Everything in the catalog

Text-to-speech demo from the dots team.

Russian text-to-speech.

Makes a 3D object from a single photo using TripoSR.

Analyzes a resume for applicant tracking system fit against a job description.

Enlarges images toward 4K resolution with an AI upscaler.

Music Genre Classifier

Transcribes spoken audio with Qwen3-ASR.

Turns a single image into a 3D model using Tencent's Hunyuan3D 2.1.

Generates a quiz that you can play yourself or let an LLM play.

Speech recognition across several languages with k2-fsa models.

Generates a 3D model from a text prompt or an image using TRELLIS.2.

Upsamples low-quality audio to a higher sampling rate using a neural model.

Quick Whisper Turbo transcription of audio files.

Extracts text from an image in many languages.

Live speech translation: speak or play audio and read the translation as it comes.

wan2.2 fast video generation with high-res stop frames

Whisper-based UI that transcribes audio and makes subtitle files.

General-purpose text translator that runs in the browser as a Hugging Face Space.

Edit video expressions with a free API

Embeds sentences with Qwen3 in the browser and plots them on a 2D scatterplot by meaning.

Search a photo set by describing it in words, with CLIP embeddings computed in the browser.

Generate images from text prompts or edit existing images using one unified AI model.

Now supports inference providers and multimodal.

Private cloud manager for AI coding CLI sessions