Skip to main content
Glama
Sign In
YoutuberBox

YoutuberBox

by saroby
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript

YoutuberBox

Faceless YouTube video automation MCP server — shorts (9:16) and long-form (16:9).

The connected LLM does the creative work (script, scene beats, image prompts); YoutuberBox does the execution: TTS narration via voicebox, AI images via CodexImage, whisper-timed burned-in captions, and ffmpeg assembly with Ken Burns motion. Built-in quality guardrails push output away from AI slop.

Pipeline

create_project → set_script → generate_narration ┐
                              generate_images    ├→ generate_captions → assemble_video
                                                 ┘

Tool

What it does

create_project

New project (shorts 1080×1920 / long 1920×1080), returns the quality guide

set_script

LLM-authored scenes (narration + 1–3 image prompts each), returns pacing/quality lint warnings

generate_narration

Per-scene TTS via voicebox (/generate/stream); reports durations; per-scene regeneration via sceneIds

generate_images

Per-scene images via CodexImage; 2–3 prompts per scene = intra-scene cuts; consistent style anchor

generate_captions

Word timestamps via mlx_whisper/whisper (proportional fallback) → karaoke word-highlight ASS; position/highlightColor knobs

assemble_video

Ken Burns per still (alternating direction), cuts every few seconds, caption burn-in, looped/ducked BGM, −14 LUFS loudnorm

list_voices

Voicebox voice profiles so the LLM picks a fitting narrator

generate_thumbnail

Text-free thumbnail via CodexImage (add typography yourself — AI text is a slop tell)

project_status

Pipeline state per scene

Resource: guide://quality — the anti-slop guide (hooks, pacing targets, image prompt rules, mix levels).

Related MCP server: Orbixio Studio

Requirements

  • Node.js 20+

  • ffmpeg / ffprobe on PATH

  • voicebox for TTS

  • CodexImage for image generation

  • Optional: mlx_whisper or whisper CLI for word-accurate caption timing

Install

npm install
npm run build

Register with your MCP client (e.g. Claude Code):

{
  "mcpServers": {
    "youtuberbox": {
      "command": "node",
      "args": ["/path/to/YoutuberBox/dist/index.js"]
    }
  }
}

Projects land in ~/YoutuberBox/projects/<id>/ (override with YOUTUBERBOX_HOME).

Configuration

Env var

Default

Purpose

VOICEBOX_URL

http://127.0.0.1:17493

Voicebox REST API (run the Voicebox app)

CODEXIMAGE_URL

— (required)

CodexImage server base URL

CODEXIMAGE_API_KEY

— (required)

CodexImage API token (Bearer)

CODEXIMAGE_QUALITY

medium

low | medium | high

YOUTUBERBOX_HOME

~/YoutuberBox

Where projects and renders are stored

Voice selection: pass voice to create_project/generate_narration as a Voicebox profile name or id; defaults to your first profile.

Captions: if your ffmpeg has libass, captions are burned in (styled, word-group pop for shorts). Otherwise they're muxed as a soft mov_text track and the tool tells you how to upgrade.

Design notes

Ideas borrowed from the best of the ecosystem: granular execution tools the LLM orchestrates (stephengpope/remotion-media-mcp) instead of a single god-tool (gyoridavid/short-video-maker's create-short-video); scene = {narration, visual spec} as the exchange format and dual-aspect maturity (MoneyPrinterTurbo); LLM-authored structure over hidden config (ShortGPT's edit-markup thesis); karaoke captions and voice discovery endpoints (short-video-maker); motion-on-stills + a cut every few seconds — the #1 documented "AI slop" complaint is static visuals.

The deliberate difference: no built-in script generation — the LLM you connect writes the script with full context of your channel and audience, and the server lints it against pacing/quality rules (hook length, words/sec, cliché openers, text-in-image prompts, static-scene warnings) instead of generating generic content itself.

License

MIT

Available Tools

8 tools
assemble_videoA

Render the final video: Ken Burns motion per scene (alternating direction), concat, optional caption burn-in, optional background music (looped, ducked), loudness-normalized to -14 LUFS. Returns the output path.

Inputs: projectId (required), bgmPath, captions, bgmVolumeDb.

create_projectA

Start a new faceless video project. format 'shorts' = 1080x1920 vertical (<60s), 'long' = 1920x1080. Returns the project id used by all other tools, plus the quality guide you should follow when writing the script.

Inputs: title (required), format (required), voice, language, +1 more.

generate_captionsA

Build burned-in captions from the narration audio. Uses whisper word timestamps when available (mlx_whisper or whisper CLI), otherwise proportional timing. Shorts get karaoke word-highlight. Run after generate_narration.

Inputs: projectId (required), position, highlightColor.

generate_imagesB

Generate one image per scene (or the listed sceneIds) with CodexImage, at the project aspect ratio. The project imageStyle is appended to every prompt for visual consistency.

Inputs: projectId (required), sceneIds.

generate_narrationA

Synthesize narration audio for every scene (or the listed sceneIds) with voicebox TTS. Returns per-scene durations.

Inputs: projectId (required), voice, sceneIds.

generate_thumbnailA

Generate a text-free thumbnail image via CodexImage (1536x1024 landscape for long-form, 1024x1536 for shorts). Prompt one dramatic subject with strong lighting — add title text later in an editor.

Inputs: prompt (required), projectId (required).

list_voicesA

List available voicebox voice profiles (name + id) so you can pick a fitting narrator.

Inputs: no named parameters.

set_scriptA

Set (or replace) the full scene list: per scene one narration passage and one image prompt. You are the writer — bring a hook, concrete details, and one idea per scene. Returns pacing/quality warnings; fix them before generating assets.

Inputs: scenes (required), projectId (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A4/5.0

    Scored across 8 tools

    Disambiguation5/5

    Each tool has a distinct, non-overlapping purpose, covering the entire video creation pipeline. There is no ambiguity about which tool to use for a given task.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern (e.g., create_project, set_script, generate_narration), making them predictable and easy to understand.

    Tool Count5/5

    With 8 tools, the set is well-scoped for a faceless video creation workflow. Each tool serves a necessary step without being too few or too many.

    Completeness4/5

    The tools cover the core workflow (create project, script, generate assets, assemble, thumbnail) but lack scene-level editing or project management features, which are minor gaps.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers

    • WhisperCUT

      wallpapa
      F
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that automates short-form video production for TikTok, Instagram Reels, and YouTube Shorts, using AI agents and behavioral science to generate production-ready videos from a topic and vibe.
      1
      -

    Appeared in Searches