video-podcast-maker

Name: video-podcast-maker
Availability: InStock
Author: niehu2018

Generate a publish-ready video podcast MP4 from a topic input using Azure Speech and Remotion workflows.

Updated Aug 27, 2026

Search Tags:#automation #timing #ffmpeg #tts #remotion #video-podcast #publish-info

Ready to run

npx skills add https://github.com/niehu2018/video-podcast-maker --skill video-podcast-maker

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: video-podcast-maker
Source: https://github.com/niehu2018/video-podcast-maker/tree/main
Command: npx skills add https://github.com/niehu2018/video-podcast-maker --skill video-podcast-maker

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The pipeline automates the end-to-end creation of a professional video podcast from a user-provided topic, handling research, script writing, TTS audio synthesis, Remotion video rendering, and final MP4 assembly with optional background music and subtitles.

Core Features & Use Cases

Research, script generation, AI TTS, and Remotion-based video composition to deliver a publish-ready podcast from a single topic input.
Supports 4K output, subtitle embedding, and Bilibili optimizations, including chapter timing and thumbnail generation.

Quick Start

Provide a topic and let the system generate research notes, a narrated script, TTS audio, Remotion video, and the final MP4 ready for publication.

Frequently Asked Questions about video-podcast-maker

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I automate video podcast creation from a single topic input?▼

Automated video podcast creation uses a topic-to-podcast pipeline that researches subjects, writes scripts, generates AI TTS audio, and renders Remotion video to output a publish-ready MP4 file end-to-end.

What's the best way to generate TTS audio and sync it with Remotion video rendering?▼

The best way to sync TTS audio with Remotion video rendering is using a timing-driven synchronization workflow that processes Azure Speech outputs and robustly handles silent sections to ensure accurate audio-video alignment.

Do I need Azure Speech and FFmpeg to produce an end-to-end MP4 podcast?▼

Yes, producing an end-to-end MP4 podcast requires an Azure Speech environment for AI TTS synthesis, FFmpeg for final MP4 assembly, and Python or Node.js environments to orchestrate the Remotion video rendering pipeline.

Can I optimize video podcast output for Bilibili with subtitles and chapter timing?▼

Yes, you can optimize video podcast output for Bilibili by embedding subtitles, generating chapter timing, and creating optional thumbnails to meet platform-specific publication requirements.

How does timing-driven synchronization handle silent sections during TTS audio processing?▼

Timing-driven synchronization handles silent TTS sections by applying robust processing logic during Remotion video composition, ensuring continuous audio-video alignment without timeline drift or rendering desynchronization.

What are the limitations of automating video podcast production with Remotion and FFmpeg?▼

Limitations of automating video podcast production include dependency on specific Python or Node.js environments, Azure Speech configurations, and timing-driven synchronization constraints across Remotion and FFmpeg rendering stages.