"Anthropic ships hidden, undisclosed steering vectors/PEFT to silently sabotage machine learning research work" was not on my bingo card, so sad
Johan Nordberg retweeted
It’s been a blast working on this one with @dabkowski_piotr.
Audio-to-audio model with full emotional and background transfer, capable of cloning source speakers in a controllable way.
We’re giving everyone 15 free minutes on Starter and 30 free minutes on Creator+ subscriptions for the first 7 days, so go give it a try!
Johan Nordberg retweeted
Now we're talking! Elevenlabs new music model can get super experimental.
Up to and including making a techno song made by and for mosquitos.
Unironically, this is what I've been wanting for a long time.
Johan Nordberg retweeted
Now that @karpathy is not making videos for a while at least we can listen to him sing
Music V2 is out! I'm proud of this one, the level of control and generalization is day and night compared to v1 - will post some samples shortly
Now that @karpathy is not making videos for a while at least we can listen to him sing
Johan Nordberg retweeted
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
Johan Nordberg retweeted
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 songs with Eleven Music.
Johan Nordberg retweeted
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.
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!
Johan Nordberg retweeted
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.
Johan Nordberg retweeted
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 diarization, audio event tagging, and precise timestamps –