Agents365-ai/video-podcast-maker

Topic → 4K narrated video for coding agents. v4.0: all TTS via the ttsCN engine component (11 platforms incl. MiniMax voice clone, native word-level subtitle sync), manifest-based Asset Engine, Remotion composition, cost-gated AI generation

What it solves

It automates the complex process of turning a simple topic into a professional 4K video podcast. It eliminates the need for manual research, scriptwriting, voice recording, and video editing by coordinating several AI tools into a single pipeline.

How it works

Users provide a topic to a coding agent (like Claude Code), which then orchestrates a multi-step workflow:

  1. Research & Scripting: The agent researches the topic and generates a narration script (podcast.txt).
  2. Audio Generation: It uses the ttscn bridge to synthesize speech via one of 11 supported TTS backends (including OpenAI, Azure, and ElevenLabs).
  3. Visual Composition: It utilizes Remotion to compose the video, integrating AI-generated stills, B-roll, and overlays.
  4. Rendering: The final output is rendered in 4K with native subtitles and background music mixed in via FFmpeg.
  5. Optimization: It can generate 9:16 vertical shorts from long-form content and adapt formatting for platforms like YouTube, Bilibili, and TikTok.

Who it’s for

Content creators and podcasters who want to produce high-quality video content quickly without needing deep technical skills in video editing or audio engineering.

Highlights

  • Extensive TTS Support: Integrates 11 different text-to-speech engines for diverse voice options.
  • 4K Production: Renders high-resolution video with React-based subtitles via Remotion.
  • Multi-Platform Ready: Tailors output and publishing info for Bilibili, YouTube, Xiaohongshu, Douyin, and WeChat Channels.
  • Asset Integration: Connects with various AI engines for stock footage, AI stills, and B-roll.
  • Pronunciation Control: Includes global and per-project phoneme dictionaries to fix TTS mispronunciations.

Related

  • Project
    naqashafzal/AI-Content-Studio

    An AI-powered studio that automates the entire YouTube video creation process, from research and scriptwriting to voice generation, video production, and direct publishing.

  • Project
    xhongc/ai_story

    An AI-driven automation platform that transforms a story theme into a complete video by automating scriptwriting, storyboarding, image generation, and video production.

  • Project
    ATH-MaaS/Pixelle-Video

    An AI-powered automated short-video engine that generates scripts, visuals, and voiceovers from a single topic to create complete videos without manual editing.

  • Project
    myccarl/ai-shortVideo-pipeline

    An end-to-end automated pipeline for producing short-form AI videos, covering everything from topic discovery and scripting to visual generation and post-production.

  • Project
    zenstory-ai/video-recap-skills

    An AI-powered pipeline that transforms videos into narrated Chinese recap videos by automating scene understanding, scriptwriting, voiceover generation, and video assembly.