Running on T4 373 373 HierSpeech++ (Zero-shot TTS) β‘ Generate high-quality speech from text using a prompt audio
pyannote/speaker-diarization-3.1 Automatic Speech Recognition β’ Updated May 10, 2024 β’ 10.8M β’ 672
stabilityai/stable-video-diffusion-img2vid-xt Image-to-Video β’ Updated Jul 10, 2024 β’ 399k β’ 2.85k
Running 84 84 Gradio Lipsync Wav2lip π Combine audio with a video or image to create a lip-synched video