Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

If you're looking for a weekend project, how about training your own text-to-speech model from scratch on your own GPU, and then running it on any device's CPU? We just open-sourced the entire Pocket TTS training stack: data pipeline, recipes, and evals. It learns pretty damn fast: ~15k steps:... babbling starts turning into words ~50k steps: it reads anything you type (WER under 1%) ~200k steps: the voice stops sounding synthetic On a beefy consumer GPU, that's a week of training. On eight H100s: 10-20 hours. A TTS training run will cost you less than $200 if you rent your hardware, and an order of magnitude less if you just pay for power. Some things we'd love to see people try: - Train it in your own language (a few hundred hours of speech gets you surprisingly far). - Add new features to Pocket TTS (Emotion tags? Make it sing?). - Beat us at our own game: make it faster and smaller. Show us what you build! We'll highlight the best models and new languages for the whole community to enjoy. Pocket TTS has already found many use cases, from reading for people with visual impairments to making NPCs in video games talk, and we're sure there's much more to do with it! Here's an example of a Czech Pocket TTS. Try just asking your favorite agent to find data and apply the method, and you can have your own. Get started:show more

kyutai

27,833 subscribers

106,234 views • 1 month ago •via X (Twitter)

Science & Technology Education Health & Wellness

Anya Rossi• Live Now

Private livecam show

34 Comments

pulsatingGenius1 month ago

Thanks for releasing the training code it matches what i was doing. only issue was mine kept blabbering and eos token prediction had issues

0xShugo1 month ago

PocketTTS --- the fastest model in the audio.cpp Arena!

Josh Whiton1 month ago

Love Pocket, but can you train the English model to say "live" with a hard "i" when appropriate? In my experience, it incorrectly says it with a soft 'i' 90% of the time.

Spletni zvočnik 🔊1 month ago

Anyone interested in doing Slovenian?

Owen Song1 month ago

would really love to see audio tags on a kyutai model one day!

Bastien Gares1 month ago

Vous êtes des crack 🫡

sour kiwi1 month ago

crazy release! thank you

The Tech Fuse1 month ago

Training TTS on one GPU and running it on CPU is a killer open stack.

Nathan Roll1 month ago

you guys are cracked-- keep it up!

Shahar Nechmad1 month ago

Wow. Under $200 to train a useful TTS model from scratch is way more accessible than I expected. How much clean speech data do you need before it starts sounding natural in a new language, not just reading it correctly?

Mena Botrous1 month ago

i like the open approach here. training recipes plus cpu inference makes this a practical tts project.

cetusian1 month ago

does the 50k step number hold for a language with way less data? romanian is my usual wall

Habtamu Asefa1 month ago

You made my day 😁

Ryan Edkins1 month ago

Running inference on any device's CPU is the part I care about, that's the difference between a demo and something you'd actually ship inside a product.

rehan1 month ago

love it!!!

Bart S.1 month ago

That's cool 🔥

RG1 month ago

thats what i was waiting for so long

Vishal Singh 🥑1 month ago

Amazing, thanks 🔥🙌

Ekrem1 month ago

There goes my $300

Adrian Scott | A.I. + Business Upscaling1 month ago

exciting, thanks!

semonic1 month ago

Thank you You made my day

Jikku Jose1 month ago

So are you saying any language TTS can be built with this stack? Isn’t the tokenizer dependent on language?

Rudra Satani1 month ago

The step-count breakdown is the useful part: WER under 1% at ~50k but not sounding synthetic until ~200k means intelligibility and prosody are separate curves, and WER alone says you're done long before you are.

bright1 month ago

thank you 🙏🏼

Prosper1 month ago

Finally the wait is over!

Sebastian Buzdugan1 month ago

cpu latency is mostly memory bound, so model size decides whether this ships

Zaky Vids1 month ago

@kyutai_labs I am not very tech savy and I am trying to learn python but it will be quite sometime before I can do these things is there any way for you guys to release a version or some way where we can train our own voice in the browser like via browser inference

Ayush1 month ago

thanks for this 🤑

영웅 (woogie)1 month ago

< $200 for a full TTS train is the part I keep thinking about. that's the 200k-step run on rented H100s?

Ivan Fioravanti ᯅ1 month ago

Amazing 🤩 thanks thanks thanks!

