Everything in the catalog

Generates matching sound effects for a video clip.

Generates custom songs from structured text prompts in a studio-style interface.

Syncs the lips in a face video to a new audio track.

Hosted chat with Qwen3 models, with an optional thinking mode.

Turns text into speech with the Kitten TTS 2 model and the open-source 0.8 models.

Chat with Gemma 3 12B, with image input and an adjustable system prompt.

Transcribes audio or video with faster-whisper and can translate the result, with subtitle export.

Restores and colorizes old or damaged family photos.

Describes an image as a prompt suitable for FLUX generation.

Finds and masks personal data such as names and emails in text using Microsoft Presidio.

OCRs a scanned PDF and returns the recognised text.

Generates a recipe from a list of ingredients.

Segments objects in an image from point clicks or boxes with the SAM 2 model.

Chat playground that downloads open models and runs them locally on WebGPU with WebLLM.

Chat with a compact vision-language model about images you upload.

Reads text and layout from document images with the dots.ocr model.

Summarises long passages by splitting them into chunks and condensing each with a seq2seq model.

Predicts a depth map from a single photo with DPT.

Generates music from a text prompt and streams the audio as it is made.

Runs Phi-1 and Phi-2 text generation in WebAssembly through Rust Candle with no server.

Generates FLUX.1 dev images and can caption an input picture to build the prompt.

Converts a video into several anime styles.

Generates a full-body anime character image from a random seed with a GAN.

Generates multi-instrument MIDI music with a transformer model.