Suno is building a future where anyone can make great music.

You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert

Provided with genre, artist, and lyrics as input, Jukebox outputs a new music sample produced from scratch. Below, we show some of our favorite samples. Automatic music generation dates back to more than half a century.[^reference-1][^reference-2][^reference-3][^reference-4] A prominent approach is to generate music symbolically in the form of a piano roll, which specifies the timing, pitch, veloc

Whisper is an automatic speech recognition (ASR) system trained on 680,000 hours of multilingual and multitask supervised data collected from the web. We show that the use of such a large and diverse dataset leads to improved robustness to accents, background noise and technical language. Moreover, it enables transcription in multiple languages, as well as translation from those languages into Eng

You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert

"Our 380.000+ employees all over the world must have the same competence profile. Synthesia helps us develop engaging, relevant and localised training content at scale."

Create professional videos using just a still image with text or audio powered by AI.

This Space has been paused by its owner. Want to use this Space? Head to the community tab to ask the author(s) to restart it.

A text to image foundation model that can be adapted for a wide range of image generation tasks. The model accepts a prompt which is some text describing the image you want to generate. The output images tend to get better as you add more descriptive words to the prompt. The output JSON object contains a key called output which represents the generated image as a base64 string. 1import requests 2i

DALL·E 2 is an AI system that can create realistic images and art from a description in natural language.

A conversational AI system that listens, learns, and challenges

A graphic design app that helps you create professional quality social media posts, invitations, digital postcards, graphics, and more. Start with your idea and create something unique for you.

New: turn images and designs into apps using AI-powered express design Today, we’re thrilled to announce the preview of express design in Power Apps: the ability to instantly generate low-code apps directly from design files and images. In just a few clicks, customers can now create web and mobile apps from a broad range of inputs—including paper forms and PDFs, sketches on the whiteboard, and eve

Microsoftは、WindowsやMacにダウンロードして無料で使える「Lobe」を公開している。同ツールでは、ネット接続やログインもなしで機械学習トレーニングができて、利用するデータはプライベートに保たれる。 Microsoftは2018年にLobeを買収し、同ツールをブラッシュアップしてきた。今では、誰でも簡単に機械学習モデルがトレーニングできるように…とのコンセプトを体現したものになっている。写真をインポートすれば自動でトレーニングLobeのWebサイトに掲載の紹介動画を観れば、このツールのシンプルな使い勝手が認識できるだろう。ナビゲーターがPCのWebカメラで水を飲む写真を複数通り撮影。同じく水を飲んでいないシーンを撮影すると、トレーニングが自動で行われる。 ラベルを調整して、Webカメラの前で水を飲むと「水を飲む」動作が検出できるように。また、モデルの修正も簡単にできるようだ

Enhance your creative works with photos generated completely by AI. Search our gallery of high-quality diverse photos or create unique models by your parameters in real time