Submissions by mvoodarla

Masked Audio Generation Using a Single Non-Autoregressive Transformer

Masked Audio Generation Using a Single Non-Autoregressive Transformer

Sieve (YC W22), the video/audio AI cloud, is hiring ML infrastructure engineers

The most cost-effective audio transcription API

Audiobox Demo: Where anyone can make a sound with an idea

Sieve (YC W22), video/audio AI cloud, is hiring systems engineers

Audiobox: Generating audio from voice and natural language prompts

Improving on open-source for fast, high-quality AI lipsyncing

Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning

Sieve (YC W22), a video/audio AI cloud, is hiring AI/product engineers

Sieve (YC W22), a video/audio AI cloud, is hiring AI engineers

Show HN: State of the art audio enhance (open source AudioSR and DeepFilterNet)

DA-Clip: Controlling Vision-Language Models for Universal Image Restoration

Sieve (YC W22), the video/audio AI cloud, is hiring systems engineers

Voicebox: The first generative AI model for speech to generalize across tasks

DINOv2: State-of-the-art computer vision models with self-supervised learning

Sieve (YC W22) is hiring hackers to build AI infrastructure for video

Sieve (YC W22) is building plug-and-play APIs for video AI

Show HN: TrackObject – Drag-and-drop computer vision object tracking

Sieve (YC W22) is building AI infra for video data, come join us