Space

Launch a medical case simulation where AI agents act as doctor, nurse, and patient in a spoken dialogue.

This demo converts entered text into spoken audio with selectable voice options.

Upload an image for CLIP analysis and receive a text prompt describing it that can help recreate similar artwork.

Synesthesia in Space asks players to navigate space puzzles and save a loved one.

This app transcribes spoken Tunisian Arabic into text using Arabic characters.

This app presents a scrollable timeline of AI model announcements during 2024 with filters for open-source models.

This demo generates responses for a trust game after users choose a persona and game type.

MMAudio generates sound for a short video or creates an audio clip from a text prompt.

Upload an image to generate a detailed text prompt that can be used to recreate it with an image model.

This app displays a real-time simulation of autonomous AI traders buying and selling in a virtual market.

Moe TTS generates speech from text and can convert existing audio to another speaker’s voice.

This cybersecurity agent scans security logs and files for threats and recommends mitigations.

This Hugging Face Space displays the README for a curated list of AI web search software.

This Hugging Face Space creates a GIF from an image and a prompt, with settings for negative prompts and generation steps.

OpenPuppies displays animated puppy GIFs when visitors press the space bar.

This app creates product advertisements and images, analyzes social sentiment, and suggests posting times.

This app plans, writes, and edits blog articles with multiple AI agents.

This tool converts Sindhi text into speech and lets users choose a voice gender.

VBench lets users upload model evaluation files to update a video generation benchmark.

This data science agent helps clean datasets, create visualizations and models, and generate reports.

This app returns a buy, hold, or sell recommendation with reasons for a stock ticker.

The Hugging Face Space by Hugorowan is labeled as a project for turning images into videos.

This speech recognition app transcribes audio uploaded as a file, recorded by microphone, or provided through a URL.

The S4 repository presents structured state space sequence models for sequence modeling research.