Gabriel Clark

AI and audio at Zyphra

[Xianbang Wang @kevinxbwang2007]

T2I systems look complex only because we keep adding components. How about removing them?

Introducing our latest work MiniT2I 🪄: purely flow matching objective on pixels, no auxiliary losses, all open-source data and academia-affordable compute. Everything is just designed so simple and minimal. ✨

[andi (twocents.com) @Nexuist]

me: hey can I get a 5 ultra high definition photos of 70ft tall Anne Hathaway stomping around Manhattan and crushing people under red heels?

midjourney: sure here you go

me: btw do you know where I can go to get cancer screenings?

midjourney: you’re not gonna believe this

[Noam Shazeer @NoamShazeer]

I’m excited to share that I’ll be joining OpenAI and look forward to working with the exceptional team there.

It was a difficult decision to move on. I’m incredibly proud of the amazing team at Google and everything we’ve built together. It has been an honor and a pleasure to work with all of you.

[Midjourney @midjourney]

A technical dive inside our new "Midjourney Scanner"

[Shraey @iamshraey_]

MLX port for apple silicon is up + quantized weights as well.
Is pretty solid TTS model, probably one of the top 2-3 open-source models I’ve used.

https://t.co/B1pNp24Rc5

[Gabriel Clark @Gcabrielclark]

@iamshraey_ Thanks for the MLX port! Excited to eval this and try it on my mac :)

[Gabriel Clark @Gcabrielclark]

@umi33563 @teortaxesTex It runs realtime on an m1 mac at q4

[Gabriel Clark @Gcabrielclark]

@manateelazycat It does!

[Gabriel Clark @Gcabrielclark]

@arata_ae You actually might be able to run it locally. Because its moe you can do realtime on an m1 mac at q4.

[Gabriel Clark @Gcabrielclark]

@koguGameDev Curious to hear your thoughts. Especially interested in any specific voices you are trying to get good results on.

[Gabriel Clark @Gcabrielclark]

@shinshin86 based

[shinshin86｜AITuber OnAir開発者｜AIキャラのミコをバズらせたい人 @shinshin86]

出たばかりのZONOS2、Colabで簡単に試せるようにしました！

日本語対応・Apache-2.0（商用OK）・声のクローンもいける、MoEで低遅延の新しいオープンウェイトTTS

Local TTS on Colabに追加したので、ZONOS2をセレクトボックスから選択後、生成されたコマンドを貼るだけでOpenAI互換APIとして起動して動作確認できます

新しいモデルをすぐ触れるの、やっぱり楽しい😊
https://t.co/Zgf8d0vs1q

[Gabriel Clark @Gcabrielclark]

@JanssenManno @ZyphraAI @AMD We will post pricing soon!!

[Gabriel Clark @Gcabrielclark]

@yugshende @ZyphraAI @AMD Going to have to agree here. The benchmarks we post are pretty narrow and talk only about naturalness in a few verticals. I have so much respect for the Gemini multimodal team they are cooking 🔥.

[Gabriel Clark @Gcabrielclark]

@auroter @ZyphraAI @AMD 😂

[Gabriel Clark @Gcabrielclark]

@pipipoopo228 @teortaxesTex @AMD Based

[Gabriel Clark @Gcabrielclark]

@IgorIlyinsky If you self host you can clone from any length of audio but on our api, which is at the bottom of the tweet thread, clone length is capped at 120 seconds.

[Gabriel Clark @Gcabrielclark]

Been working on this for a while go check it out!

Tech report coming soon. I’m so excited for people to dig into all the weird stuff we found.

[Zyphra @ZyphraAI]

Today we're releasing ZONOS2, our next-generation real-time TTS model with high-fidelity voice cloning.

ZONOS2 is the most expressive open-source TTS model, released under Apache 2.0 and available on Zyphra Cloud on @AMD. 🧵

[Gabriel Clark @Gcabrielclark]

@BachelderDan @ZyphraAI @AMD Its currently free only. We are working on pricing and will have an option for this soon!

[Gabriel Clark @Gcabrielclark]

@multimodalart Aye nice!!

[Gabriel Clark @Gcabrielclark]

@multimodalart woah so fast!!!