LatentSync
Audio Conditioned LipSync with Latent Diffusion Models
Transcribe audio files to text with timestamps
F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)
Edit an image based on the given instruction.
Browse apps made with DeepSite
New Ghibli EasyControl model is now released!!
Generate realistic dialogue from a script, using Dia!