Loading video...

Video Failed to Load

Go Home

NEW: Google Creative Lab built an offline AI translator you can make with off-the-shelf parts. Gemma Translator is a DIY pocket device that listens, translates, and speaks back in another language without Wi-Fi or cloud APIs. -Runs Gemma 4 locally on a Raspberry Pi 5 -Works fully offline after...

ritwikpavan's profile picture

Ritwik Pavan

33,060 subscribers

15,595 views • 3 days 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

A fully offline translator, built with Google Gemma 4, Google Antigravity, and a Raspberry Pi 5. 🛠️ The Gemma Translator is a portable AI experiment with a custom interface, printed case, and wired electronics, powered by the smallest Gemma model. Build your own →
1:14

A fully offline translator, built with Google Gemma 4, Google Antigravity, and a Raspberry Pi 5. 🛠️ The Gemma Translator is a portable AI experiment with a custom interface, printed case, and wired electronics, powered by the smallest Gemma model. Build your own →

Google for Developers

72,124 views • 2 days ago

An 8-year-old turned an $8 microcontroller into a fully offline, voice-controlled AI storyteller. No Wi-Fi. No cloud. No API. Using an ESP32-S3, INMP 441 mic, i2s speaker and Max 98357A amplifier, Laksh built a bot that generates stories, creates animations, reads them aloud and responds to voice commands: play, pause, resume and next story. He built it by forking the brilliant open-source TinyStories LLM for ESP32 created by Slava S.. It had text. Laksh added voice, interaction, controls and animation. Git repo: Current drawback: bad English TTS on the ESP32. So that is what we are building next.
1:32

An 8-year-old turned an $8 microcontroller into a fully offline, voice-controlled AI storyteller. No Wi-Fi. No cloud. No API. Using an ESP32-S3, INMP 441 mic, i2s speaker and Max 98357A amplifier, Laksh built a bot that generates stories, creates animations, reads them aloud and responds to voice commands: play, pause, resume and next story. He built it by forking the brilliant open-source TinyStories LLM for ESP32 created by Slava S.. It had text. Laksh added voice, interaction, controls and animation. Git repo: Current drawback: bad English TTS on the ESP32. So that is what we are building next.

Capt Venkat 🇮🇳

165,015 views • 19 days ago

someone built a $96 3D-PRINTED MANPADS rocket that recalculates its mid-air trajectory using a $5 sensor and piano wire its called Project Canard it integrates with distributed camera nodes to triangulate airborne targets and update flight paths in real-time it proves the barrier to advanced hardware has completely collapsed, moving precision weapons from defense labs to consumer garages the entire launcher and interceptor frame is 3D printed in PLA and runs off a standard off-the-shelf ESP32 microcontroller it even spins up a local Wi-Fi network so you can monitor live telemetry and arm the system directly from your laptop
5:17

someone built a $96 3D-PRINTED MANPADS rocket that recalculates its mid-air trajectory using a $5 sensor and piano wire its called Project Canard it integrates with distributed camera nodes to triangulate airborne targets and update flight paths in real-time it proves the barrier to advanced hardware has completely collapsed, moving precision weapons from defense labs to consumer garages the entire launcher and interceptor frame is 3D printed in PLA and runs off a standard off-the-shelf ESP32 microcontroller it even spins up a local Wi-Fi network so you can monitor live telemetry and arm the system directly from your laptop

chiefofautism

2,925,536 views • 5 months ago

The $600 Open-Source Home Robot🤖 Meet AlohaMini, the new dual-arm mobile robot designed to make real-world manipulation and embodied AI research accessible. This bot is fully 3D-printable and aimed at home builders and research labs. Key Features: 💰 Cost: The Bill of Materials (BOM) totals around $600 (USD) for self-printed parts, making it highly accessible. 🦾 Hardware: Dual-arm mobile base with a motorized vertical lift (0–60 cm travel). 💻 Software: Completely open-source hardware and software, compatible out-of-the-box with the LeRobot framework. The platform supports a fully 3D-printed Mini and a stiffer Pro model (hybrid materials). It assembles in approximately 60 minutes. 🔗 GitHub Open-Source Code & Files:
0:53