刘朝 Zhao Liu1 month ago

Open-sourcing recipes and evals turns TTS from an API dependency into a reproducible lab experiment. The next frontier is voice quality, latency, and footprint together; WER under 1% is one axis when an agent must speak on CPU in real time.

Michael1 month ago

Hi guys, I decided to train this model on my MacBook, and the README invited a bug‑fix PR because it wasn't supported out of the box, so I opened one after making it possible to train on my MacBook, but the maintainer closed it, saying that was an oversight since they can't support platforms they have no hardware to test. I hold no grudge; his comment ended warmly, and I just want to share it here in case anyone wants to use it to train on a Mac as well.

rasmus1 month ago

i might try!

HopeCCCCCCCCCCCCCCCC1 month ago

under $200 for a full run is way lower than i would have guessed

Related Videos

“don’t train your own model” is common ai advice. it's wrong. your token bill's the proof. today, we’re excited to launch castform into open preview. castform is the easiest way for you to train your own model, on your own data. open-weights models are performant and much cheaper. when trained on your task & proprietary data, they beat closed models. the thing standing between you and that was weeks of plumbing & years of ml expertise. with castform, model training is as simple as prompt engineering. castform bring your agent traces or raw corpora. castform turns it into training data, picks the right algorithmic recipes, manages gpus, and gives you an ide to watch and chat with your model as it learns. see what you can build with castform👇

“don’t train your own model” is common ai advice. it's wrong. your token bill's the proof. today, we’re excited to launch castform into open preview. castform is the easiest way for you to train your own model, on your own data. open-weights models are performant and much cheaper. when trained on your task & proprietary data, they beat closed models. the thing standing between you and that was weeks of plumbing & years of ml expertise. with castform, model training is as simple as prompt engineering. castform bring your agent traces or raw corpora. castform turns it into training data, picks the right algorithmic recipes, manages gpus, and gives you an ide to watch and chat with your model as it learns. see what you can build with castform👇

girish

463,474 views • 4 months ago

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 views • 8 months ago

We just made the Warp API and MCP completely free. Most HR platforms make you sit through a sales call and a questionnaire just to reach your own data. We think that's backwards. You can pull your entire company and employee data, time off, compensation, payroll, IT, basically anything in Warp. Build your own dashboards. Connect Warp to your internal systems. Run your own automations on top of your data. We built this because our customers are technical and AI-native. They don't want to stare at a dashboard. They want to build on top of their data. Legacy platforms silo it on purpose, and the API, when it exists at all, is a pricey add-on buried behind a sales process. We shipped the API eight weeks ago, and some of our top customers have already built real tools on top of Warp. Today we're removing the last barrier to doing that. If you're an AI-native founder, exec, CIO, or Chief People Officer who's been duct taping this together, the API and MCP are now included free on most plans. On Enterprise, a small fee unlocks the more powerful version with uptime SLAs, webhooks, and audit logs. Your data should be yours. Excited to see what you build with it.

We just made the Warp API and MCP completely free. Most HR platforms make you sit through a sales call and a questionnaire just to reach your own data. We think that's backwards. You can pull your entire company and employee data, time off, compensation, payroll, IT, basically anything in Warp. Build your own dashboards. Connect Warp to your internal systems. Run your own automations on top of your data. We built this because our customers are technical and AI-native. They don't want to stare at a dashboard. They want to build on top of their data. Legacy platforms silo it on purpose, and the API, when it exists at all, is a pricey add-on buried behind a sales process. We shipped the API eight weeks ago, and some of our top customers have already built real tools on top of Warp. Today we're removing the last barrier to doing that. If you're an AI-native founder, exec, CIO, or Chief People Officer who's been duct taping this together, the API and MCP are now included free on most plans. On Enterprise, a small fee unlocks the more powerful version with uptime SLAs, webhooks, and audit logs. Your data should be yours. Excited to see what you build with it.

Ayush S

730,614 views • 4 months ago

I built a service desk agent using ElevenLabs’ new Conversational AI Agents feature. Watch the video to see how responsive it is! Previously, I used ElevenLabs for cloning my voice and used my generated voice for narrations in some of my youtube videos. This feature takes elevenlabs' voice AI to a whole new level! It simplifies systems that used to require separate TTS (text-to-speech) and STT (speech-to-text) processes for both sides of the conversation. Now, it’s much simpler! Create your own agent here What will you create with this?

