seedance-podcast-visual

# Podcast Visual — Audio-to-Video Transformation Prompts Transform podcast audio into cinematic visual content using Seedance 2.0 on Higgsfield. This skill produces video prompts that replace static audiograms with storytelling-driven visual experiences built entirely from constructed imagery. --- ## Input Specifications **Primary inputs:** - Up to 3 audio files (podcast clips, interview excerpts, sound bites, episode highlights) - Transcript or key quote text from the audio - Speaker name(s) and brief context (topic, show name, tone) - Desired visual style (abstract, cinematic, interview reconstruction, kinetic) - Target platform (Instagram Reels, YouTube Shorts, LinkedIn, TikTok) - Aspect ratio: 9:16 (vertical/mobile-first), 16:9 (widescreen), or 1:1 (square) **Audio file handling:** - File 1: Primary clip — the main sound bite or key quote being visualized - File 2 (optional): Intro or context clip — sets up the narrative before the hook - File 3 (optional): Reaction or follow-up clip — speaker response, co-host moment, audience reaction - Duration guidance: each clip should be 15–90 seconds; total sequence up to 3 minutes **What you extract from audio before writing prompts:** - The single most quotable sentence (becomes the visual anchor) - The emotional register: contemplative, fired-up, vulnerable, instructive, funny - Pacing: fast and punchy vs. slow and deliberate delivery - Natural pauses: where silence lives (these become visual breath moments) - Speaker ener...