正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Introducing Stable Audio 2.0 – a new model capable of producing high-quality, full tracks with coherent musical structure up to three minutes long at 44.1 kHz stereo from a single prompt. Explore the model and start creating for free at: Read the blogpost here: (1/3)

Stability AI

257,944 subscribers

457,689 次观看 • 2 年前 •via X (Twitter)

科学技术音乐

Anya Rossi• Live Now

Private livecam show

10 条评论

Stability AI 的头像

Stability AI2 年前

2.0 goes beyond text-to-audio to include audio-to-audio capabilities. Users can now upload audio samples and, through natural language prompts, transform these samples into a wide array of sounds. (2/3)

Stability AI 的头像

Stability AI2 年前

2.0 was exclusively trained on a licensed dataset from the @AudioSparx music library, honoring opt-out requests and ensuring fair compensation for creators. (3/3)

Moonlit Monkey 🐕🙏🪽 的头像

Moonlit Monkey 🐕🙏🪽2 年前

I don't understand why people in AI aren't making riff or timbre generators and are instead focused on this 'complete music' approach. Musicians would love granular tools. Not sure anyone wants infinite stock music that much.

Furkan Gözükara 的头像

Furkan Gözükara2 年前

great move. nothing like suno yet but i hope will reach there

Ryan English 的头像

Ryan English2 年前

My membership doesn't include this? Makes me wonder what my $20/mo is actually for tbh

BAIJ 的头像

BAIJ2 年前

Ugh doesn’t do lyrics.

arbitrarity 的头像

arbitrarity2 年前

When local

nano 的头像

nano2 年前

SD3 is not coming guys Microsoft killed it

Der tapfere kleine Toaster 的头像

Der tapfere kleine Toaster2 年前

You guys will do anything EXCEPT release SD3. There is limited time left and you waste it on this?

🇵🇸🇱🇧 Tourvi𝕏us 的头像

🇵🇸🇱🇧 Tourvi𝕏us2 年前

So not an open source...

相关视频

Today we’re launching Stable Audio 2.5: The first audio model built for enterprise-grade sound production 🔊 Audio influences brand engagement by 86%, but few enterprises are leveraging audio as an extension of their brand, making customized sound an untapped differentiator. Stable Audio 2.5 is purpose-built for this opportunity to create customizable, high-quality audio at scale, with capabilities that include: ▶️ Improved musical composition: Generate full songs with multi-part structure, meaning a clear intro, middle, and outro. ▶️ Audio inpainting: Input audio, select where the track should start, and the model uses the context to generate the rest of the track. ▶️ Customization: Our team can fine-tune Stable Audio 2.5 to help enterprises create the right sound for their brand. ▶️ Faster inference: The model can generate up to three-minute long tracks in under two seconds on a GPU, outputting in just eight steps (compared to ~50 in the previous model). You can learn more here 👉

Stability AI

67,491 次观看 • 10 个月前

Introducing Dream Machine - a next generation video model for creating high quality, realistic shots from text instructions and images using AI. It’s available to everyone today! Try for free here #LumaDreamMachine

Introducing Dream Machine - a next generation video model for creating high quality, realistic shots from text instructions and images using AI. It’s available to everyone today! Try for free here #LumaDreamMachine

Luma

2,477,223 次观看 • 2 年前

ByteDance has released Seed3D 2.0, a model capable of generating 3D objects from a single image or a text prompt.

ByteDance has released Seed3D 2.0, a model capable of generating 3D objects from a single image or a text prompt.

Kashberg

164,747 次观看 • 2 个月前

Today we’re delighted to launch more new features, starting with a model capable of two-minute generations, udio-130. This makes it much easier to create tracks with long-term coherence and structure. Check out the track below for a taste of what’s possible using a single prompt. udio-130 will launch alongside our existing model. For now, two-minute generation is an experimental feature available at a discounted credit-rate to pro-subscribers only, but we will be rolling it out more broadly over the coming weeks. 1/4

Today we’re delighted to launch more new features, starting with a model capable of two-minute generations, udio-130. This makes it much easier to create tracks with long-term coherence and structure. Check out the track below for a taste of what’s possible using a single prompt. udio-130 will launch alongside our existing model. For now, two-minute generation is an experimental feature available at a discounted credit-rate to pro-subscribers only, but we will be rolling it out more broadly over the coming weeks. 1/4

udio

93,046 次观看 • 2 年前

Literally, the first transcription model that you can steer with a prompt. Send audio + a prompt. The model does what you ask. Universal 3 Pro from AssemblyAI is the world's first production model to support this. 2026 is off to a great start!

