Omnilingual ASR Media Transcription
Transcribe audio or video into text in multiple languages
Transcribe audio or video into text in multiple languages
Generate speech using reference audio and text
Enhance and upscale short videos using AI
generate a video from an image with a text prompt
Fast, multi-speaker TTS (44.1kHz) with voice cloning
Generate higher quality Python with a clened DeepSeek-Coder.
Edit and guide image generation
Door number recognition
Piano Sound Quality Classifier
HEp2 cell image classifier
Retrieve image model information and generate JSON data
Discriminator of Bel Canto and Chinese Folk Singing
Online programming aids
Generate speech from text in multiple languages
Convert spoken words into text
Erhu Performance Technique Recognizer
Generate captions for images in various styles
Convert figured bass to chord
Enhance and upscale images with advanced models
Frame-level guzheng playing technique detector
Chinese Music Pentatonic Mode Detector
Chinese Traditional Instrument Sound Retriever
Guzheng Performance Technique Recognizer
Test Simple Mail Transfer Protocol (SMTP)