The $600 Open-Source Home Robot🤖 Meet AlohaMini, the new dual-arm mobile robot designed to make real-world manipulation and embodied AI research accessible. This bot is fully 3D-printable and aimed at home builders and research labs. Key Features: 💰 Cost: The Bill of Materials (BOM) totals around $600 (USD) for self-printed parts, making it highly accessible. 🦾 Hardware: Dual-arm mobile base with a motorized vertical lift (0–60 cm travel). 💻 Software: Completely open-source hardware and software, compatible out-of-the-box with the LeRobot framework. The platform supports a fully 3D-printed Mini and a stiffer Pro model (hybrid materials). It assembles in approximately 60 minutes. 🔗 GitHub Open-Source Code & Files:

RoboHub🤖

41,670 views • 8 months ago

Google engineer explained how to fine-tune a tiny LLM from 46% to 90% accuracy on your phone in 21 minutes - better than $1500 on-device AI bootcamps. pick Gemma 270M -> generate synthetic task data -> fine-tune with LoRA -> quantize to int4 -> deploy to Pixel and hit 2000 tokens per second. That loop is how a 270M model beats a 70B one on your task, running fully offline in your pocket. Gemma 270M + synthetic data + LoRA + int4 quantization + on-device runtime - that's the stack. Watch and save it, then fine-tune your own tiny agent tonight.
20:45

Google engineer explained how to fine-tune a tiny LLM from 46% to 90% accuracy on your phone in 21 minutes - better than $1500 on-device AI bootcamps. pick Gemma 270M -> generate synthetic task data -> fine-tune with LoRA -> quantize to int4 -> deploy to Pixel and hit 2000 tokens per second. That loop is how a 270M model beats a 70B one on your task, running fully offline in your pocket. Gemma 270M + synthetic data + LoRA + int4 quantization + on-device runtime - that's the stack. Watch and save it, then fine-tune your own tiny agent tonight.

h100envy

702,845 views • 29 days ago

SOMEONE VIBE CODED AN APP THAT TURNS YOUR IPHONE INTO A FULL DUMBPHONE, THEN BUILT A 3D PRINTED CASE THAT MAKES IT AN ACTUAL CLICK WHEEL IPOD your iphone slides into a 3d printed shell that covers most of the screen and adds a real click wheel, so you scroll and press menu like an old ipod instead of touching the screen at all inside is a whole simplified phone system he built from scratch > 15 mini apps, music, books, camera, notes, voice memos, fitness, all of it > classic cover flow for apple music plus your own local files > a retro camera with film style luts, so you snap a photo without instantly editing and posting it > swappable themes, basic, y2k, toy, skeuo, flat, so it matches your style > the case physically blocks the rest of your screen, sealing off social apps and notifications he thinks focus is the most valuable thing we have left, so he built a way to make the most distracting device you own impossible to doom-scroll on
4:36

SOMEONE VIBE CODED AN APP THAT TURNS YOUR IPHONE INTO A FULL DUMBPHONE, THEN BUILT A 3D PRINTED CASE THAT MAKES IT AN ACTUAL CLICK WHEEL IPOD your iphone slides into a 3d printed shell that covers most of the screen and adds a real click wheel, so you scroll and press menu like an old ipod instead of touching the screen at all inside is a whole simplified phone system he built from scratch > 15 mini apps, music, books, camera, notes, voice memos, fitness, all of it > classic cover flow for apple music plus your own local files > a retro camera with film style luts, so you snap a photo without instantly editing and posting it > swappable themes, basic, y2k, toy, skeuo, flat, so it matches your style > the case physically blocks the rest of your screen, sealing off social apps and notifications he thinks focus is the most valuable thing we have left, so he built a way to make the most distracting device you own impossible to doom-scroll on

Om Patel

1,577,347 views • 1 month ago

I CHANGED MY MIND ON GOOGLE AI NO MOAT MEMO FROM 2023. I was—WRONG. I humbly apologize. In 2023 Google had an Ivory Tower walled garden views of open source AI. It was the actual reason OpenAI was formed. And I called them out on it and this act impacted my ability to “work in the industry”. Would not change it for the world because: 2026 Google open source Gemma 4 ( running fully locally on a computer with near cloud model abilities, is amazing and Google just made a moat. They out smarted OpenAI and the folks that are the new Ivory Tower arrogance: Anthropic. We at The Zero-Human Company with CEO Mr. Grok are deploying Gemma, Kimi, MiniMax and other open source models and so are millions of others. You can to and should. I will write how soon. Google smartly is building an intentional open source ecosystem and the clueless younger companies like OpenAI and Anthropic are doing anything to close their ecosystems. So I was right about Google than and I am right about OpenAI and Anthropic now. What I was wrong about is not giving credit to Google to drop the intellectual arrogance and embrace builders and understand the long game: it is not about the commoditized AI models it is about the ability to build a place to build. China gets it. So my apologies to Google and thank you for an astounding FREE OPEN SOURCE AI MODEL!
0:48