Literally, the first transcription model that you can steer with a prompt. Send audio + a prompt. The model does what you ask. Universal 3 Pro from AssemblyAI is the world's first production model to support this. 2026 is off to a great start!

Santiago

10,147 次观看 • 4 个月前

Breaking!** The Big Launch 🚀 A revolution in AI video generation is here! CraftStory has just unveiled Model 2.0, setting a new benchmark with studio-quality human videos up to 5 minutes long. Say goodbye to short, glitchy clips. This is the era of long-form storytelling 👇

Breaking!** The Big Launch 🚀 A revolution in AI video generation is here! CraftStory has just unveiled Model 2.0, setting a new benchmark with studio-quality human videos up to 5 minutes long. Say goodbye to short, glitchy clips. This is the era of long-form storytelling 👇

Hayyan

24,183 次观看 • 7 个月前

Researchers at Meta recently shared MAGNeT, a single non-autoregressive transformer model for text-to-music & text-to-sound generation capable of generating audio on-par with the quality of SOTA models — at 7x the speed. MAGNeT is open source as part of AudioCraft. Hear audio samples and get more details on this work ➡️

Researchers at Meta recently shared MAGNeT, a single non-autoregressive transformer model for text-to-music & text-to-sound generation capable of generating audio on-par with the quality of SOTA models — at 7x the speed. MAGNeT is open source as part of AudioCraft. Hear audio samples and get more details on this work ➡️

AI at Meta

122,001 次观看 • 2 年前

Today, together with kyutai, we’re introducing our new Audio-to-MIDI model. It takes a finished recording, identifies the instruments playing, and returns separate MIDI tracks for each — voice, drums, bass, keys, and more. Unlike most existing solutions, our model works directly from the full mix rather than requiring separate stems. It also detects chords, key, and tempo, giving producers broader musical context. We’ve written more about the model, the problem, and how it works here:

Today, together with kyutai, we’re introducing our new Audio-to-MIDI model. It takes a finished recording, identifies the instruments playing, and returns separate MIDI tracks for each — voice, drums, bass, keys, and more. Unlike most existing solutions, our model works directly from the full mix rather than requiring separate stems. It also detects chords, key, and tempo, giving producers broader musical context. We’ve written more about the model, the problem, and how it works here:

Mirelo

158,030 次观看 • 21 小时前

Introducing Grok Imagine v0.9, our new video generation model with massive upgrades from v0.1 in visual quality, motion, audio generation, and more. Try it for free in the Grok App.

Introducing Grok Imagine v0.9, our new video generation model with massive upgrades from v0.1 in visual quality, motion, audio generation, and more. Try it for free in the Grok App.

Grok

102,036,433 次观看 • 9 个月前

Introducing Architect I am releasing the first iteration of a model which generates optimized project plans with a single prompt. Think Linear or JIRA, but for agents. A living model that learns from the gossiping network, and gets smarter with every interaction.

Introducing Architect I am releasing the first iteration of a model which generates optimized project plans with a single prompt. Think Linear or JIRA, but for agents. A living model that learns from the gossiping network, and gets smarter with every interaction.

Varun

56,906 次观看 • 3 个月前

🔥🔥 Introducing BuildKit 2.0 🔥🔥 The shadcn for AI tools.→ Build AI tools + MCPs in minutes → Customize with a single prompt → Works with any SDK - AI SDK, , #mcp Stop waiting for integrations. Start creating them. 🚀 Out now.

🔥🔥 Introducing BuildKit 2.0 🔥🔥 The shadcn for AI tools.→ Build AI tools + MCPs in minutes → Customize with a single prompt → Works with any SDK - AI SDK, , #mcp Stop waiting for integrations. Start creating them. 🚀 Out now.

Moe

14,587 次观看 • 10 个月前

Here is something completely new you can do in one shot with Runway. This entire video was generated from a single long audio file. Runway analyzed the file, read the audio transcription, and generated one coherent video to bring it all together visually.

Here is something completely new you can do in one shot with Runway. This entire video was generated from a single long audio file. Runway analyzed the file, read the audio transcription, and generated one coherent video to bring it all together visually.

