seedance-podcast-visual

seedance-podcast-visual is a skill for Claude Code, Codex from rediumvex/ai-video-generator-claude. It costs 90 tokens per session (5,768 once invoked), scanned A, original, MIT.

A guide for writing prompts that turn podcast or interview audio into short visual videos with Seedance 2.0 on Higgsfield. It uses audio, transcripts, speaker context, and visual references to plan the result.

In plain words
What is it for?
Planning podcast clips, interview highlights, quote videos, and other short audio-led content for platforms such as TikTok, Reels, Shorts, or LinkedIn.
Why use it?
It helps replace a static audiogram with a visual sequence that follows the spoken content and fits a chosen platform and format.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Planning podcast clips, interview highlights, quote videos, and other short audio-led content for platforms such as TikTok, Reels, Shorts, or LinkedIn.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rediumvex/ai-video-generator-claude/10-podcast-visual
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add rediumvex/ai-video-generator-claude --skill 10-podcast-visual
Clone the repo
git clone --depth 1 https://github.com/rediumvex/ai-video-generator-claude

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for seedance-podcast-visual

README.md
[![agentmods](https://agentmods.dev/badge/skills/rediumvex/ai-video-generator-claude/10-podcast-visual/github.svg)](https://agentmods.dev/skills/rediumvex/ai-video-generator-claude/10-podcast-visual)
Your own site
<a href="https://agentmods.dev/skills/rediumvex/ai-video-generator-claude/10-podcast-visual"><img src="https://agentmods.dev/badge/skills/rediumvex/ai-video-generator-claude/10-podcast-visual/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for seedance-podcast-visual

Your own site · 80×15
<a href="https://agentmods.dev/skills/rediumvex/ai-video-generator-claude/10-podcast-visual"><img src="https://agentmods.dev/badge/skills/rediumvex/ai-video-generator-claude/10-podcast-visual.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,768 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00090 $0.05768
Opus 5 $0.00045 $0.02884
Sonnet 5 $0.00018 $0.01154
Haiku 4.5 $0.00009 $0.00577

Measured 12d ago against content hash 62a8cf049983, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

seedance-podcast-visual scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/10-podcast-visual/SKILL.md · 367 lines

How it starts

The opening of the file, as written. The whole thing — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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 energy level: seated calm, animated gesturing, emotional peak

Philosophy

Old model (audiogram) New model (podcast visual)
Show the waveform Show what the words feel like
Static background image Constructed cinematic environment
Speaker photo as thumbnail Speaker reconstructed in scene
Generic brand colors Lighting and atmosphere matched to tone
Passive viewing Active emotional engagement
Optimized for "audio on" Compelling even on mute

Read the full file on GitHub · 367 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 367 lines · 90 tokens per session scan A 62a8cf049983

Subscribe to this mod's changes

seedance-podcast-visual is a skill published in the GitHub repository rediumvex/ai-video-generator-claude (361 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 5,768 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

linkedin-humanizer

Remove the AI tells human readers and LinkedIn's AI-slop filter react to in a post or comment: 2026 vocabulary by paragraph density, reveal bridges, staccato fragments, stacked triads, performed sincerity. Tiered rewriter (forensic / strict / aesthetic / all) plus --mode audit pass-fail review and --mode profile voice…

sergebulaev/linkedin-skills · 124 tokens

linkedin-marketing

Plan, draft, audit, and publish LinkedIn posts and comments. Use when the user wants to write a viral LinkedIn post, draft a comment or reply on any LinkedIn post URL, audit a draft against 2026 algorithm heuristics, remove AI tells, extract hook formulas from viral posts, or plan a week of content. Powered by the…

sergebulaev/linkedin-skills · 97 tokens

linkedin-reply-handler

Draft a reply to a specific existing LinkedIn comment from its URL. Use when the user wants to reply to a comment on any post, or follow up after an author replied to them. Parses the commentUrn, resolves the correct parentComment target (LinkedIn flattens threads to 2 levels), and posts via Publora on approval. Not…

sergebulaev/linkedin-skills · 88 tokens

linkedin-post-writer

Draft a new LinkedIn post from scratch using one of 20 2026 hook formulas (anaphora, R.I.P., time-anchor, curiosity-gap, contrarian, controlled A/B, false-binary, and more) plus a founders-edition angle library, picked by engagement goal (comments, reposts, likes, saves). Runs the humanizer pass and schedules via…

sergebulaev/linkedin-skills · 120 tokens

linkedin-comment-drafter

Draft a LinkedIn comment on someone else's post from its URL, or reshare (repost) it to your feed with optional commentary. Use when the user pastes a post URL and asks to comment, engage, be first commenter, or repost with their thoughts. Produces 1-3 variants in the user's voice, picks a reaction, and publishes via…

sergebulaev/linkedin-skills · 97 tokens

linkedin-content-planner

Generate a 7-day LinkedIn content plan from a theme, audience, and pillars. Produces per-day post pillar, format, hook type, CTA, posting time, daily comment targets, and a weekly inbound-readiness check. Use when the user wants to plan a week or month of content, not draft a single post.

sergebulaev/linkedin-skills · 72 tokens