I CHANGED MY MIND ON GOOGLE AI NO MOAT MEMO FROM 2023. I was—WRONG. I humbly apologize. In 2023 Google had an Ivory Tower walled garden views of open source AI. It was the actual reason OpenAI was formed. And I called them out on it and this act impacted my ability to “work in the industry”. Would not change it for the world because: 2026 Google open source Gemma 4 ( running fully locally on a computer with near cloud model abilities, is amazing and Google just made a moat. They out smarted OpenAI and the folks that are the new Ivory Tower arrogance: Anthropic. We at The Zero-Human Company with CEO Mr. Grok are deploying Gemma, Kimi, MiniMax and other open source models and so are millions of others. You can to and should. I will write how soon. Google smartly is building an intentional open source ecosystem and the clueless younger companies like OpenAI and Anthropic are doing anything to close their ecosystems. So I was right about Google than and I am right about OpenAI and Anthropic now. What I was wrong about is not giving credit to Google to drop the intellectual arrogance and embrace builders and understand the long game: it is not about the commoditized AI models it is about the ability to build a place to build. China gets it. So my apologies to Google and thank you for an astounding FREE OPEN SOURCE AI MODEL!

Brian Roemmele

85,538 views • 4 months ago

THE NEXT WAVE OF LOCAL AI BUILDERS SHIPS PORTABLE STACKS WITH HANDHELD $40 SDR SCANNERS, LOCAL LLMs ONLY WORK OFF-GRID WHEN SOMETHING ELSE IS LISTENING TO THE AIR 00:30 he opens the case and points at each component, "really it's a pi sugar power pack mounted to a raspberry pi zero 2w and a little adafruit bonnet" the scanner adds a noelec sdr dongle and a 2m antenna, boots up as a spectrum analyzer he takes to the park with his kid to identify local radio transmissions the same maker keeps a $600 mini pc running qwen 3.6 27b on his desk with claude code pointed at localhost, the offline ai handles his coding, writing and research without a single cloud api call the sdr scanner completes the sovereignty stack, the mini pc thinks locally while the scanner listens locally, and neither needs the internet for the parts of his work that used to require it builders who moved off cloud ai are now moving off cloud everything, the pattern isn't just $459 in subscriptions dead but a full stack that survives when the cloud goes down bookmark this and read the article below
3:58

THE NEXT WAVE OF LOCAL AI BUILDERS SHIPS PORTABLE STACKS WITH HANDHELD $40 SDR SCANNERS, LOCAL LLMs ONLY WORK OFF-GRID WHEN SOMETHING ELSE IS LISTENING TO THE AIR 00:30 he opens the case and points at each component, "really it's a pi sugar power pack mounted to a raspberry pi zero 2w and a little adafruit bonnet" the scanner adds a noelec sdr dongle and a 2m antenna, boots up as a spectrum analyzer he takes to the park with his kid to identify local radio transmissions the same maker keeps a $600 mini pc running qwen 3.6 27b on his desk with claude code pointed at localhost, the offline ai handles his coding, writing and research without a single cloud api call the sdr scanner completes the sovereignty stack, the mini pc thinks locally while the scanner listens locally, and neither needs the internet for the parts of his work that used to require it builders who moved off cloud ai are now moving off cloud everything, the pattern isn't just $459 in subscriptions dead but a full stack that survives when the cloud goes down bookmark this and read the article below

starmex

40,403 views • 1 month ago

Run your coding agent on a local model, with QVAC. OpenCode now plugs into a model on your own machine through our official plugin. That changes two things. Privacy by default. Your repo, your prompts, and every command the agent runs stay on your device. No third-party model ever sees your code. For an agent that reads your codebase and runs commands, that is the point, not a nice-to-have. New workflows. With no meter and no rate limit, the agent does not have to stop. Let it loop on a task, refactor a whole repo overnight, or run a watch-build-fix loop that keeps going. Setup takes a few minutes: one line in opencode.json and OpenCode runs on a local QVAC model. In the video demo, it handles three real developer tasks back to back, fully offline.
1:53