I built a service desk agent using ElevenLabs’ new Conversational AI Agents feature. Watch the video to see how responsive it is! Previously, I used ElevenLabs for cloning my voice and used my generated voice for narrations in some of my youtube videos. This feature takes elevenlabs' voice AI to a whole new level! It simplifies systems that used to require separate TTS (text-to-speech) and STT (speech-to-text) processes for both sides of the conversation. Now, it’s much simpler! Create your own agent here What will you create with this?

Melvin Vivas

27,722 views • 1 year ago

You can now just text DoorDash and let it order for you. It’s proactive, learns from your repeat orders, and helps you find the best deals and new spots. Just tell it what you want without any extra setup. Ask it to reorder your usual, or add it to a group text to collect everyone’s orders. You can even send a photo of your fridge and it’ll tell you what ingredients you’re missing for a recipe you want to make and deliver the ingredients to your doorstep. We believe agents are a new app paradigm and are building for that future at DoorDash AI Research, with a lot more to come. This feature is in beta in the US, would love for you to let us know what you think! Waitlist:

You can now just text DoorDash and let it order for you. It’s proactive, learns from your repeat orders, and helps you find the best deals and new spots. Just tell it what you want without any extra setup. Ask it to reorder your usual, or add it to a group text to collect everyone’s orders. You can even send a photo of your fridge and it’ll tell you what ingredients you’re missing for a recipe you want to make and deliver the ingredients to your doorstep. We believe agents are a new app paradigm and are building for that future at DoorDash AI Research, with a lot more to come. This feature is in beta in the US, would love for you to let us know what you think! Waitlist:

Andy Fang

1,129,210 views • 12 days ago

Voice agents are awkward, and everyone notices: You ask a question. The agent thinks. You wait. And wait... Nobody wants this. I'd rather talk to a person. If your model's response time is over 300ms, you won't make it. Unfortunately, most text-to-speech models can't get anywhere close to that. I want you to take a look at the latest model released by : TTS-1.5. I built a simple voice agent using the model so you can see it in action and test it on your computer. You'll find the repository link below. The latency numbers of this model are wild: • Max model → under 250ms • Mini model → under 130ms That's 4x faster than prior generations and faster than human response times!

Voice agents are awkward, and everyone notices: You ask a question. The agent thinks. You wait. And wait... Nobody wants this. I'd rather talk to a person. If your model's response time is over 300ms, you won't make it. Unfortunately, most text-to-speech models can't get anywhere close to that. I want you to take a look at the latest model released by : TTS-1.5. I built a simple voice agent using the model so you can see it in action and test it on your computer. You'll find the repository link below. The latency numbers of this model are wild: • Max model → under 250ms • Mini model → under 130ms That's 4x faster than prior generations and faster than human response times!

Santiago

69,462 views • 8 months ago

🚨Governor DeSantis applauds the Florida House for addressing property taxes but says his plan is NOT going to happen in regular session, but he will call a SPECIAL SESSION. “It's going to get done and you guys are going to be able to go to the polls and be able to vote something that's really meaningful. I just think at the end of the day, your home is your castle. You either own it or you don't, right? And if you have to keep paying tax to the government your whole life just to live on your own property, do you really own it then if they can take it back from you if you don't pay?”

🚨Governor DeSantis applauds the Florida House for addressing property taxes but says his plan is NOT going to happen in regular session, but he will call a SPECIAL SESSION. “It's going to get done and you guys are going to be able to go to the polls and be able to vote something that's really meaningful. I just think at the end of the day, your home is your castle. You either own it or you don't, right? And if you have to keep paying tax to the government your whole life just to live on your own property, do you really own it then if they can take it back from you if you don't pay?”

Chris Nelson 🏝️🇺🇸

31,667 views • 7 months ago

New video series: How to Amiko In this series, we’ll walk you through how to use the Amiko site, from onboarding your twin to exploring everything live inside our Beta. Episode 2: Train Your Twin Once you create your social and behavioral twin, shape what it knows about you and how it understands you in Training Chats. Training your twin builds depth: this is where you give it your personal traits, memories, preferences, history. This is where it learns specific, personal information about you, always controlled by you. Training teaches your twin more about you, beyond the social and behavioral layer, and keeps you in control of the data the twin has access to. Without training, your twin will act like the oldest child in a large family. With training, it will know you were the oldest of five siblings, and any additional details you wish to disclose.

