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。

Geez, I'm using voice for everything now. Searches, Slack conversations, even this tweet. Prevents typos and gets ideas down So many tools for this; VoiceInk is what I use. It's open source + compilable from source, runs on device, no subscriptions

Ben Holmes

45,419 subscribers

47,471 次观看 • 5 个月前 •via X (Twitter)

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

Y'all need to use VoiceInk for voice dictation. It's fast, 100% local, open source, compilable from the GitHub repo, and no subscription fee. Replaced Wisprflow with it and it's just as fast and accurate. 🔊 Sound on!

Y'all need to use VoiceInk for voice dictation. It's fast, 100% local, open source, compilable from the GitHub repo, and no subscription fee. Replaced Wisprflow with it and it's just as fast and accurate. 🔊 Sound on!

Ben Holmes

41,468 次观看 • 8 个月前

Fixing plastic AI generated skin is a $100k/month problem. Apps like Enhancor AI use open-source models and ComfyUI workflows as a backend. How do I know this? I built a workflow that clones their core feature and I'm dropping it below for FREE. Same results, no subscriptions. Use it yourself OR build your own app around it. Why pay for open-source tools? 🧵

Fixing plastic AI generated skin is a $100k/month problem. Apps like Enhancor AI use open-source models and ComfyUI workflows as a backend. How do I know this? I built a workflow that clones their core feature and I'm dropping it below for FREE. Same results, no subscriptions. Use it yourself OR build your own app around it. Why pay for open-source tools? 🧵

rob - comfyui

74,528 次观看 • 9 个月前

You can now vibe code a 3D website using this open source model. - Totally free - Runs even locally - Works with any image This workflow is compatible with all tools (Replit, Lovable, Claude Code, etc.) Quick steps below:

You can now vibe code a 3D website using this open source model. - Totally free - Runs even locally - Works with any image This workflow is compatible with all tools (Replit, Lovable, Claude Code, etc.) Quick steps below:

Paul Couvert

140,388 次观看 • 1 年前

I get a lot of questions on what I use for analytics, it's OpenPanel Analytics made by my incredible friend Carl Lindesvärd. If you are looking for a great analytics service, this one is for you! Also 100% open source 🖤

I get a lot of questions on what I use for analytics, it's OpenPanel Analytics made by my incredible friend Carl Lindesvärd. If you are looking for a great analytics service, this one is for you! Also 100% open source 🖤

Pontus Abrahamsson — oss/acc

12,689 次观看 • 1 年前

Many AI tools need subscriptions, Open-source options can be free if self-hosted . Save costs 💰 Explore new tech . Check privacy 🔒.

Many AI tools need subscriptions, Open-source options can be free if self-hosted . Save costs 💰 Explore new tech . Check privacy 🔒.

F.O.L.A

44,921 次观看 • 7 个月前

After staring at Blender's UI for years I started taking it for granted. But now working on a Godot theme I can't help but notice how ridiculously well-designed it is. It's a fucking miracle this is open-source

After staring at Blender's UI for years I started taking it for granted. But now working on a Godot theme I can't help but notice how ridiculously well-designed it is. It's a fucking miracle this is open-source

passivestar

93,477 次观看 • 2 年前

Woow Tencent has released a model 100% open source which is better than Google Translate... And it runs locally on your phone?! - Only 440MB (!!) - 33 languages - On-device translation So we have now a local Google Translate which is running completely offline. They are using AngelSlim which their compression toolkit. That's why the model is so efficient.

Woow Tencent has released a model 100% open source which is better than Google Translate... And it runs locally on your phone?! - Only 440MB (!!) - 33 languages - On-device translation So we have now a local Google Translate which is running completely offline. They are using AngelSlim which their compression toolkit. That's why the model is so efficient.

Paul Couvert

141,760 次观看 • 1 个月前

Now this is truly what Pokémon VR could be. I'm super proud of this even if it's a bit rough and not finished. This is the culmination of everything I've learned so far with voice commands, a custom animation, lots of effects and scripting. I would play the heck out of this game.

Now this is truly what Pokémon VR could be. I'm super proud of this even if it's a bit rough and not finished. This is the culmination of everything I've learned so far with voice commands, a custom animation, lots of effects and scripting. I would play the heck out of this game.

Matt - BMFVR

10,584 次观看 • 5 个月前

🚨🇪🇺🇮🇷 Europe won't even allow U.S bombers to use their airspace - this is wild I'm sure Trump is going to make NATO pay for this. Source: Aaron Rheins YT

🚨🇪🇺🇮🇷 Europe won't even allow U.S bombers to use their airspace - this is wild I'm sure Trump is going to make NATO pay for this. Source: Aaron Rheins YT

Mario Nawfal

309,266 次观看 • 3 个月前

Many people asked, so – I just published ActiveFrame open source on GitHub. It's a stripped version of what we've been using so far at Active Theory – but has all the main ingredients. Still lot of work to do

Many people asked, so – I just published ActiveFrame open source on GitHub. It's a stripped version of what we've been using so far at Active Theory – but has all the main ingredients. Still lot of work to do

Luigi De Rosa

27,165 次观看 • 2 个月前

Introducing step . parts, an open source directory of 12,000+ STEP parts for your next CAD project Many CAD tools like Autodesk have huge closed libraries of standard mechanical and electrical parts The goal is to build an equivalent catalog for the open source CAD community

Introducing step . parts, an open source directory of 12,000+ STEP parts for your next CAD project Many CAD tools like Autodesk have huge closed libraries of standard mechanical and electrical parts The goal is to build an equivalent catalog for the open source CAD community

