Firefly - Audio/VideoInstall

Summary

Generate a video of a digital avatar speaking content based on either text input or an audio file, with customizable language, voice, avatar, and background settings.

Inputs

• Input Type (required) — Choose whether the avatar video is generated from text or an audio file.
• Script Input (required) — When using text input, provide the text for the avatar to speak or a pre-signed URL to a text file.
• Locale Code (required) — Specify the language code for the speech synthesis when input is text.
• Voice ID (required) — Identify the voice to use for speech synthesis; obtainable via the 'Get Voices' operation.
• Audio URL (required) — When using audio input, provide a pre-signed URL to the WAV audio file.
• Audio Locale Code (required) — Specify the language code associated with the provided audio file.
• Avatar ID (required) — Select the avatar to use for the video; obtain the list via the 'Get Avatars' operation.
• Background Type (required) — Choose the background type for the video: color, image, or video.
• Background Color — Specify the hex color code for a solid color background (visible when 'Background Type' is 'color').
• Background URL — Provide a pre-signed URL to the background image or video (used when 'Background Type' is 'image' or 'video').

Output shape

a JSON object representing the generated avatar video job or result metadata

The output includes details of the submitted avatar video generation job; it does not directly return the video file. You may need to use additional operations to monitor or retrieve the completed video.