skills.rest
NarratorAI-Studio
NarratorAI-StudioOFFICIAL
Explore all skills by this author →
WebsiteGitHub

narrator-ai-cli

Orchestrate narrator-ai-cli tasks to create movie narration videos with user approval.

1.9k|255|Updated Mar 19, 2026
Search Tags:#content automation#tts#cli orchestration#video narration#film commentary#ai dubbing
One-click install
npx skills add https://github.com/NarratorAI-Studio/narrator-ai-cli-skill --skill narrator-ai-cli
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: narrator-ai-cli
Source: https://github.com/NarratorAI-Studio/narrator-ai-cli-skill/tree/main
Command: npx skills add https://github.com/NarratorAI-Studio/narrator-ai-cli-skill --skill narrator-ai-cli

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill removes the complexity of setting up a multi-step video narration pipeline by guiding an AI agent to reliably use the narrator-ai-cli tool to produce finished narration videos.

Core Features & Use Cases

  • End-to-end movie narration video generation: Automates the workflow from selecting/confirming source material (video + SRT), choosing BGM and dubbing voice, generating narration script, and composing the final video.
  • Two production workflows: Supports both Fast Path (original narration workflow variants) and Standard Path (adapted/learned narration workflow), including required decision ordering.
  • Optional visual enhancement (“magic-video”): Adds post-composition subtitle/branding templates only after explicit user request and confirmation.
  • Standalone tasks: Enables voice cloning and text-to-speech via the same CLI.

Use case: When a user requests a comedy movie narration video for a specific film, the Skill walks through confirmation of the chosen movie material, BGM track, and dubbing voice, then generates the script and returns a downloadable MP4.

Quick Start

Tell your agent: Create a comedy film commentary narration video for The Shawshank Redemption.

Frequently Asked Questions about narrator-ai-cli

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

FAQPage Schema
How do I automate end-to-end movie narration video creation with an AI agent?▼

Movie narration video creation is automated by orchestrating a CLI workflow that chains source selection, BGM/voice selection, script generation, and video composing. The agent ensures consistent language linkage across dubbing, script, and text parameters while requiring mandatory user approval at each step.

Can I generate AI film commentary without manually writing the narration script?▼

Yes, AI film commentary generation includes automatic script creation based on the selected source material. After confirming the video source and SRT, the workflow generates the narration script and matches it with appropriate BGM and dubbing voices before composing the final MP4.

What is the difference between Fast Path and Standard Path workflows for video narration?▼

Fast Path supports original narration workflow variants, while Standard Path uses an adapted or learned narration workflow. Both paths require specific decision ordering for resource selection, script generation, and video composing to ensure correct task chaining and output generation.

Does the narration workflow support adding subtitles and branding templates after composing?▼

Yes, optional visual enhancement using magic-video templates can add post-composition subtitles and branding. This feature is applied only after explicit user request and confirmation, ensuring that the base narration video is composed before any template enhancements are layered on.

How do I ensure language consistency across AI dubbing and generated narration scripts?▼

Language consistency across AI dubbing and scripts requires maintaining consistent language linkage throughout the workflow. The dubbing voice selection, script language generation, and magic-video text parameters must all align to ensure the final composed video has matching audio and text languages.

Can I use the CLI for standalone text-to-speech and voice cloning without generating a full video?▼

Yes, the CLI supports standalone tasks for text-to-speech and voice cloning. These functions operate independently of the full end-to-end video narration pipeline, allowing you to generate audio assets without requiring source video selection or final video composing steps.

Related Skills

Explore More Content & Communication Skills→
krillinaikrillinai
10.7k

krillinai-tts

Generate target-language TTS audio from SRT subtitles via KrillinAI CLI.

Community
Advanced
jkf87jkf87
3

ppt-to-video-workflow

Convert presentation slides into narrated MP4 videos with subtitles.

Community
Advanced
refly-airefly-ai
199

fal-audio

Generate MP3 or WAV audio from text using Fal.ai models.

Official
Intermediate
inference-shinference-sh
688

ai-content-pipeline

Orchestrate multi-step AI content pipelines for image, video, audio, and text.

Official
Advanced