Takes a video as input and outputs the same video with both spoken and written subtitles in Spanish, replicating each individual voice. Utilizes OpenAI Whisper, Opus NLP, Pyannote and xTTS models.
Takes a video as input and outputs the same video with both spoken and written subtitles in Spanish, replicating each individual voice. Utilizes OpenAI Whisper, Opus NLP, Pyannote and xTTS models.