Hindi Speech Model should be free and open-source. And... we’re making it happen. >High quality >Multiple voices >UI to generate audio + API for deployment Follow me to get notified when it launches. Listen to the audio till the end!show more

We're making building with the text-to-speech API even easier... by adding it to the Playground! Just enter a message to generate audio in one of six preset voices.show more

Breaking: Pika launches the first near-real-time HD audio-driven performance... model > Selfie + sound clip -> hyper-realistic, expressive videos > Works in any style: photorealistic, anime, pixel art, fantasy > 6 sec to generate, 20x faster & cheaper 9 Impressive examples 👇show more

Wan 2.2 Speech-to-Video 14B just landed > audio-driven cinematic... video generation > weights & demo on the hub > apache 2.0 license + looks like it could be compatiable with Wan 2.x LoRAs out-of-the-boxshow more

Love when the high low is executed from a... big to a guard >>> Kalani Brown dishes it off to Celeste Taylor 🫡 LVA-PHX | Watch FREE on the WNBA APPshow more

Stable Audio 3 by Stability AI is just out... It mainly comes with 3 open source variants: - Stable Audio 3 Medium (2B) - Stable Audio 3 Small (0.6B) - Music - Stable Audio 3 Small (0.6B) - VFX (and a "large" closed variant) The open models are really fast and high qualityshow more

When J. Cole puts each of his mixtapes on... streaming to coincide with his audio docuseries episodes all leading up to The Fall Off >>>show more

NVIDIA's PiD is a new pixel diffusion decoder for... high-res image models. It skips decode-then-upscale stop, making sharper outputs faster. > Directly generates 4K images > Up to 5.9x faster than SeedVR2 > Free & open weightsshow more

There’s just something about a tropical brunette ❤️🍓well-built, stunning,... and dangerously hard to ignore >>>> Just watch till the end ❤️🍓show more

“Even though each of us is very active with... our solo activities, we’ve talked a lot among the members about putting the team first as a priority. When it’s time for us to work as a group, we should really do it and prioritize it more.” ㅡ Chanyeol, 2025 his loyalty >>>>>>>>show more

We've got a new audio-conditioned video model 👀 LTX... Studio now lets you upload or generate audio, and then creates a lip-synced video. This is going to be HUGE for consistent character voices + AI influencers. I tested it w/ an animation of my pets. More on how to use it 👇show more

Holy smoke... Hunyuan3D 2.0 MV is impressive (and open... source 🫨) ➡️ You can generate a mesh from multiple images in just seconds. Next workflow: effortlessly create a consistent turnaround on Scenario > then generate the mesh from it.show more

Chat GPT 4o released their API it is INSANE... for static ads! We made a tool to generate 10 static ads in one click: > upload a reference image > write your prompt > get 10 static ads in 2min It's live today! Comment Arcads to get early access 👇show more

I gave it audio! >:3c

Growing up this happened to be one of the... most covered part 🤔 We go extra miles to see it But today>>>>>>>>>>>show more

> Don't be like Sourav Joshi > Treat wife... as cameraman > Ignore her > Used her for views and content creation > Actually doesn't love her > Don't listen to her > No love seen from him till now Everything seems like a formalityshow more

People that actually think outside the box >>>>>> This... is a breath of fresh air from the usual they want to use and finish us. The fact that it looks appetizing....I rate it a 💯 abeg Would you be willing to try this out?show more

This popular streamer, Duke Dennis and his love for... Beyoncé>>> “You don’t listen to Beyoncé? Then who the fuck do you listen to” 🤣👏👏👏show more

> releases weights > releases the tech report >... open sources most of the production code > explains economics with deployment statistics > for good measure, writes a paper with full design rationale and hardware design recommendations > 50K hoppers cultists will still be madshow more