Cohere Transcribe WebGPU
β‘
38
Run Cohere Transcribe locally in your browser on WebGPU.
Generate speech from text using a reference audio
Upgraded to v1.0!
Remove noise from images
Generate a video transitioning between two images
Explore speech model benchmarks and request new evaluations
Video Super-Resolution with Text-to-Video Model
Enhance and upscale images with face restoration
Segment objects in a video with clickβbased masks
Clean and restore noisy scanned documents
Request evaluation for a new model
Convert a GitHub repo to a text file for any LLM to use