Pinned Repositories
auto-reel-edit
Enhance a 9:16 reel video by updating the background and incorporating captions for better engagement.
describe
Incredibly descriptive audiovisual summaries for videos
examples
The code for some apps built with Sieve.
fast-asd
an optimized, production-ready implementation of active speaker detection
pytube
A lightweight, dependency-free Python library (and command-line utility) for downloading YouTube Videos.
sievesync
A quality zero-shot lipsync pipeline built with MuseTalk, LivePortrait, and CodeFormer.
speaker-enhance
Quickly enhance a talking-head video. Cleans/enhances audio, corrects eye-contact, and blurs the background (or adds a custom one)
tortoise-tts
A multi-voice TTS system trained with an emphasis on quality
video-sound-effect
A simple way to generate sound effects for stock videos using AI.
video2dialogue
Transform YouTube Videos into Conversational Avatars with Sieve
Sieve Community's Repositories
sieve-community/examples
The code for some apps built with Sieve.
sieve-community/fast-asd
an optimized, production-ready implementation of active speaker detection
sieve-community/sievesync
A quality zero-shot lipsync pipeline built with MuseTalk, LivePortrait, and CodeFormer.
sieve-community/auto-reel-edit
Enhance a 9:16 reel video by updating the background and incorporating captions for better engagement.
sieve-community/describe
Incredibly descriptive audiovisual summaries for videos
sieve-community/video-sound-effect
A simple way to generate sound effects for stock videos using AI.
sieve-community/speaker-enhance
Quickly enhance a talking-head video. Cleans/enhances audio, corrects eye-contact, and blurs the background (or adds a custom one)
sieve-community/pytube
A lightweight, dependency-free Python library (and command-line utility) for downloading YouTube Videos.
sieve-community/video2dialogue
Transform YouTube Videos into Conversational Avatars with Sieve
sieve-community/hub
sieve-community/StyleTTS
Official Implementation of StyleTTS
sieve-community/tortoise-tts
A multi-voice TTS system trained with an emphasis on quality
sieve-community/urhythmic
Unsupervised Rhythm Modeling for Voice Conversion