Someone is hidden.

@primalpoly Start from a principle: 'People should mostly be free to do what they like' For a brief period of history, partially developed technology meant that it was possible to make copies fairly cheaply, but only using expensive equipment. This made a weird novel business model possible

Hourglass + Diffusion = ❤️ We introduce a new transformer backbone for diffusion models that can directly generate megapixel images without the need for multiple stages like latent diffusion. Read here! → arxiv.org/abs/2401.11605 Project page → crowsonkb.github.io/hourglass-diff…

Driving in Italy

I joined ElevenLabs in January and It’s been an absolute blast working with Flavio Schneider on this! This one is generated from a single text prompt “rap about never stopping to learn”, lyrics included. Not 100% yet but we are just getting started ;)

Text to Sound Effects is here. Our newest AI Audio model generates sound effects, short instrumental tracks, soundscapes, and a wide variety of character voices, all from a text prompt. Available now for all users. Everyone from content creators, video game developers, to film

POV you get your morning coffee after a long night of working on music models

Introducing Voice Isolator. Remove unwanted background noise and extract crystal clear dialogue from any audio to make your next podcast, interview, or film sound like it was recorded in the studio. Try it free: elevenlabs.io/voice-isolator…

One line, one word. ✏️🔤 A simple #p5js sketch where you draw a line and Gemini tries to describe it in a single word. I find it really fun to have the model write on the canvas with me (wherever drawing finishes). Uses Gemini 1.5 Flash API. Try it + fork/remix my sketch here:

Scribe is out! I've spent the past few months working on speech-to-text at ElevenLabs. Today, we're excited to introduce Scribe, the smartest audio understanding model. Scribe can convert speech to text in 99 languages, and it includes features such as multi-speaker

Introducing Eleven v3 (alpha) - the most expressive Text to Speech model ever. Supporting 70+ languages, multi-speaker dialogue, and audio tags such as [excited], [sighs], [laughing], and [whispers]. Now in public alpha and 80% off in June.

Eleven v3 [laughs] are amazing—don't laugh :D

Been working hard on this for the last year and a bit, which is in my biased opinion the best sounding music model ever made :) Go try it!

Artists can now combine recordings with real instruments and AI tracks generated by Eleven Music into hybrid songs. In this single-take demo, Mark from our Voices team shows how to blend live piano with AI violin and vocals using one-shot prompting.

Introducing the Eleven Music API. This is the first Music API for developers trained on licensed data and cleared for broad commercial use. You can now integrate the highest quality AI music into your products and workflows. Since launch, creators have generated over 750k

Introducing v2 of our SFX model. Generate any sound effect directly from a prompt, via UI or API. • Higher SFX quality • New: seamlessly looping sound effects • Maximum duration extended from 22s to 30s • Sample rate increased from 44.1kHz to 48kHz • Refreshed SFX Library

🚀 Code Released! EgoX: Egocentric Video Generation from a Single Exocentric Video ✨ 💻 The code is now available! You can generate egocentric videos just like in the demo, or use EgoX to transform your own exocentric videos into egocentric ones.