on their prototypes which loops back into Claude/Codex as next steps how it works in ~60s 👇

Ridd 🤿

31,965 次观看 • 1 个月前

Text-to-speech is moving way too fast. Just a few days ago, I tweeted about PersonaPlex-7B, NVIDIA's new open source TTS ( And today, Qwen just open-sourced Qwen3-TTS 🤯 It’s a revolutionary text-to-speech model built for control. Not just about generating speech, but about shaping how it sounds directly from language. You can guide the pace, the tone, and the expressiveness straight from text, without touching audio graphs or hand-tuning parameters. That’s the real shift! What makes Qwen3-TTS stand out is how practical it already is: → voice cloning from just a few seconds of audio → voice creation without any reference sample → support for 10 languages out of the box → end-to-end latency down to ~97ms → works in both streaming and non-streaming setups The models come in two sizes (0.6B and 1.7B), so you can trade off quality and hardware cost depending on your setup. You can work with curated voices, designed voices, or cloned ones, and it integrates cleanly with vLLM for production use. It also ships as a simple Python package you can pip install. If you’re building real-time voice systems, this removes a lot of friction! 100% free and open source. I put the repo in the 🧵↓

Text-to-speech is moving way too fast. Just a few days ago, I tweeted about PersonaPlex-7B, NVIDIA's new open source TTS ( And today, Qwen just open-sourced Qwen3-TTS 🤯 It’s a revolutionary text-to-speech model built for control. Not just about generating speech, but about shaping how it sounds directly from language. You can guide the pace, the tone, and the expressiveness straight from text, without touching audio graphs or hand-tuning parameters. That’s the real shift! What makes Qwen3-TTS stand out is how practical it already is: → voice cloning from just a few seconds of audio → voice creation without any reference sample → support for 10 languages out of the box → end-to-end latency down to ~97ms → works in both streaming and non-streaming setups The models come in two sizes (0.6B and 1.7B), so you can trade off quality and hardware cost depending on your setup. You can work with curated voices, designed voices, or cloned ones, and it integrates cleanly with vLLM for production use. It also ships as a simple Python package you can pip install. If you’re building real-time voice systems, this removes a lot of friction! 100% free and open source. I put the repo in the 🧵↓

Charly Wargnier

59,144 次观看 • 5 个月前

People get Framer components, but don't know how to use them. So I'm giving away 50+ free components with how-to videos. It shows exactly how to plug it right into your project. Here's how you can grab: 1. Follow wayden 2. Like & Reply "FC" I'll DM you all

People get Framer components, but don't know how to use them. So I'm giving away 50+ free components with how-to videos. It shows exactly how to plug it right into your project. Here's how you can grab: 1. Follow wayden 2. Like & Reply "FC" I'll DM you all

wayden

45,970 次观看 • 8 个月前

Stop what you're doing. Claude Opus 4.6 just released and it's incredible Both OpenClaw and Claude Code are 10x better with it It's now my daily driver for both In this video I cover EVERYTHING you need to know about Opus, and how to get the most out of it:

Stop what you're doing. Claude Opus 4.6 just released and it's incredible Both OpenClaw and Claude Code are 10x better with it It's now my daily driver for both In this video I cover EVERYTHING you need to know about Opus, and how to get the most out of it:

Alex Finn

71,388 次观看 • 5 个月前

Claude Code sub-agents is probably the easiest way to build complex, custom agentic systems. Not just for code, but for anything you can imagine. Watch me build a multi-agent deep research system with Claude Code subagents. Chain subagents with /commands for reliability.

Claude Code sub-agents is probably the easiest way to build complex, custom agentic systems. Not just for code, but for anything you can imagine. Watch me build a multi-agent deep research system with Claude Code subagents. Chain subagents with /commands for reliability.

elvis

190,039 次观看 • 11 个月前

We ran Anthropic Claude Opus 4.7 against our hardest benchmark - complex concurrency bugs that require multi-step reasoning. Almost 20% better than previous generations. Here's what we did to get it production-ready and what you can take from it for your own stack 👇

We ran Anthropic Claude Opus 4.7 against our hardest benchmark - complex concurrency bugs that require multi-step reasoning. Almost 20% better than previous generations. Here's what we did to get it production-ready and what you can take from it for your own stack 👇