Cristóbal Valenzuela

21,428 次观看 • 8 天前

Stop searching for the perfect stock track. Just describe it instead. ✍️🎶 We’re bringing Lyria 3 Pro, Google’s latest music generation model, to Google Vids! Now you can create tracks from 30 seconds up to 3 minutes using just a prompt. Try it at today.

Stop searching for the perfect stock track. Just describe it instead. ✍️🎶 We’re bringing Lyria 3 Pro, Google’s latest music generation model, to Google Vids! Now you can create tracks from 30 seconds up to 3 minutes using just a prompt. Try it at today.

Google Workspace

15,646 次观看 • 3 个月前

Today, we’re introducing Pomelli’s latest feature update, ‘Photoshoot’ With Photoshoot, you can start from a single image of your product and easily create high quality, customized product shots to elevate your marketing. Available free of charge in the US, Canada, Australia & New Zealand! Get started with Pomelli today at

Today, we’re introducing Pomelli’s latest feature update, ‘Photoshoot’ With Photoshoot, you can start from a single image of your product and easily create high quality, customized product shots to elevate your marketing. Available free of charge in the US, Canada, Australia & New Zealand! Get started with Pomelli today at

Google Labs

24,108,179 次观看 • 4 个月前

Seedance 2.0 is LIVE for EVERYONE on ALL Higgsfield plans! UP TO 70% OFF. 7 Days of UNLIMITED for new users. With FREE generations for a quick start*! World's most awaited model is FINALLY HERE. You waited long. And you get it on Higgsfield.

Seedance 2.0 is LIVE for EVERYONE on ALL Higgsfield plans! UP TO 70% OFF. 7 Days of UNLIMITED for new users. With FREE generations for a quick start*! World's most awaited model is FINALLY HERE. You waited long. And you get it on Higgsfield.

Higgsfield AI 🧩

1,680,257 次观看 • 3 个月前

🔉 Introducing SAM Audio, the first unified model that isolates any sound from complex audio mixtures using text, visual, or span prompts. We’re sharing SAM Audio with the community, along with a perception encoder model, benchmarks and research papers, to empower others to explore new forms of expression and build applications that were previously out of reach. 🔗 Learn more:

🔉 Introducing SAM Audio, the first unified model that isolates any sound from complex audio mixtures using text, visual, or span prompts. We’re sharing SAM Audio with the community, along with a perception encoder model, benchmarks and research papers, to empower others to explore new forms of expression and build applications that were previously out of reach. 🔗 Learn more:

AI at Meta

1,250,034 次观看 • 6 个月前

The future of digital humans starts with Meshcapade. At #GDC2024, we've unveiled our updated platform. World's best markerless mocap from a single video. High-quality human motions from text. A new viewer with all the old features. Try it here for free:

The future of digital humans starts with Meshcapade. At #GDC2024, we've unveiled our updated platform. World's best markerless mocap from a single video. High-quality human motions from text. A new viewer with all the old features. Try it here for free:

Meshcapade

17,599 次观看 • 2 年前

🚨 BREAKING: this new video gen model is so cracked Hollywood-quality shots 1 minute long from a single prompt i've tested every major video model that dropped this year. sora, kling, runway, all of them. none of them made me stop and rewatch the same clip 6 times. (genuinely thought it was real footage for a second)

🚨 BREAKING: this new video gen model is so cracked Hollywood-quality shots 1 minute long from a single prompt i've tested every major video model that dropped this year. sora, kling, runway, all of them. none of them made me stop and rewatch the same clip 6 times. (genuinely thought it was real footage for a second)

Robin Delta

25,168 次观看 • 3 个月前

🚀Hyped to share Cartesia's $64M Series A along with Sonic 2.0, a new state-of-the-art audio model! Our new model is faster (40 ms!), higher quality, and has insane voice cloning (see a demo of Albert Gu and Timothy Luong (Chongz)'s clones below)!

🚀Hyped to share Cartesia's $64M Series A along with Sonic 2.0, a new state-of-the-art audio model! Our new model is faster (40 ms!), higher quality, and has insane voice cloning (see a demo of Albert Gu and Timothy Luong (Chongz)'s clones below)!

Ivory Tang

10,963 次观看 • 1 年前

introducing Visual Copilot - a new AI model to convert designs to high quality, responsive code in record time full announcement:

introducing Visual Copilot - a new AI model to convert designs to high quality, responsive code in record time full announcement:

Steve (Builder.io)

69,888 次观看 • 2 年前