New video series: How to Amiko In this series, we’ll walk you through how to use the Amiko site, from onboarding your twin to exploring everything live inside our Beta. Episode 2: Train Your Twin Once you create your social and behavioral twin, shape what it knows about you and how it understands you in Training Chats. Training your twin builds depth: this is where you give it your personal traits, memories, preferences, history. This is where it learns specific, personal information about you, always controlled by you. Training teaches your twin more about you, beyond the social and behavioral layer, and keeps you in control of the data the twin has access to. Without training, your twin will act like the oldest child in a large family. With training, it will know you were the oldest of five siblings, and any additional details you wish to disclose.

AMIKO

18,976 views • 11 months ago

What if your voice AI could interrupt you the moment it figured out your question - sometimes even before you finished asking it? Last week, I sat down with Neil, CEO of Gradium and co-founder of Kyutai , to talk about the future of speech-to-speech models and why he believes today's cascaded voice systems will soon look "archaic and brittle." Some highlights from our conversation: 🎯 How Kyutai built Moshi—a full duplex conversational AI with "negative latency"—in 6 months with just 4-6 people (while big tech teams had 10-20x the resources) 🧠 Why speech-to-speech models lose intelligence compared to their text counterparts (and what's being done about it) 📱 Pocket TTS: The first voice cloning model that runs on your phone's CPU—not GPU, CPU 🤖 Why robotics and spatial audio represent the next frontier (hint: current voice systems completely break in these environments) 👶 The efficiency gap: Babies learn to speak fluently from <5,000 hours of audio. Current models train on millions of hours. We're doing something wrong. My favorite vision from Neil? The first truly contrarian AI that interrupts you mid-sentence to tell you why you're wrong. Not just more natural conversation—but actually useful for testing ideas and playing devil's advocate. Full episode and detailed blog post linked in the comments 👇 What's your take - will speech-to-speech replace cascaded systems, or will modularity keep cascaded architectures dominant even as naturalness improves?

What if your voice AI could interrupt you the moment it figured out your question - sometimes even before you finished asking it? Last week, I sat down with Neil, CEO of Gradium and co-founder of Kyutai , to talk about the future of speech-to-speech models and why he believes today's cascaded voice systems will soon look "archaic and brittle." Some highlights from our conversation: 🎯 How Kyutai built Moshi—a full duplex conversational AI with "negative latency"—in 6 months with just 4-6 people (while big tech teams had 10-20x the resources) 🧠 Why speech-to-speech models lose intelligence compared to their text counterparts (and what's being done about it) 📱 Pocket TTS: The first voice cloning model that runs on your phone's CPU—not GPU, CPU 🤖 Why robotics and spatial audio represent the next frontier (hint: current voice systems completely break in these environments) 👶 The efficiency gap: Babies learn to speak fluently from <5,000 hours of audio. Current models train on millions of hours. We're doing something wrong. My favorite vision from Neil? The first truly contrarian AI that interrupts you mid-sentence to tell you why you're wrong. Not just more natural conversation—but actually useful for testing ideas and playing devil's advocate. Full episode and detailed blog post linked in the comments 👇 What's your take - will speech-to-speech replace cascaded systems, or will modularity keep cascaded architectures dominant even as naturalness improves?

Brooke Hopkins

13,000 views • 7 months ago

GPT 5.6 SOL IS HERE! How to run your personal + business life with GPT 5.6 Sol + Codex (full 49 min masterclass) We tested it for 30 days and the video it's the CLEAREST look at the FUTURE of work: Here's what's possible once you set it up: 1. Your inbox becomes cards every morning, each with a summary and a reply drafted in your own voice. Y 2. Your Slack, meeting notes, and company updates can turn into one daily feed with a clear next action. It learns what you care about over time and rewrites its own prompts to get sharper. 3. You can give your agent its own email address, so your other tools and even your team's Slack bot email it directly and it just handles things. 4. You can have it watch you do a task once and turn it into a skill it repeats forever. 5. You can set a long goal and walk away. You can have it run for 20 hours straight, and fine-tune your own models, something that was out of reach for non-engineers 12 months ago. How to start: Open Codex, give it access to your computer, and ask it to suggest things it could do for you based on how you already work. Full episode on The Startup Ideas Podcast (SIP) 🧃 (thanks Dan Shipper for sharing your entire workflow and review of GPT 5.6) Start with one boring task, get it working, and build from there. You'll learn exactly how to make something similar. GPT 5.6 Sol is impressive. Sol (according to openAI benchmarks) is the best coding model out right now. It set a new state of the art on Terminal-Bench 2.1 at 88.8%, and its "ultra mode" hits 91.9%, beating Claude Opus 4.8, Fable 5, and even Mythos 5 this masterclass is 100% free, like always. For more The Startup Ideas Podcast (SIP) 🧃 Watch

