Loading video...

Video Failed to Load

Go Home

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...

StabilityAI's profile picture

Stability AI

258,083 subscribers

94,796 views • 1 year ago •via X (Twitter)

Science & TechnologyMusicEducation
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

HappyHorse 1.0 is now on OpenArt 🐎 It's the #1 ranked text-to-video model on Artificial Analysis right now. Generate up to 15 seconds 1080p video with synchronised audio in a single pass and support for 7 languages.
0:14

HappyHorse 1.0 is now on OpenArt 🐎 It's the #1 ranked text-to-video model on Artificial Analysis right now. Generate up to 15 seconds 1080p video with synchronised audio in a single pass and support for 7 languages.

OpenArt

2,249,094 views • 2 months ago

This is WILD. Freepik just gave AI video a voice with Wan 2.5. Smooth motion. Clean visuals. And now? Built-in audio from just text or images. It’s fast, fluid, and free to try. Here’s what you can generate in seconds:
0:10

This is WILD. Freepik just gave AI video a voice with Wan 2.5. Smooth motion. Clean visuals. And now? Built-in audio from just text or images. It’s fast, fluid, and free to try. Here’s what you can generate in seconds:

Dhaval Makwana

19,768 views • 9 months ago

🚀 LTX-2 is now the first AI model to generate 20 seconds of continuous, synchronized audio and video! That’s double the previous 10-second max. With 20s of audio + video, we finally have time to tell much more interesting - and touching - stories. 🎥 Open-sourcing soon! 🧵👇
0:19

🚀 LTX-2 is now the first AI model to generate 20 seconds of continuous, synchronized audio and video! That’s double the previous 10-second max. With 20s of audio + video, we finally have time to tell much more interesting - and touching - stories. 🎥 Open-sourcing soon! 🧵👇

Yoav HaCohen

33,230 views • 8 months ago

Stable Audio 3 by Stability AI is just out It mainly comes with 3 open source variants: - Stable Audio 3 Medium (2B) - Stable Audio 3 Small (0.6B) - Music - Stable Audio 3 Small (0.6B) - VFX (and a "large" closed variant) The open models are really fast and high quality
0:14

Stable Audio 3 by Stability AI is just out It mainly comes with 3 open source variants: - Stable Audio 3 Medium (2B) - Stable Audio 3 Small (0.6B) - Music - Stable Audio 3 Small (0.6B) - VFX (and a "large" closed variant) The open models are really fast and high quality

apolinario (poli)

41,484 views • 1 month ago

Today, we are adding Stable Video Diffusion, our foundation model for generative video to the Stability AI Developer Platform API. The model can generate 2 seconds of video, comprising of 25 generated frames and 24 frames of FILM interpolation, within an average time of 41 seconds. Developers interested in utilizing Stable Video Diffusion through an API can access it now on the Stability AI Developer Platform. Learn more here:
0:18

Today, we are adding Stable Video Diffusion, our foundation model for generative video to the Stability AI Developer Platform API. The model can generate 2 seconds of video, comprising of 25 generated frames and 24 frames of FILM interpolation, within an average time of 41 seconds. Developers interested in utilizing Stable Video Diffusion through an API can access it now on the Stability AI Developer Platform. Learn more here:

Stability AI

175,571 views • 2 years ago

Meet Stable Audio 3.0, the open-weight model family built for artistic experimentation. This is our open invitation to experiment with generative audio. We believe the best innovations are still waiting to be built. The 4-1-1 on 3.0: 📣 You own your outputs, and can distribute and commercialize them under the Stability AI Community License (up to $1 million in revenue). 🎵 New and improved capabilities include variable-length generation up to six minutes, and full song composition on portable devices, no GPU required. ✅ Trained on a fully licensed dataset. 🎨 You can customize the models on your own library with support for LoRa training, which we’ve documented for the first time. More on the models 👇
0:10

Meet Stable Audio 3.0, the open-weight model family built for artistic experimentation. This is our open invitation to experiment with generative audio. We believe the best innovations are still waiting to be built. The 4-1-1 on 3.0: 📣 You own your outputs, and can distribute and commercialize them under the Stability AI Community License (up to $1 million in revenue). 🎵 New and improved capabilities include variable-length generation up to six minutes, and full song composition on portable devices, no GPU required. ✅ Trained on a fully licensed dataset. 🎨 You can customize the models on your own library with support for LoRa training, which we’ve documented for the first time. More on the models 👇

Stability AI

158,037 views • 1 month ago

introducing new video models and video-to-audio. Kling 1.6, Hunyuan, and 01-Live are now available in Krea and now you can generate audio for videos. free users can finally generate videos too!
0:13

introducing new video models and video-to-audio. Kling 1.6, Hunyuan, and 01-Live are now available in Krea and now you can generate audio for videos. free users can finally generate videos too!

Krea

80,188 views • 1 year ago

🚨BREAKING: Now you can generate high-quality 4K videos just by using a text description! SkyReels V2 lets you create cinematic content completely free and open source, with no time limits on videos over 30 seconds. Here’s why this will blow your mind:
0:12

🚨BREAKING: Now you can generate high-quality 4K videos just by using a text description! SkyReels V2 lets you create cinematic content completely free and open source, with no time limits on videos over 30 seconds. Here’s why this will blow your mind:

Hasan Toor

190,035 views • 1 year ago

We’re proud to highlight Google Research’s contributions to improving Clear Calling, the background noise reduction feature on Pixel, which can now handle full-band audio & is powered by an audio-to-audio ML model that was optimized to run at low latency on Google Tensor.
0:13

We’re proud to highlight Google Research’s contributions to improving Clear Calling, the background noise reduction feature on Pixel, which can now handle full-band audio & is powered by an audio-to-audio ML model that was optimized to run at low latency on Google Tensor.

