TMElyralab/MuseTalk
real-time high quality audio-driven lip-syncing for video dubbing
View on index · View in 3D Map
Related repos
- audio-driven video dubbing with unlimited length and accurate lip sync
- Automates video creation from text-to-speech and motion graphics
- automates 2D lip sync animation from audio for games and cartoons
- offline audio and video transcription with whisper, batch support, privacy focused
- generates synchronized talking head videos from audio and reference images
- open-source text-to-speech with voice cloning and emotion control
- Lip-syncs any video to an audio track
- Lip-sync videos to audio using a diffusion model
- open source model for long-form, multi-speaker text-to-speech
- Transcribes audio streams in real-time
