sieve
/
dubbing
Visual detail to process at
Frame rate to process video at
Speeds up processing at the cost of quality
Use the transcript as context. Increases cost.
# Video dubbing in a few lines of code
transcribe = sieve.function.get("sieve/whisper")
translate = sieve.function.get("sieve/translate")
tts = sieve.function.get("sieve/xtts")
sync = sieve.function.get("sieve/video_retalking")
# Transcribe, translate, and generate audio
transcript = transcribe.run(source_video)
translated = translate.run(text, "eng", language)
speech = tts.run(source_audio, language, translated)
# Lipsync dubbed audio!
dubbed_video = sync.run(source_video, speech)