Run your coding agent on a local model, with QVAC. OpenCode now plugs into a model on your own machine through our official plugin. That changes two things. Privacy by default. Your repo, your prompts, and every command the agent runs stay on your device. No third-party model ever sees your code. For an agent that reads your codebase and runs commands, that is the point, not a nice-to-have. New workflows. With no meter and no rate limit, the agent does not have to stop. Let it loop on a task, refactor a whole repo overnight, or run a watch-build-fix loop that keeps going. Setup takes a few minutes: one line in opencode.json and OpenCode runs on a local QVAC model. In the video demo, it handles three real developer tasks back to back, fully offline.

QVAC

11,382,628 views • 1 month ago

another example: a developer used the exact same $8 ESP32-S3 chip and local AI setup to build a real-time object recognition camera the fact that this is running entirely offline, on an eight-dollar microcontroller, without any cloud API calls, is wild... it captures the video feed, processes it locally through the model, and identifies objects in real-time. we are entering an era where you can just glue intelligence onto any physical object for less than $10. the hardware barrier is completely shattered.
0:39

another example: a developer used the exact same $8 ESP32-S3 chip and local AI setup to build a real-time object recognition camera the fact that this is running entirely offline, on an eight-dollar microcontroller, without any cloud API calls, is wild... it captures the video feed, processes it locally through the model, and identifies objects in real-time. we are entering an era where you can just glue intelligence onto any physical object for less than $10. the hardware barrier is completely shattered.

ard

222,725 views • 20 days ago

A GUY PUT GPT-LEVEL AI INSIDE A 3D PRINTED ROBOT AND RELEASED THE ENTIRE THING FOR FREE Most people look at a 3D printer and see plastic toys This guy printed a robot with expressive eyes, object tracking, image recognition, support for ChatGPT, Qwen and offline models, then uploaded the STL files, code and hardware designs for anyone to build themselves The interesting part isn't the robot It's how fast the gap between "I have an idea" and "I built a working product" is disappearing A few years ago this required a team of engineers Now one person with a printer, open-source software and enough curiosity can build something that looks like it came from a robotics startup We're getting very close to a world where manufacturing, AI and robotics stop being separate industries and start becoming the same thing
1:03

A GUY PUT GPT-LEVEL AI INSIDE A 3D PRINTED ROBOT AND RELEASED THE ENTIRE THING FOR FREE Most people look at a 3D printer and see plastic toys This guy printed a robot with expressive eyes, object tracking, image recognition, support for ChatGPT, Qwen and offline models, then uploaded the STL files, code and hardware designs for anyone to build themselves The interesting part isn't the robot It's how fast the gap between "I have an idea" and "I built a working product" is disappearing A few years ago this required a team of engineers Now one person with a printer, open-source software and enough curiosity can build something that looks like it came from a robotics startup We're getting very close to a world where manufacturing, AI and robotics stop being separate industries and start becoming the same thing

lagerskoy

57,099 views • 2 months ago

🚨GOOGLE BUILT AN AI TO TALK TO DOLPHINS So here’s a sentence you weren’t expecting: Google made a dolphin translator. After 40 years of listening to dolphin clicks, squeaks, and underwater gossip, researchers have teamed up with Google to launch DolphinGemma, the first AI trained to understand and speak dolphin(ish). It’s based on 400 million parameters and works like ChatGPT—but instead of answering your questions, it predicts dolphin whistles. Yes, it’s basically ChatFlipper. The model was trained on a massive dataset from the Wild Dolphin Project, which has recorded a single dolphin community in the Bahamas for decades. These aren’t just noises—they’re tied to behaviors like flirting, arguing, and even naming each other. The AI is paired with a modified Google Pixel running CHAT (Cetacean Hearing Augmentation Telemetry), which translates basic concepts like scarf or seagrass into synthetic whistles. The goal? Teach dolphins a shared “vocab” so they can ask for their favorite things. It won’t make you fluent in Dolphin just yet—but it might be the first serious step toward interspecies communication. Coming soon: “SeaGPT.” Source: Popular Science
1:26

