Video Podcast Maker

中文文档

Automated pipeline to create professional video podcasts from a topic. Supports Bilibili, YouTube, Xiaohongshu, Douyin, and WeChat Channels with multi-language output (zh-CN, en-US). Combines research, script generation, local TTS (edge free, plus azure), Remotion rendering, and FFmpeg mixing. Current release: v5.3.0 — see CHANGELOG.md for version history.

Works with: Claude Code · OpenClaw · OpenCode · Codex · Pi — any coding agent that supports SKILL.md

Publish to: Bilibili · YouTube · Xiaohongshu · Douyin · WeChat Channels

No coding required! Just describe your topic in plain language — the coding agent guides you through each step interactively. You make creative decisions, the agent handles all the technical details.

Note: This project is still under active development and may not be fully mature yet. Your feedback is greatly appreciated — feel free to open an issue.

Features

• Topic → 4K video - research, narration script, TTS audio, Remotion composition, 4K render + BGM in one pipeline
• Local TTS backends - Edge (free, no key) and Azure — synthesized in-house, no external component skill required
• Asset engine - per-video manifest with license provenance; producers are user files, assetseeker stock, imagencn AI stills, videogencn AI B-roll, and Hyperframes overlays — paid generation always asks first
• 4K output + Remotion-native subtitles - 3840×2160; SRT rendered in React at 4K (legacy FFmpeg burn-in available)
• Design learning - extract style profiles from reference videos/images; auto-applied when topics match
• Vertical shorts - 9:16 highlight clips generated from long-form sections
• Multi-platform & multi-language - Bilibili / YouTube / Xiaohongshu / Douyin / WeChat Channels × zh-CN / en-US, with per-platform publish info
• Pronunciation control - global + per-project phoneme dictionaries for Chinese polyphones

Quick Start

1. Install: with the skills CLI, pointing at the full skill:

npx skills add Agents365-ai/video-podcast-maker/skills/video-podcast-maker -g

Drop the /skills/video-podcast-maker suffix to install all three variants (full, -lite, -nano), or clone this repo instead. Paths below are written from the repo root; under a skills CLI install the same files live in the agent's ${SKILL_DIR}.

2. Set up — Python 3.8+, Node.js 18+, FFmpeg, and a Remotion project:

brew install ffmpeg node python3          # macOS (Ubuntu: sudo apt install ffmpeg nodejs python3)
pip install -r skills/video-podcast-maker/requirements.txt
npx create-video@latest my-video-project   # or reuse an existing Remotion project
cd my-video-project && npm i

One-time cost: a fresh Remotion project downloads ~2.2 GB of npm packages plus a ~90 MB Chrome headless shell. Prefer reusing an existing Remotion project (with node_modules/ already installed) for your next video — the heavy install happens once per project, not per video. Lottie animations are optional (@remotion/lottie + lottie-web); install them per project only if you use LottieAnimation.

3. Configure — set TTS_BACKEND plus its API keys (see TTS Backends and Environment Variables).

4. Tell your agent:

"Create a video podcast about [your topic]"

The agent runs the whole workflow (research → script → TTS → Remotion composition → Studio review → 4K render + BGM). Preview and iterate in Remotion Studio (npx remotion studio src/remotion/index.ts); the agent waits for your explicit "render 4K" confirmation before the final render.

⚠️ For the human reading this (not the AI): manually polish podcast.txt, repeatedly

This section is for you, the human — not the agent. Every downstream step — TTS narration, subtitles, section transitions, animation timing, final cut — is derived from this single podcast.txt. A weak script renders into 4K garbage. No amount of polish downstream saves it.

The AI-generated draft is a starting point, nothing more. Do these yourself — don't hand them off to the AI:

1. Mentally read it as the narrator. Treat each sentence as one breath — if a line forces you to "catch your breath" or backtrack to parse, fix it. Where you stumble silently is where TTS stumbles audibly.
2. Revise at least three times.
   • Pass 1: typos, awkward phrasing, tongue-twisters
   • Pass 2: cut filler, cut throat-clearing intros ("So today we're going to talk about…"), cut redundancy
   • Pass 3: tune rhythm — where to pause, where to break a long sentence, which word carries the stress
3. Read each [SECTION:xxx] block end-to-end. Confirm each section opens with a hook and lands a clean transition into the next — not a bullet-point dump.
4. Audit numbers, proper nouns, and English terms separately. ~90% of TTS mispronunciations live here. If pronunciation is wrong, add it to phonemes.json; if it just sounds awkward, rewrite it.
5. Know your length budget. Estimate ~280 zh-CN chars/min or ~150 en words/min. A 5–10 min video means ~1400–2800 chars / 750–1500 words. Don't pad to fill time.

The only acceptance test: read through it once in your head — does any line make you wince? If yes, don't move on to Step 7 (TTS) yet. Otherwise you're just rendering 4K of something even you don't want to hear.

Workflow

Related Skills

Variants in this repo (skills/):

• video-podcast-maker — the full production pipeline (this README's subject)
• video-podcast-maker-lite — minimal personal pipeline: Azure SSML TTS + Remotion, no bundled templates
• video-podcast-maker-nano — tool-agnostic, logic-only pipeline (any TTS backend, any video tool); autonomous by default, oversight configured per project

External skills:

• remotion-best-practices - recommended; core Remotion patterns and guidelines (built-in minimum rules if absent)
• assetseeker - optional; license-vetted stock photos/video/BGM/SFX/icons/fonts
• imagencn - optional; AI stills and thumbnails (paid APIs)
• videogencn - optional; AI video clips for B-roll (paid APIs)
• Hyperframes - optional; transparent overlay animations (Node 22+)

Requirements

Installed through the skills CLI? SKILL.md, scripts, and templates then live under the agent's ${SKILL_DIR}; paths in this README are written from the repo-root perspective, which is what a clone gives you.

TTS Backends (local)

TTS synthesis is in-house — no external component skill required. Set TTS_BACKEND to a platform id; only the active platform's env vars are needed:

Want more platforms? The former ttscn component skill (cosyvoice, doubao, tencent, baidu, minimax, xunfei, elevenlabs, openai, google) is no longer a dependency. Install it separately and call it directly if you need those.

Environment Variables

Add to ~/.zshrc or ~/.bashrc:

export TTS_BACKEND="edge"                  # edge (default) / azure
export TTS_VOICE="zh-CN-XiaoxiaoNeural"    # optional; unset = backend default
export TTS_RATE="+5%"                      # optional; also settable in user_prefs.json (global.tts.rate)
export TTS_STYLE="gentle"                  # optional; azure only
export AZURE_SPEECH_KEY="..."              # keys for azure (see table above)
export AZURE_SPEECH_REGION="eastasia"      # azure speech region
export GEMINI_API_KEY="..."                # optional: AI thumbnails (imagencn)
export DASHSCOPE_API_KEY="..."             # optional: AI thumbnails (imagencn; ark/hunyuan/zhipu/step also work)

Then reload: source ~/.zshrc

Configuration

Mutable user-level files live in `~/.video-p