GPT 5.6 SOL IS HERE! How to run your personal + business life with GPT 5.6 Sol + Codex (full 49 min masterclass) We tested it for 30 days and the video it's the CLEAREST look at the FUTURE of work: Here's what's possible once you set it up: 1. Your inbox becomes cards every morning, each with a summary and a reply drafted in your own voice. Y 2. Your Slack, meeting notes, and company updates can turn into one daily feed with a clear next action. It learns what you care about over time and rewrites its own prompts to get sharper. 3. You can give your agent its own email address, so your other tools and even your team's Slack bot email it directly and it just handles things. 4. You can have it watch you do a task once and turn it into a skill it repeats forever. 5. You can set a long goal and walk away. You can have it run for 20 hours straight, and fine-tune your own models, something that was out of reach for non-engineers 12 months ago. How to start: Open Codex, give it access to your computer, and ask it to suggest things it could do for you based on how you already work. Full episode on The Startup Ideas Podcast (SIP) 🧃 (thanks Dan Shipper for sharing your entire workflow and review of GPT 5.6) Start with one boring task, get it working, and build from there. You'll learn exactly how to make something similar. GPT 5.6 Sol is impressive. Sol (according to openAI benchmarks) is the best coding model out right now. It set a new state of the art on Terminal-Bench 2.1 at 88.8%, and its "ultra mode" hits 91.9%, beating Claude Opus 4.8, Fable 5, and even Mythos 5 this masterclass is 100% free, like always. For more The Startup Ideas Podcast (SIP) 🧃 Watch

GREG ISENBERG

156,806 views • 3 months ago

I just inscribed the CRAWL module to Termina! You can now crawl the OCI to find Bitmap districts with reinscriptions or children! GO TO: TRY: > crawl bitmap This will take a long time, but don't worry! I already did it for you. Bring your own data: Let's work together to keep this dataset updated. You can crawl ranges (for example, of your own bitmaps) and submit a pull request. It took me about 7 hours to crawl all of bitmap with about 15 windows open each running on a range. It would've taken about 10 days with just one window! Definitely some improvements that can be made in performance for the future, but so now we have at least made it possible! And it is mind-blowing what we will be able to do with this data. Stay tuned later this week to find out how we can piggyback off this data to build powerful tools on-chain!

I just inscribed the CRAWL module to Termina! You can now crawl the OCI to find Bitmap districts with reinscriptions or children! GO TO: TRY: > crawl bitmap This will take a long time, but don't worry! I already did it for you. Bring your own data: Let's work together to keep this dataset updated. You can crawl ranges (for example, of your own bitmaps) and submit a pull request. It took me about 7 hours to crawl all of bitmap with about 15 windows open each running on a range. It would've taken about 10 days with just one window! Definitely some improvements that can be made in performance for the future, but so now we have at least made it possible! And it is mind-blowing what we will be able to do with this data. Stay tuned later this week to find out how we can piggyback off this data to build powerful tools on-chain!

bitoshi blockamoto 🧱 BITMAP 🟧

23,686 views • 1 year ago

here's what we built at the Sarvam x GrowthX hackathon! > an interactive, voice-first game where you learn new languages through everyday conversations > our insight was that not everyone needs to master a language - they only need a few sentences, useful in everyday situations > you can choose your region (like Bengaluru), and the level of difficulty according to which your interactions are based > it then guides you on what to say in a given situation, like booking an auto > it grades on you how well you spoke, what you missed, progressively getting difficult with more levels didn't make it to the top 15, but hey we had fun :) Sarvam for Developers's TTS-STT stack is definitely some of the best in the world currently.

here's what we built at the Sarvam x GrowthX hackathon! > an interactive, voice-first game where you learn new languages through everyday conversations > our insight was that not everyone needs to master a language - they only need a few sentences, useful in everyday situations > you can choose your region (like Bengaluru), and the level of difficulty according to which your interactions are based > it then guides you on what to say in a given situation, like booking an auto > it grades on you how well you spoke, what you missed, progressively getting difficult with more levels didn't make it to the top 15, but hey we had fun :) Sarvam for Developers's TTS-STT stack is definitely some of the best in the world currently.

