Loading video...

Video Failed to Load

Go Home

Advice for AI engineers 💡 A small Audio Language Model transcribes audio in real-time on your device, without internet connection or cloud costs. For example, LFM2-Audio-1.5B by ↓

paulabartabajo_'s profile picture

Pau Labarta Bajo

69,544 subscribers

31,993 views • 9 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Advice for AI engineers 💡 A small Visual Language Model fine-tuned on your custom dataset is as accurate as GPT-5... ... and costs 50 times less. For example, LFM2-VL-3B by ↓
0:15

Advice for AI engineers 💡 A small Visual Language Model fine-tuned on your custom dataset is as accurate as GPT-5... ... and costs 50 times less. For example, LFM2-VL-3B by ↓

Pau Labarta Bajo

112,571 views • 9 months ago

Meet Gemma 3n, a model that runs on as little as 2GB of RAM 🤯 It shares the same architecture as Gemini Nano, and is engineered for incredible performance. We added audio understanding, so now it’s multimodal, fast and lean, and runs on-device (no cloud connection required!)
0:15

Meet Gemma 3n, a model that runs on as little as 2GB of RAM 🤯 It shares the same architecture as Gemini Nano, and is engineered for incredible performance. We added audio understanding, so now it’s multimodal, fast and lean, and runs on-device (no cloud connection required!)

Google AI

228,822 views • 1 year ago

Today we’re open-sourcing Stable Audio Open Small, a 341M-parameter text-to-audio model optimized to run entirely on Arm CPUs. This means 99% of smartphones can now generate music-production samples in seconds, right on-device with no internet required. Built for fast, on-the-go creation, it turns your next quick idea into up to 11 seconds of audio. Generate drum loops, foley, riffs, and textures right where you are. No cords 🔌 just chords 🎹 You can learn more here:
0:17

Today we’re open-sourcing Stable Audio Open Small, a 341M-parameter text-to-audio model optimized to run entirely on Arm CPUs. This means 99% of smartphones can now generate music-production samples in seconds, right on-device with no internet required. Built for fast, on-the-go creation, it turns your next quick idea into up to 11 seconds of audio. Generate drum loops, foley, riffs, and textures right where you are. No cords 🔌 just chords 🎹 You can learn more here:

Stability AI

94,796 views • 1 year ago

Voice AI has an evaluation problem. Models look strong on public benchmarks, then collapse on real-world audio. Introducing a recipe-driven evaluation framework for low-resource languages, real-world audio, and production failure modes. Details ↓
0:10

Voice AI has an evaluation problem. Models look strong on public benchmarks, then collapse on real-world audio. Introducing a recipe-driven evaluation framework for low-resource languages, real-world audio, and production failure modes. Details ↓

Poseidon

34,623 views • 3 months ago

Dubbing is dead Introducing Instant AI video dubbing This works by taking the actor/audio from the original video and fine-tuning a voice model. Then overlaps the AI generated dubbed audio onto the original video. This one is huge for creators 🧵
0:19

Dubbing is dead Introducing Instant AI video dubbing This works by taking the actor/audio from the original video and fine-tuning a voice model. Then overlaps the AI generated dubbed audio onto the original video. This one is huge for creators 🧵

Linus ✦ Ekenstam

358,191 views • 3 years ago

Decentralized audio video connectivity, powered by YOU 🫵 ⚡ Become a Media Node Operator ⚡️ Share your unused internet bandwidth ⚡️ Earn $HUDL to power decentralized audio video communication 👾 For more alpha & access to early tiers - join Discord:
0:12

Decentralized audio video connectivity, powered by YOU 🫵 ⚡ Become a Media Node Operator ⚡️ Share your unused internet bandwidth ⚡️ Earn $HUDL to power decentralized audio video communication 👾 For more alpha & access to early tiers - join Discord:

Huddle01

330,531 views • 1 year ago

🔊👁️‿ゝ👁️ We've rebuilt Guilded audio capture from the ground up so you can stream all your favorite games without missing a note! Fully revamped audio capture — live now on Guilded for PC.
0:13

🔊👁️‿ゝ👁️ We've rebuilt Guilded audio capture from the ground up so you can stream all your favorite games without missing a note! Fully revamped audio capture — live now on Guilded for PC.

Guilded

19,222 views • 3 years ago

Un pequeño adelanto de nuestro primer audio ya disponible en la plataforma con P o para su compra individual A small preview of our first audio already available on the platform with P or for individual purchase #cuckold #humillation #femdom #findom
0:18

Sensitive content

Un pequeño adelanto de nuestro primer audio ya disponible en la plataforma con P o para su compra individual A small preview of our first audio already available on the platform with P or for individual purchase #cuckold #humillation #femdom #findom

OLYMPUS OF FEET❤️‍🔥 🦶🏼

10,658 views • 1 year ago

Chatterbox Turbo by Resemble AI now on MLX 🚀🎉 You can now run it locally on your Mac and it supports voice cloning and emotion control. I'm getting 3.8x faster than real-time. > pip install -U mlx-audio Model collection 👇🏽
0:18

Chatterbox Turbo by Resemble AI now on MLX 🚀🎉 You can now run it locally on your Mac and it supports voice cloning and emotion control. I'm getting 3.8x faster than real-time. > pip install -U mlx-audio Model collection 👇🏽

Prince Canuma

24,953 views • 8 months ago

The new open-weights Hailuo AI (MiniMax) H3 is live on OpenRouter thanks to MiniMax (official)! H3 is a lightweight video model for text, image, audio, & video input, with native audio-visual output. Built for instruction-led edits, text/brand rendering, and video-2-video motion transfer.
0:15

The new open-weights Hailuo AI (MiniMax) H3 is live on OpenRouter thanks to MiniMax (official)! H3 is a lightweight video model for text, image, audio, & video input, with native audio-visual output. Built for instruction-led edits, text/brand rendering, and video-2-video motion transfer.

