Flavio Schneider @flavioschneide Twitter profile

Pinned Tweet

Flavio Schneider

@flavioschneide

11 days

🎵

ElevenLabs

@elevenlabsio

11 days

Here’s an early preview of ElevenLabs Music. All of the songs in this thread were generated from a single text prompt with no edits. Title: It Started to Sing Style: “Pop pop-rock, country, top charts song.”

334

1K

5K

8

2

32

Last Seen Profiles

@C2CFootball

@Go20192021

@COBLH

@RjpSchmitt

@sugiyan14052611

@AlizaL4018

@livepureglobal

@CesarbernardoI1

@nbuounb

@imidak_art

@praetor_eth

@EuanYours

@SacBIRMINGHAM

@twicetheMF

@screspin02

@MacronDesintox

@TheGGC1717

@softwarecooliee

@VisionZeroTO

@JPRouve

@steve11572906

@cutmylipmp3

@BrytonTerr21063

@b1lsa

@mergodPRO

@ysfan_ponzu2013

@RxK8n7v4x5HNUbl

@poopy69poopy420

@Racheltrans76

@seouldreamer94

@ChaosKig

@Drea_got_banned

@TechWelsh1012

@NateRoseArt

@BellaRama13227

@ikotrius

Flavio Schneider

@flavioschneide

1 year

Excited to share what I've been working on for the past 6 months: Text-to-Audio Diffusion. More samples and info here: Enjoy! 🔊 Prompt: "Dubstep Insane Drop Remix (Deluxe Edition), 2 of 4"

261

321

2K

Flavio Schneider

@flavioschneide

1 year

2023 will be a seminal year for AI-generated audio – will keep track of all models and papers here:

15

115

848

Flavio Schneider

@flavioschneide

11 days

ElevenLabs Music model rap.

72

140

804

Flavio Schneider

@flavioschneide

1 year

The world's most advanced TTS system is now accessible with the new Elevenlabs Python API - a few lines of code, and you're good to go. Streaming? Custom voices? All there. Enjoy! 🗣️ GitHub: Colab:

15

99

562

Flavio Schneider

@flavioschneide

7 months

Welcome to the era of synthetic music! 🎧 One of the finest machines I've built at @elevenlabsio . Enjoy!

35

65

513

Flavio Schneider

@flavioschneide

10 months

@elevenlabsio now supports low-latency input streaming. This allows you to listen to LLMs in real-time as the text is being generated. 🔊 "A one-sentence relaxing speech"

15

28

257

Flavio Schneider

@flavioschneide

11 days

Not everyone liked the one 1+ one year ago, how's this?

38

18

178

Flavio Schneider

@flavioschneide

3 years

Drag & drop with 50'000 objects using instanced meshes. In the process of making this even more declarative - this shouldn't be possible in a web browser. @reactjs + @threejs_org + R3F + React Spring

4

16

130

Flavio Schneider

@flavioschneide

3 years

Working on Graphire: a fully declarative and unopinionated react graph library. It supports force layouts in both 2D and 3D using SVGs or @threejs with R3F. repo: sandbox:

4

20

124

Flavio Schneider

@flavioschneide

3 months

Here I fixed it: Sora videos with epic ElevenLabs generated music. Turn on your headphones and feel the future! 🎧

14

18

78

Flavio Schneider

@flavioschneide

3 years

Draggable graph nodes with graphire, use-gesture, and react-three-fiber. Graphire makes it super simple to build diagrams, networks, or flow interfaces. graphire: sandbox:

0

5

64

Flavio Schneider

@flavioschneide

10 months

Just write a generator function yielding text chunks and you're good to go!

0

3

38

Flavio Schneider

@flavioschneide

11 days

@rileybrown_ai It is!

3

0

24

Flavio Schneider

@flavioschneide

1 year

ChatGPT has been lying all along - it's an LSTM!

1

2

24

Flavio Schneider

@flavioschneide

2 years

Working on a new unconditional voice generation architecture with diffusion models in @PyTorch . I'm really enjoying using @weights_biases reports to document the progress. Here are a few weird but cool generated voice samples:

Audio Diffusion (Bravo)

Publish your model insights with interactive plots for performance metrics, predictions, and hyperparameters. Made by Flavio Schneider using W&B

wandb.ai

0

4

21

Flavio Schneider

@flavioschneide

11 days

@VJM0N @elevenlabsio Sure!

4

0

13

Flavio Schneider

@flavioschneide

3 years

A declarative interface for general/force graphs that uses instancing. The integration between functional D3 and declarative React interfaces has always been uncomfortable - we need react-d3-fiber 😅 libs: @threejs , react-three-fiber, d3-force-3d. box:

0

6

Flavio Schneider

@flavioschneide

10 months

@tdinh_me @elevenlabsio Hi there! I just tried a minimalistic example to connect with websockets using JS and seems to work for me - check it out:

ElevenLabs input streaming JS

ElevenLabs input streaming JS. GitHub Gist: instantly share code, notes, and snippets.

gist.github.com

1

0

6

Flavio Schneider

@flavioschneide

3 years

@lavrton @0xca0a @reactjs @threejs_org Here it is, I had to write a custom gesture control for D&D: it's still a work in progress though.

drag-and-drop-instanced-meshes - CodeSandbox

Drag and drop with instanced meshes with custom GestureControl and single matrix animation hook.

codesandbox.io

1

0

6

Flavio Schneider

@flavioschneide

4 months

🦄

ElevenLabs

@elevenlabsio

4 months

We are delighted to start the year by announcing a set of upcoming product launches and our $80 million Series B funding round. We are grateful for the continued trust from @a16z , @natfriedman & @danielgross who co-led the round. Listen & Read:

34

53

474

0

4

Flavio Schneider

@flavioschneide

2 years

@peduarte @delba_oliveira That's what I was going to suggest. I have implemented it using radix in my blog (bottom right)

0

4

Flavio Schneider

@flavioschneide

1 year

@cameronsmith @itsoksami It does! Check this out

Ȧrchinet

@archinetai

2 years

🔊 Enhance! Superhuman voice upsampling from 1.5kHz to 48kHz with audio-diffusion-pytorch

3

36

1

0

4

Flavio Schneider

@flavioschneide

2 years

@borisdayma I think it refers to something like this, but with text: . The idea is that you concatenate the usual mean token with all other N text embedding, then you attend on this N+1 sequence and output only the last token as sentence embedding.

0

3

Flavio Schneider

@flavioschneide

7 months

@Scobleizer @elevenlabsio Glad you like it! [Here's the embed for the lazy:]

1

0

3

Flavio Schneider

@flavioschneide

2 years

#StableDiffusion

0

3

Flavio Schneider

@flavioschneide

1 year

@3DX3EM Yeah! Cloning is also just a few lines of code.

0

2

Flavio Schneider

@flavioschneide

2 years

Added new Extract feature to surgeon-pytorch, allowing you to extract sub-graphs of @PyTorch models using symbolic tracing – much better than Inspect ( @rasbt ). Easily get any intermediate function output, and change input nodes.

0

1

Flavio Schneider

@flavioschneide

7 months

@_akhaliq @computerender @elevendubz spanish

1

0