Parth

54,530 views • 2 months ago

Stop Duffing Your Wedges !! If you try and apply what you do in the long game to a 50-yard pitch shot you are in trouble. When it comes to this yardage and under it’s about finesse We need a different motion to tap into our feel. If you are patient with the transition, allowing your arms to drop this will not only help you soften things up and feel more but it will also help you use the leading edge and bounce through the turf. This feel of TURN, DROP and CATCH it with the body has been game changing for our students and my own game. #golftips #golf

Stop Duffing Your Wedges !! If you try and apply what you do in the long game to a 50-yard pitch shot you are in trouble. When it comes to this yardage and under it’s about finesse We need a different motion to tap into our feel. If you are patient with the transition, allowing your arms to drop this will not only help you soften things up and feel more but it will also help you use the leading edge and bounce through the turf. This feel of TURN, DROP and CATCH it with the body has been game changing for our students and my own game. #golftips #golf

Me and My Golf

114,808 views • 1 year ago

Introducing DuoNano🐸 Become the star of your own epic language adventure. -Just upload a pic of yourself or any character you like and dive right into the story in our Adventure Mode🐸 -One second you're wandering a lively market in Mexico City, the next you're uncovering some ancient temple in Kyoto, and through it all, it's still totally you in the mix. -Use your camera to upload pictures with Visual Vocabulary to learn how to say anything in a new language! Our visual model will detect the objects in the image and explain it to you in whatever language you select. -If you want to test your mettle, try the conversation practice tutor to test your skills against a native speaking AI. Try DN today. You're gonna love it. Link Below 👇

Introducing DuoNano🐸 Become the star of your own epic language adventure. -Just upload a pic of yourself or any character you like and dive right into the story in our Adventure Mode🐸 -One second you're wandering a lively market in Mexico City, the next you're uncovering some ancient temple in Kyoto, and through it all, it's still totally you in the mix. -Use your camera to upload pictures with Visual Vocabulary to learn how to say anything in a new language! Our visual model will detect the objects in the image and explain it to you in whatever language you select. -If you want to test your mettle, try the conversation practice tutor to test your skills against a native speaking AI. Try DN today. You're gonna love it. Link Below 👇

bone

40,423 views • 1 year ago

I just inscribed the FILTER module to Termina! You can now SEARCH and FILTER bitmap content and fields, powered by CRAWL and the WORLDTREE data! Go to: Try > filter content bitoshi blockamoto > filter type audio > filter address skynet > filter (type image) (timestamp 2023) > filter help Make sure you have the latest snapshot from WORLDTREE, or have run your own CRAWL and WORLDTREE (warning - these take a long time! I'll be looking into ways to make running these more accessible). Bring your own data: The help menu is your friend here! Please try as much as you can. You can filter single values, or multiple things at the same time with parenthesis. I've found so many inscriptions on Bitmap this way! Please have fun with it, and if you make a new inscription on Bitmap, be sure to run "crawl bitmap [range]" and "worldtree bitmap full [range]" on your district so you can search & filter, and make sure to add it to github via a pull request. This way we can share the latest snapshot data. If you want to build your own dataset, try using CRAWL and WORLDTREE. I warn you though, the CRAWL module especially will take days if you don't have 18 windows open each scanning a range (in which case it will take about 8 hours). The WORLDTREE module takes about 8 hours with just one window open, so probably can accellerate the speed with multiple windows. This is why it's easier to piggyback off the github snapshots, but in the future these scans will be baked into the fabric of the operating system, automatically updated by users exploration and constantly scanning in the background (if turned on). Maybe there's some synergy to be had in this regard with ZmAKin_1981.🟧 extension to make sure we always have latest data. Anyway, that's all for now folks! Please share your findings.