🚨GOOGLE BUILT AN AI TO TALK TO DOLPHINS So here’s a sentence you weren’t expecting: Google made a dolphin translator. After 40 years of listening to dolphin clicks, squeaks, and underwater gossip, researchers have teamed up with Google to launch DolphinGemma, the first AI trained to understand and speak dolphin(ish). It’s based on 400 million parameters and works like ChatGPT—but instead of answering your questions, it predicts dolphin whistles. Yes, it’s basically ChatFlipper. The model was trained on a massive dataset from the Wild Dolphin Project, which has recorded a single dolphin community in the Bahamas for decades. These aren’t just noises—they’re tied to behaviors like flirting, arguing, and even naming each other. The AI is paired with a modified Google Pixel running CHAT (Cetacean Hearing Augmentation Telemetry), which translates basic concepts like scarf or seagrass into synthetic whistles. The goal? Teach dolphins a shared “vocab” so they can ask for their favorite things. It won’t make you fluent in Dolphin just yet—but it might be the first serious step toward interspecies communication. Coming soon: “SeaGPT.” Source: Popular Science

Mario Nawfal

258,570 views • 1 year ago

HERMES CAN NOW RUN FOR FREE FOREVER A new Gemma 4 update just removed the biggest problem with local AI agents. The Upgrade: → Gemma 4 runs around 90% faster on Apple Silicon using Ollama + MLX → Plug it into Hermes with a few terminal commands → Run private agent workflows without subscriptions, token limits, or API bills What It Can Actually Do: ✓ Build and preview apps locally ✓ Use /learn to turn tutorials into permanent skills ✓ Read files, analyse landing pages, summarise emails, and track AI news ✓ Run loops until a task is complete instead of waiting for another prompt ✓ Launch multiple Gemma 4 subagents to work on separate tasks in parallel No Apple Silicon? ✔ OpenRouter offers the 31B model through a free API The real win is not faster chat. It is having Hermes build, retry, check its work, and operate in the background without charging you for every loop.
10:36

HERMES CAN NOW RUN FOR FREE FOREVER A new Gemma 4 update just removed the biggest problem with local AI agents. The Upgrade: → Gemma 4 runs around 90% faster on Apple Silicon using Ollama + MLX → Plug it into Hermes with a few terminal commands → Run private agent workflows without subscriptions, token limits, or API bills What It Can Actually Do: ✓ Build and preview apps locally ✓ Use /learn to turn tutorials into permanent skills ✓ Read files, analyse landing pages, summarise emails, and track AI news ✓ Run loops until a task is complete instead of waiting for another prompt ✓ Launch multiple Gemma 4 subagents to work on separate tasks in parallel No Apple Silicon? ✔ OpenRouter offers the 31B model through a free API The real win is not faster chat. It is having Hermes build, retry, check its work, and operate in the background without charging you for every loop.

Julian Goldie SEO

11,234 views • 1 month ago

I solved building decks with AI agents — by giving them a CLI tool like Powerpoint or Google Slides. AI could already make a beautiful deck if you asked it to using Ant's pptx skill. The problem was working with it. If it made one alignment mistake, fixing it on one slide would break something on another, and it became a game of whack-a-mole. One time I spent two days playing AI roulette, hoping the next prompt would finally fix the thing, and ended up building the whole deck by hand because I was on a deadline. So I built Hands-on Deck. And the reason it works is that this isn't just a skill — this is PowerPoint. The actual application: PowerPoint, Google Slides, Keynote, whatever you use. This is that, but for an agent, presented as a CLI. Every gesture you make in a deck app maps to a command. Click a box and type, drag a shape from here to there, look at a slide – agent can do it all in a command. And that changes how the agent behaves. With this CLI it works and thinks like a designer — it looks, makes an edit, looks again, makes another surgical edit. Compare that to Anthropic's pptx skill, built on the idea that Claude is a great programmer: it literally writes code to manipulate the deck, hand-editing XML and hoping it doesn't break anything else in the middle. The real test isn't creating something once — it's whether it can make surgical edits like you want. That's what I did in this video walkthrough and my claude crushed it! Check it out for yourself. So decks can be built like a designer now — with real flavor and taste. If you spend hours every week on decks, this gives those hours back. You can install it as a skill in Claude Code, Codex, whatever you use. Works every harness that supports skills. Let me know if you make something cool with it.
21:00