CodeRabbit

10,896 次观看 • 2 个月前

Wow Anthropic just released Claude Code for Web/Mobile, and it changes everything Now AI Agents can build apps for you 24/7 Here's your full beginner's guide to building an AI agent army that works for you all day (trust me you want to bookmark this one)

Wow Anthropic just released Claude Code for Web/Mobile, and it changes everything Now AI Agents can build apps for you 24/7 Here's your full beginner's guide to building an AI agent army that works for you all day (trust me you want to bookmark this one)

Alex Finn

160,698 次观看 • 8 个月前

Can AI agents really manage other agents? Most of us can't even get one AI agent to really work well. But it works in Replit ⠕ v3. For real. And it's so cool. I had it do a 2.75 hour autonomous security audit. One agent managing other AI agents. Here's how it worked:🧵

Can AI agents really manage other agents? Most of us can't even get one AI agent to really work well. But it works in Replit ⠕ v3. For real. And it's so cool. I had it do a 2.75 hour autonomous security audit. One agent managing other AI agents. Here's how it worked:🧵

Jason ✨👾SaaStr.Ai✨ Lemkin

14,102 次观看 • 9 个月前

How is the Web changing due to AI? This visit to TinyFish yesterday goes deeply into just how. TinyFish makes a new kind of web browser. One that is started virtually. It is like a Google Chrome in the cloud. But it is very smart, can read and use any website, and your AI agents can talk to it. Here we talk about what it all means for business and the future of robots, brain computer interfaces, and AI glasses. It lets you build systems that can look at MANY websites at the same time and build new kinds of apps to do all sorts of new things.

How is the Web changing due to AI? This visit to TinyFish yesterday goes deeply into just how. TinyFish makes a new kind of web browser. One that is started virtually. It is like a Google Chrome in the cloud. But it is very smart, can read and use any website, and your AI agents can talk to it. Here we talk about what it all means for business and the future of robots, brain computer interfaces, and AI glasses. It lets you build systems that can look at MANY websites at the same time and build new kinds of apps to do all sorts of new things.

Robert Scoble

16,341 次观看 • 6 个月前

Pi0 from Physical Intelligence is one of the best generalist Vision-Language-Action (VLA) models for robotics (and predecessor of Pi0.5). 🧵 Here's how it works + how you can fine-tune it on your own robot for a simple task:

Pi0 from Physical Intelligence is one of the best generalist Vision-Language-Action (VLA) models for robotics (and predecessor of Pi0.5). 🧵 Here's how it works + how you can fine-tune it on your own robot for a simple task:

Ilia

32,956 次观看 • 10 个月前

Testing the new Claude Opus 4.6 vs. Gemini 3 Pro on Sider’s Artifacts! 🚀 I love turning complex articles into "interactive reading" to boost my efficiency. With the new Claude Opus 4.6 out, I ran a head-to-head comparison. Here's the breakdown: 1/ Gemini 3 Pro: The "Gamified" Experience 🎮 The interface is incredibly clean and minimalist, but the real magic is the interactivity. It’s highly engaging and fun—honestly, it feels like playing a game. It turns passive reading into an active exploration where you actually enjoy clicking through the content. 2/ Claude Opus 4.6: The "High-Tech" Analyst 🧠 The visuals are dazzling—it has a super cool, futuristic vibe. But beyond the look, the breakdown is insanely detailed. It dissects complex concepts from multiple granular angles. It feels like examining the DNA of the article. The Verdict: Choose Gemini 3 Pro for a clean layout with a fun, game-like vibe. Choose Claude Opus 4.6 for "cooler" visuals and superior, microscopic content breakdown. Both are game-changers for "chewing" through difficult papers! 📖✨ Which style do you prefer?

Testing the new Claude Opus 4.6 vs. Gemini 3 Pro on Sider’s Artifacts! 🚀 I love turning complex articles into "interactive reading" to boost my efficiency. With the new Claude Opus 4.6 out, I ran a head-to-head comparison. Here's the breakdown: 1/ Gemini 3 Pro: The "Gamified" Experience 🎮 The interface is incredibly clean and minimalist, but the real magic is the interactivity. It’s highly engaging and fun—honestly, it feels like playing a game. It turns passive reading into an active exploration where you actually enjoy clicking through the content. 2/ Claude Opus 4.6: The "High-Tech" Analyst 🧠 The visuals are dazzling—it has a super cool, futuristic vibe. But beyond the look, the breakdown is insanely detailed. It dissects complex concepts from multiple granular angles. It feels like examining the DNA of the article. The Verdict: Choose Gemini 3 Pro for a clean layout with a fun, game-like vibe. Choose Claude Opus 4.6 for "cooler" visuals and superior, microscopic content breakdown. Both are game-changers for "chewing" through difficult papers! 📖✨ Which style do you prefer?