I just inscribed the FILTER module to Termina! You can now SEARCH and FILTER bitmap content and fields, powered by CRAWL and the WORLDTREE data! Go to: Try > filter content bitoshi blockamoto > filter type audio > filter address skynet > filter (type image) (timestamp 2023) > filter help Make sure you have the latest snapshot from WORLDTREE, or have run your own CRAWL and WORLDTREE (warning - these take a long time! I'll be looking into ways to make running these more accessible). Bring your own data: The help menu is your friend here! Please try as much as you can. You can filter single values, or multiple things at the same time with parenthesis. I've found so many inscriptions on Bitmap this way! Please have fun with it, and if you make a new inscription on Bitmap, be sure to run "crawl bitmap [range]" and "worldtree bitmap full [range]" on your district so you can search & filter, and make sure to add it to github via a pull request. This way we can share the latest snapshot data. If you want to build your own dataset, try using CRAWL and WORLDTREE. I warn you though, the CRAWL module especially will take days if you don't have 18 windows open each scanning a range (in which case it will take about 8 hours). The WORLDTREE module takes about 8 hours with just one window open, so probably can accellerate the speed with multiple windows. This is why it's easier to piggyback off the github snapshots, but in the future these scans will be baked into the fabric of the operating system, automatically updated by users exploration and constantly scanning in the background (if turned on). Maybe there's some synergy to be had in this regard with ZmAKin_1981.🟧 extension to make sure we always have latest data. Anyway, that's all for now folks! Please share your findings.

bitoshi blockamoto 🧱 BITMAP 🟧

16,472 views • 1 year ago

Do you know the pain of wanting to send a client an invoice, then you have to open your laptop, find your invoice document and start typing it in Or if you're one of those who use Canva for it You need an invoice and you need it in 3 minutes so you can close a deal I GOT YOU, I will show you how I made an invoice for my company using AI and then created a Webapp for it, the WebApp installs like an android app and I can open it and use anytime without internet. That's the next video Let me show you how I did my own P.S: It was my first time, so we do it together... Video dropping soon

Do you know the pain of wanting to send a client an invoice, then you have to open your laptop, find your invoice document and start typing it in Or if you're one of those who use Canva for it You need an invoice and you need it in 3 minutes so you can close a deal I GOT YOU, I will show you how I made an invoice for my company using AI and then created a Webapp for it, the WebApp installs like an android app and I can open it and use anytime without internet. That's the next video Let me show you how I did my own P.S: It was my first time, so we do it together... Video dropping soon

Richard U. | Web Developer

26,615 views • 2 months ago

🚨ELON ON OPTIMUS: OWN YOUR OWN PERSONAL ROBOT FOR LESS THAN A CAR "Anyone could own an Optimus robot, your own personal R2D2 or C3PO. At scale, it will likely cost $20,000 to $30,000—probably less than a car in the long term. What can it do? Anything you want—be a teacher, babysit your kids, walk your dog, mow your lawn, get groceries, serve drinks, or just be your friend. Whatever you can think of, it will do." Source: Tesla

🚨ELON ON OPTIMUS: OWN YOUR OWN PERSONAL ROBOT FOR LESS THAN A CAR "Anyone could own an Optimus robot, your own personal R2D2 or C3PO. At scale, it will likely cost $20,000 to $30,000—probably less than a car in the long term. What can it do? Anything you want—be a teacher, babysit your kids, walk your dog, mow your lawn, get groceries, serve drinks, or just be your friend. Whatever you can think of, it will do." Source: Tesla

Mario Nawfal

739,418 views • 2 years ago

Most AI tools today are just command-takers. You type, it responds. You click, it executes. There's truly no learning, no memory, no adaptation. You're still doing most of the work. Which is why Miles by Avo on Solana would make so much sense if built well. From what I understand so far, miles learns about you over time, adapts to how you operate, and figures out the tools you struggle to navigate on your own. Less clicking, more conversation, the more you use it, the better it gets at working with you, not just for you. That shift from command-follower to learning companion is bigger than it sounds. It's the difference between a tool and an agent that actually knows you. The second one is Agent Grid and this one is for builders and power users. But as I mentioned in this video, I'm still studying the Agent Grid. I'd come talk about it once I learn properly about it. Souren just keeps shipping!

Most AI tools today are just command-takers. You type, it responds. You click, it executes. There's truly no learning, no memory, no adaptation. You're still doing most of the work. Which is why Miles by Avo on Solana would make so much sense if built well. From what I understand so far, miles learns about you over time, adapts to how you operate, and figures out the tools you struggle to navigate on your own. Less clicking, more conversation, the more you use it, the better it gets at working with you, not just for you. That shift from command-follower to learning companion is bigger than it sounds. It's the difference between a tool and an agent that actually knows you. The second one is Agent Grid and this one is for builders and power users. But as I mentioned in this video, I'm still studying the Agent Grid. I'd come talk about it once I learn properly about it. Souren just keeps shipping!

Sir Khaycee

20,465 views • 6 months ago