Jake Fitzgerald

95,626 次观看 • 1 个月前

X_Acc_Flags - for ios The value of ‘Location (accurate)’ is coming from X’s servers, so I have no idea what it was based on Source-Code :

X_Acc_Flags - for ios The value of ‘Location (accurate)’ is coming from X’s servers, so I have no idea what it was based on Source-Code :

 CrazyMind

19,782 次观看 • 7 个月前

🇨🇳🇱🇧 CHINA’S MASSIVE “CHUBBY GIRL” LANDS IN BEIRUT A giant Chinese military plane nicknamed “Chubby Girl” touched down in Beirut this morning — and no, we’re not making that name up. The Xi’an Y-20A can haul up to 66 tons of cargo and is used for everything from troop moves to disaster relief. Source: Open Source Intel

🇨🇳🇱🇧 CHINA’S MASSIVE “CHUBBY GIRL” LANDS IN BEIRUT A giant Chinese military plane nicknamed “Chubby Girl” touched down in Beirut this morning — and no, we’re not making that name up. The Xi’an Y-20A can haul up to 66 tons of cargo and is used for everything from troop moves to disaster relief. Source: Open Source Intel

Mario Nawfal

79,043 次观看 • 1 年前

Pure wickedness. Another village's only drinking water source comes from this river. It's no surprise so many people are suffering from preventable waterborne diseases😭

Pure wickedness. Another village's only drinking water source comes from this river. It's no surprise so many people are suffering from preventable waterborne diseases😭

Jasper Ziggle 🥷🇬🇭 🇺🇸

135,399 次观看 • 1 个月前

this guy built an application that generates 3D models from images AND its open source, runs locally and supports any model

this guy built an application that generates 3D models from images AND its open source, runs locally and supports any model

Om Patel

176,035 次观看 • 3 个月前

Just dropped on HF — NeuTTS Air Next-gen on-device TTS that matches cloud-level quality while staying fully open source. > Real-time speech synthesis on CPU/GPU > 3-second voice cloning, no cloud or data upload > Compact: under 200 MB, runs on mobile and edge devices > Multilingual and expressive > Developed by Neuphonic , optimized for speed and fidelity

Just dropped on HF — NeuTTS Air Next-gen on-device TTS that matches cloud-level quality while staying fully open source. > Real-time speech synthesis on CPU/GPU > 3-second voice cloning, no cloud or data upload > Compact: under 200 MB, runs on mobile and edge devices > Multilingual and expressive > Developed by Neuphonic , optimized for speed and fidelity

steven

72,273 次观看 • 9 个月前

Must-know open-source tools for coders and makers - open source library of 30 toggles - react gamification ui components - saas starter kit nextjs + tanstack - open source google analytics/ mixpanel alternative - design engineered data visualization components

Must-know open-source tools for coders and makers - open source library of 30 toggles - react gamification ui components - saas starter kit nextjs + tanstack - open source google analytics/ mixpanel alternative - design engineered data visualization components

Csaba Kissi

46,712 次观看 • 10 天前

This is AI… For now… Optimus is coming! Source: olivervisualfx

This is AI… For now… Optimus is coming! Source: olivervisualfx

Mario Nawfal

116,154 次观看 • 1 年前

💸 Anyone here juggling multiple AI tools for work? I used to switch between ChatGPT, Claude, and different image/video tools all the time — too many tabs, too many subscriptions, and honestly, it slowed down my workflow. Recently, I tried Rita, and their Seedance 2.0 model is what really stood out 👀 It’s an official ByteDance-powered version, so there’s no waiting queue — everything runs fast and smoothly. What’s even more interesting: • Supports real-person facial recognition • Lets you go from idea → video in one workflow • Low barrier to start — new users can try it for free once Personally, I like generating ideas with ChatGPT, then bringing them into Seedance 2.0 to turn them into actual videos. Feels especially useful for: • Content creators / KOLs working across text, images, and video • Digital workers who want efficiency over juggling multiple tools • AI users who want everything in one place ⚠️ Note: 1. Real-Person Face Feature(Comming Soon) 2. All Generated Videos Will Support Commercial Use. Curious — Do you prefer an all-in-one platform, or separate tools for each task?.... Try it → Want premium subscriptions for less? Check out GamsGo — an easy way to save on popular digital services at a lower cost. 👀 Check it Now👉 #RitaAI #Seedance2

💸 Anyone here juggling multiple AI tools for work? I used to switch between ChatGPT, Claude, and different image/video tools all the time — too many tabs, too many subscriptions, and honestly, it slowed down my workflow. Recently, I tried Rita, and their Seedance 2.0 model is what really stood out 👀 It’s an official ByteDance-powered version, so there’s no waiting queue — everything runs fast and smoothly. What’s even more interesting: • Supports real-person facial recognition • Lets you go from idea → video in one workflow • Low barrier to start — new users can try it for free once Personally, I like generating ideas with ChatGPT, then bringing them into Seedance 2.0 to turn them into actual videos. Feels especially useful for: • Content creators / KOLs working across text, images, and video • Digital workers who want efficiency over juggling multiple tools • AI users who want everything in one place ⚠️ Note: 1. Real-Person Face Feature(Comming Soon) 2. All Generated Videos Will Support Commercial Use. Curious — Do you prefer an all-in-one platform, or separate tools for each task?.... Try it → Want premium subscriptions for less? Check out GamsGo — an easy way to save on popular digital services at a lower cost. 👀 Check it Now👉 #RitaAI #Seedance2

Nihan

19,296 次观看 • 1 个月前