Ace

109,206 次观看 • 5 个月前

one of the biggest hurdles in computer vision is that the front end actually matters. you can’t just build models and call it a product. that’s why we’re building Manako. we see it as a “control plane” for visual intelligence. where data, policies, and operators meet. where vision stops being research and starts having real impact in the physical world. this is built for people running real systems. operators who can do 1,000x more when vision is packaged as a real ai product from a dev perspective, we’re already 2 months ahead of plan. now the focus is polish, usability, and connecting it directly into the subnet. build with vision.

one of the biggest hurdles in computer vision is that the front end actually matters. you can’t just build models and call it a product. that’s why we’re building Manako. we see it as a “control plane” for visual intelligence. where data, policies, and operators meet. where vision stops being research and starts having real impact in the physical world. this is built for people running real systems. operators who can do 1,000x more when vision is packaged as a real ai product from a dev perspective, we’re already 2 months ahead of plan. now the focus is polish, usability, and connecting it directly into the subnet. build with vision.

Max

10,537 次观看 • 5 个月前

I made a plugin that turns figma designs to code using Claude AI Works with HTML, CSS, Tailwind, SwiftUI, Flutter, etc. This is production level code and you can enter custom prompts like "make it functional" or "add hover states". Oh and it's free. You can use your api keys.

I made a plugin that turns figma designs to code using Claude AI Works with HTML, CSS, Tailwind, SwiftUI, Flutter, etc. This is production level code and you can enter custom prompts like "make it functional" or "add hover states". Oh and it's free. You can use your api keys.

Meng To

220,706 次观看 • 1 年前

OpenAI launched Agents in ChatGPT today. It’s great for consumers who want to automate tasks in ChatGPT. But what if you want to build features powered by the same tools? I dropped put same demo prompt into Director, our web agent builder, to generate a script for that. Director enables anyone to build software powered by web agents. You prompt it once, and get a deterministic web agent that you can integrate into your application. It's a great starting point for building powerful buttons that do work FOR your users.

OpenAI launched Agents in ChatGPT today. It’s great for consumers who want to automate tasks in ChatGPT. But what if you want to build features powered by the same tools? I dropped put same demo prompt into Director, our web agent builder, to generate a script for that. Director enables anyone to build software powered by web agents. You prompt it once, and get a deterministic web agent that you can integrate into your application. It's a great starting point for building powerful buttons that do work FOR your users.

Paul Klein IV

32,299 次观看 • 1 年前

x402 is finally catching fire, but how do you actually build with it? In this video you'll learn how to build custom x402 agents in just 5 minutes. 🔥 The app is Open Source and gets you started with both a client and a merchant agent, everything you need to build your own agents. I show you how to extend it to sell EBooks for 1USDC.

x402 is finally catching fire, but how do you actually build with it? In this video you'll learn how to build custom x402 agents in just 5 minutes. 🔥 The app is Open Source and gets you started with both a client and a merchant agent, everything you need to build your own agents. I show you how to extend it to sell EBooks for 1USDC.

nader dabit

173,459 次观看 • 8 个月前

This Claude 3.7 UI workflow is awesome And many vibe coders not aware of it: 1. Have Claude 3.7 to design whole UI screen by screen 2. Ask it to make a plan, break down into components 3. Turn into actual project By having Claude focus on just UI generation, it does a great job You can build beautiful UI without shadcn If you want to learn more about vibe coding beyond basics, join my community here: (also get free access to 10xCoder.Dev)

This Claude 3.7 UI workflow is awesome And many vibe coders not aware of it: 1. Have Claude 3.7 to design whole UI screen by screen 2. Ask it to make a plan, break down into components 3. Turn into actual project By having Claude focus on just UI generation, it does a great job You can build beautiful UI without shadcn If you want to learn more about vibe coding beyond basics, join my community here: (also get free access to 10xCoder.Dev)

Jason Zhou

745,638 次观看 • 1 年前