a notebook that uses different open source AI models to transcribe, translate the audio of a video, as well as being able to export the final result of the video already translated with an AI generated voice.
- we are looking for a realistic open source voice generation model to make the result more pleasant.
- we are looking for a way to adjust the timing of the dubbing to the real video, resulting in a voice that fits more closely to the beginning and end of the mouth movement.