Google AI

69,420 views • 2 years ago

Someone built an AI you power with a hand crank it is called CrankGPT and its running without any battery, internet or data centre just you turning a handle like it is 1900 SqueezLabs built it using a Raspberry Pi 5 with 8GB of RAM an audio card and a 20 watt hand crank generator it takes about 30 seconds of cranking to boot into a working voice assistant and the onboard capacitor gives you roughly 20 seconds of runtime before you have to start cranking again they have used it to generate small images even write code 🤯 this proves you can run a real AI model on almost no power while everyone is building billion dollar data centres two guys put AI in a box
0:15

Someone built an AI you power with a hand crank it is called CrankGPT and its running without any battery, internet or data centre just you turning a handle like it is 1900 SqueezLabs built it using a Raspberry Pi 5 with 8GB of RAM an audio card and a 20 watt hand crank generator it takes about 30 seconds of cranking to boot into a working voice assistant and the onboard capacitor gives you roughly 20 seconds of runtime before you have to start cranking again they have used it to generate small images even write code 🤯 this proves you can run a real AI model on almost no power while everyone is building billion dollar data centres two guys put AI in a box

Sweep

11,610 views • 16 days ago

Holy smoke... Hunyuan3D 2.0 MV is impressive (and open source 🫨) ➡️ You can generate a mesh from multiple images in just seconds. Next workflow: effortlessly create a consistent turnaround on Scenario > then generate the mesh from it.
0:16

Holy smoke... Hunyuan3D 2.0 MV is impressive (and open source 🫨) ➡️ You can generate a mesh from multiple images in just seconds. Next workflow: effortlessly create a consistent turnaround on Scenario > then generate the mesh from it.

Emm | scenario.com

42,015 views • 1 year ago

Generate Long Videos with Wan even on Low VRAM machines! [NVIDIA ONLY] With this super-optimized gradio app from deepbeepmeep you can generate up to 12 second videos with Wan. And even generate on low VRAM machines! - Generate up to 12 sec videos - Run on 5GB~ VRAM (Read the full thread)
0:16

Generate Long Videos with Wan even on Low VRAM machines! [NVIDIA ONLY] With this super-optimized gradio app from deepbeepmeep you can generate up to 12 second videos with Wan. And even generate on low VRAM machines! - Generate up to 12 sec videos - Run on 5GB~ VRAM (Read the full thread)

cocktail peanut

135,919 views • 1 year ago

here's how to do this in 2 minutes: - upload monk image to gemini - ask it to generate a 1:1 json prompt - generate the voice with minimax audio - generate the image with nano banana pro - lipsync with infinitetalk (open-source) congrats you just saved $10k for a trip to china to find a monk.
0:18

here's how to do this in 2 minutes: - upload monk image to gemini - ask it to generate a 1:1 json prompt - generate the voice with minimax audio - generate the image with nano banana pro - lipsync with infinitetalk (open-source) congrats you just saved $10k for a trip to china to find a monk.

0x ROAS

242,758 views • 5 months ago

Perfect example of how the FREE VERSION of Rara Audio can put in work! User is on my free settings on the app, even with a precision passing overhead, he can hear the persons footsteps to his right! You are MISSING OUT if you don’t try my audio!
0:18

Perfect example of how the FREE VERSION of Rara Audio can put in work! User is on my free settings on the app, even with a precision passing overhead, he can hear the persons footsteps to his right! You are MISSING OUT if you don’t try my audio!

Rara

17,826 views • 20 days ago

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 ↓
0:14

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 ↓

Pau Labarta Bajo

31,993 views • 7 months ago

I used GPT-4o to create STL file for 3D model in ~ 20 seconds on my phone. Pretty remarkable what you can generate with AI and simple prompt now.
0:26

I used GPT-4o to create STL file for 3D model in ~ 20 seconds on my phone. Pretty remarkable what you can generate with AI and simple prompt now.

Min Choi

3,443,647 views • 2 years ago

Hindi Speech Model should be free and open-source. And we’re making it happen. >High quality >Multiple voices >UI to generate audio + API for deployment Follow me to get notified when it launches. Listen to the audio till the end!
0:11

Hindi Speech Model should be free and open-source. And we’re making it happen. >High quality >Multiple voices >UI to generate audio + API for deployment Follow me to get notified when it launches. Listen to the audio till the end!

Dheemanth Reddy

59,602 views • 1 year 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 • 5 months ago

today we're open-sourcing Krea Realtime. this 14B autoregressive model is 10x larger than any open-source equivalent, and it can generate long-form videos at 11 fps on a single B200. weights and technical report below 👇
0:13

today we're open-sourcing Krea Realtime. this 14B autoregressive model is 10x larger than any open-source equivalent, and it can generate long-form videos at 11 fps on a single B200. weights and technical report below 👇

Krea

226,904 views • 8 months ago