Docker

This Kokoro TTS demo converts English text into speech with selectable voices and speaking speed.

This demo turns entered text into speech and provides an audio file for playback.

AgentSeer visualizes AI agent decision processes as diagrams based on supplied agent information.

The NVIDIA Parakeet-TDT Hugging Face demo turns uploaded or recorded speech into text.

Scriptura helps create screenplays, storyboards, and soundtracks through automated analysis and media generation.

The MTEB leaderboard compares embedding models across tasks such as retrieval and language evaluation, with scores filterable by task or category.

This Hugging Face Space accepts a meeting recording or URL, then transcribes, translates, and summarizes the audio and extracts key points.

AnyCoder turns a short app or page description into code for formats including HTML, React, Gradio, and Streamlit.

This app turns uploaded documents into a presentation plan, images, audio, and a static HTML slide deck.

This app converts typed text to speech, with voice selection and controls for speech speed and pitch.

This data science app cleans uploaded datasets, explores statistics, builds models, and generates reports.

This image classifier checks uploaded images for inappropriate or adult content.

RewardBench displays model scores across evaluation categories and lets visitors filter the leaderboard by model name or type.

Open VLM Leaderboard displays model and dataset rankings in an interactive table with filters for evaluation dimensions and model properties.

This Wan2.2 demo generates short videos from a prompt, with options for image input, size, length, style, and LoRA modules.

This app converts entered text into speech and lets users choose a language or model.

This app explains science questions or uploaded images and PDFs with diagrams, quizzes, and downloadable reports.