narrator-ai-cli-video-narration

Generate AI-narrated movie commentary videos through script, TTS, and composition tasks.

4|Updated May 16, 2026
One-click install
npx skills add https://github.com/reason-machines/devtools-skills --skill narrator-ai-cli-video-narration-reason-machines
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: narrator-ai-cli-video-narration
Source: https://github.com/reason-machines/devtools-skills/tree/main/skills/narrator-ai-cli-video-narration
Command: npx skills add https://github.com/reason-machines/devtools-skills --skill narrator-ai-cli-video-narration-reason-machines

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires typer, httpx, httpx-sse, pyyaml, rich.

What problem does it solve? Creating movie narration and commentary videos manually requires scripting, voiceover recording, music selection, and video editing. This Skill automates the entire pipeline through the narrator-ai-cli command-line tool, turning a multi-hour production process into a sequence of API-driven tasks. ## Core Features & Use Cases - Two Narration Workflows: Original narration for creating new commentary from scratch, and adapted narration for transforming existing movies from the database into recap videos. - Asynchronous Task Pipeline: Script generation, clip data creation, text-to-speech, and video composition run as pollable tasks with file_id chaining between stages. - Resource Selection: Browse and select templates, background music, and dubbing voices, including custom voice cloning from reference audio. - Use Case: A content creator wants to produce a recap video for a short drama. They select a template, BGM, and voice, then chain script generation, TTS, and composition tasks to produce a finished MP4 without opening a video editor. ## Quick Start Ask the AI to create a movie narration video by searching for a movie, selecting a template and voice, and running the narrator-ai-cli pipeline to produce the final video.

Frequently Asked Questions about narrator-ai-cli-video-narration

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

FAQPage Schema
How do I create a movie narration video with narrator-ai-cli?▼

Install the tool via pip, set your API key with narrator-ai-cli config set, then run the pipeline: generate a script task, create clip data, run text-to-speech, and compose the final video. Each step is asynchronous and must be polled until completed.

What is the difference between original and adapted narration workflows?▼

Original narration creates commentary from scratch using a drama name and intro, suited for new content. Adapted narration uses an existing movie_id from the database and requires uploading the source video file before composition.

How do I clone a custom voice for video narration?▼

Upload a reference audio file with narrator-ai-cli upload-file, then run create-voice-clone-task with the audio file_id and a voice name. The completed task returns a new dubbing_id usable in any TTS task.

Why does my narrator-ai-cli task stay in processing status?▼

All create-*-task commands are asynchronous, so you must poll the matching query-*-task command with the task_id and task_order_num. Poll every 5-10 seconds with a timeout limit, and check the error message if status becomes failed.

What file formats does narrator-ai-cli support?▼

Video clips must be .mp4, .mov, or .avi. Audio files for BGM and voiceovers must be .mp3 or .wav. Scripts are handled as .txt or .json, and clip timeline data uses .json format.