A documentary filmmaker wants to reach a wider audience by automatically adding subtitles and voice-overs in multiple languages. Which combination of steps will accomplish this? (Choose two.)

To generate subtitles in other languages, you first need to convert the audio from the documentary into text. Amazon Transcribe is the appropriate service for this, as it provides automatic speech recognition (ASR). Once the audio is transcribed, Amazon Translate can then translate this text into multiple target languages for the subtitles. For voice-overs, after the original audio is transcribed and translated into the desired languages, Amazon Polly is used to convert this translated text into lifelike speech. Polly offers text-to-speech (TTS) capabilities, allowing for the creation of natural-sounding voice-overs. Incorrect options: Amazon Textract is an OCR service for extracting text from documents and images, not audio, so it cannot be used for transcribing spoken content or generating voice-overs. Amazon Translate is for text translation, not for generating speech from text; therefore, it cannot directly create voice-overs.