Add stuff here
Add stuff here
Add stuff here
- Frontend where user can upload
- Upload the video to bucket (Creating a bucket to store temporary stuff).
- Parse audio from video file.
- Transcribe the audio (Ask user for expected keywords in speech).
- Translate the Transcription to user desired language.
- Convert text to speech.
- Clone the voice to match with subject(s).
- Use neural puppetry to match facial expression (Optional, Too expensive).
- Slow down or speed up the resulting audio to watch with original source (I dont think i'll do this but if anyone wants welcome).
- Merge the audio with video.