OpenRouter

22,767 views • 19 days ago

We've got a new audio-conditioned video model 👀 LTX Studio now lets you upload or generate audio, and then creates a lip-synced video. This is going to be HUGE for consistent character voices + AI influencers. I tested it w/ an animation of my pets. More on how to use it 👇
0:12

We've got a new audio-conditioned video model 👀 LTX Studio now lets you upload or generate audio, and then creates a lip-synced video. This is going to be HUGE for consistent character voices + AI influencers. I tested it w/ an animation of my pets. More on how to use it 👇

Justine Moore

18,562 views • 7 months ago

Just think about it. Voice Agents that can walk around! We expanded guidance capabilities for our voice2animation model that runs on-device and in realtime! just plugin any audio wave and get instant animation.
0:13

Just think about it. Voice Agents that can walk around! We expanded guidance capabilities for our voice2animation model that runs on-device and in realtime! just plugin any audio wave and get instant animation.

Sergey Gonchar

66,372 views • 1 year ago

good morning, 𝕏 the audio in Grok Imagine is getting scary good the audio is clean, full, and present. even the mouth shapes are landing dead-on insanely strong for a current-gen ai talking-head 🤯
0:10

good morning, 𝕏 the audio in Grok Imagine is getting scary good the audio is clean, full, and present. even the mouth shapes are landing dead-on insanely strong for a current-gen ai talking-head 🤯

tetsuo

20,465,551 views • 4 months ago

New feature on Redbox Terminal Exchange corporate action feeds Global index real time feeds News search Twitter news feeds AUDIO NEWS (for Pro Traders) For more information contact sales: 8806377087 Or email:saidutt@redboxglobal.com
0:17

New feature on Redbox Terminal Exchange corporate action feeds Global index real time feeds News search Twitter news feeds AUDIO NEWS (for Pro Traders) For more information contact sales: 8806377087 Or email:[email protected]

RedboxGlobal India

12,620,683 views • 2 years ago

One of the amazing things about H3 is that you can upload audio references to get perfectly consistent voices for all your videos. Absolute game changer for AI content and incredible that it was developed by an open source model.
0:10

One of the amazing things about H3 is that you can upload audio references to get perfectly consistent voices for all your videos. Absolute game changer for AI content and incredible that it was developed by an open source model.

Mark Gadala-Maria

20,393 views • 13 days ago

Your New Creative Powerhouse: Kling 2.6 Audio on Higgsfield. Limited Time on Higgsfield: 70% OFF all tools + UNLIMITED image models for a year. The best value for creators. Higgsfield AI 🧩 This is the only place where creators get Kling 2.6 uncensored, unrestricted, and unlimited on Higgsfield. Perfect for those who need speed and control without manual cleanup.
0:10

Your New Creative Powerhouse: Kling 2.6 Audio on Higgsfield. Limited Time on Higgsfield: 70% OFF all tools + UNLIMITED image models for a year. The best value for creators. Higgsfield AI 🧩 This is the only place where creators get Kling 2.6 uncensored, unrestricted, and unlimited on Higgsfield. Perfect for those who need speed and control without manual cleanup.

Maxxxxx

109,740 views • 8 months ago

Introducing: OpenGranola 🔥 I built an open source meeting copilot for macOS. It transcribes both sides of your call on-device, searches your own notes in real time, and hands you talking points right when the conversation needs them. No audio leaves your Mac. Point it at a folder of markdown files, pick any LLM through OpenRouter (Claude, GPT-4o, Gemini, Llama), and it just works. It's invisible to screen share too — nobody knows you have it. The whole thing is open source. Link below
0:17

Introducing: OpenGranola 🔥 I built an open source meeting copilot for macOS. It transcribes both sides of your call on-device, searches your own notes in real time, and hands you talking points right when the conversation needs them. No audio leaves your Mac. Point it at a folder of markdown files, pick any LLM through OpenRouter (Claude, GPT-4o, Gemini, Llama), and it just works. It's invisible to screen share too — nobody knows you have it. The whole thing is open source. Link below

yazin

293,178 views • 5 months ago

Apple wasn’t kidding, the iPhone 17 Pro is really built for running LLMs Here’s LFM2 8B A1B by running on-device with MLX in Locally AI - Local AI Chat, the iPhone runs the 8B model with zero struggle Thanks Prince Canuma for the port to MLX, it made the MLX Swift port possible
0:17

Apple wasn’t kidding, the iPhone 17 Pro is really built for running LLMs Here’s LFM2 8B A1B by running on-device with MLX in Locally AI - Local AI Chat, the iPhone runs the 8B model with zero struggle Thanks Prince Canuma for the port to MLX, it made the MLX Swift port possible

Adrien Grondin

493,561 views • 10 months ago