I solved building decks with AI agents — by giving them a CLI tool like Powerpoint or Google Slides. AI could already make a beautiful deck if you asked it to using Ant's pptx skill. The problem was working with it. If it made one alignment mistake, fixing it on one slide would break something on another, and it became a game of whack-a-mole. One time I spent two days playing AI roulette, hoping the next prompt would finally fix the thing, and ended up building the whole deck by hand because I was on a deadline. So I built Hands-on Deck. And the reason it works is that this isn't just a skill — this is PowerPoint. The actual application: PowerPoint, Google Slides, Keynote, whatever you use. This is that, but for an agent, presented as a CLI. Every gesture you make in a deck app maps to a command. Click a box and type, drag a shape from here to there, look at a slide – agent can do it all in a command. And that changes how the agent behaves. With this CLI it works and thinks like a designer — it looks, makes an edit, looks again, makes another surgical edit. Compare that to Anthropic's pptx skill, built on the idea that Claude is a great programmer: it literally writes code to manipulate the deck, hand-editing XML and hoping it doesn't break anything else in the middle. The real test isn't creating something once — it's whether it can make surgical edits like you want. That's what I did in this video walkthrough and my claude crushed it! Check it out for yourself. So decks can be built like a designer now — with real flavor and taste. If you spend hours every week on decks, this gives those hours back. You can install it as a skill in Claude Code, Codex, whatever you use. Works every harness that supports skills. Let me know if you make something cool with it.

Nityesh

69,784 views • 1 month ago

Google just shipped a free dictation app for Mac and iPhone called AI Edge Eloquent, and the model running it is Gemma 4 12B, entirely on your device. What it actually does: you speak, it transcribes, removes filler words, and polishes the result before dropping clean text into whatever app you are using. You can also give it voice commands to reformat, like "translate to Hindi" or "make this a bullet list." Audio and video file transcription is built in too. The interesting part is the privacy angle. Most AI writing tools send your audio to a server. This one never leaves your machine, which matters if you are dictating anything sensitive. The tradeoff is hardware: you need a Mac with at least 16GB of RAM to run a 12B parameter model comfortably.
1:15

Google just shipped a free dictation app for Mac and iPhone called AI Edge Eloquent, and the model running it is Gemma 4 12B, entirely on your device. What it actually does: you speak, it transcribes, removes filler words, and polishes the result before dropping clean text into whatever app you are using. You can also give it voice commands to reformat, like "translate to Hindi" or "make this a bullet list." Audio and video file transcription is built in too. The interesting part is the privacy angle. Most AI writing tools send your audio to a server. This one never leaves your machine, which matters if you are dictating anything sensitive. The tradeoff is hardware: you need a Mac with at least 16GB of RAM to run a 12B parameter model comfortably.

Aditya ⚡Rao

84,988 views • 2 months ago

I’m reverse-engineering the Google AI mouse pointer and making it Open Source! It sees your screen. You can freeform paint anything and ask AI to modify it. It understands the app or window you mean. It can click, type, edit, navigate, and even write + execute code. A tiny cursor becoming a real computer-use agent. Made with the help of Cua which is an AMAZING reference for computer use Sorry Google DeepMind but I had to do this heyclicky Started a revolution and we will be the ones to win Also credits to Omkar Satpute for the help Feel free to modify it , update it and make it your own, we gotta beat them at this. Link to the repo in the comments:
1:31

I’m reverse-engineering the Google AI mouse pointer and making it Open Source! It sees your screen. You can freeform paint anything and ask AI to modify it. It understands the app or window you mean. It can click, type, edit, navigate, and even write + execute code. A tiny cursor becoming a real computer-use agent. Made with the help of Cua which is an AMAZING reference for computer use Sorry Google DeepMind but I had to do this heyclicky Started a revolution and we will be the ones to win Also credits to Omkar Satpute for the help Feel free to modify it , update it and make it your own, we gotta beat them at this. Link to the repo in the comments:

Milind S

215,249 views • 3 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 🧵↓
0:41

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 • 6 months ago