convez.ai
Skill
NarratorAI-Studio

narrator-ai-cli

NarratorAI-Studio/narrator-ai-cli

Ver no GitHub
BomPluginScore · de 0 a 100

AI 解说大师 — CLI 客户端;用于终端调用视频解说生成 API

Instalação

$npx convez-ai NarratorAI-Studio/narrator-ai-cli

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
148
Forks
28
Acompanhando
1
Saúde
50%
Último commit
há 2 dias
Versão
v1.0.0
Issues abertas
6
Contribuidores
5

README

A tradução para o português deste README ainda está na fila.

🎬 Narrator AI CLI — Create Movie Narration Videos with Natural Language

中文文档

One command to install, one sentence to create videos. 93 built-in movies, 146 BGM tracks, 63 dubbing voices, 90+ narration templates — ready out of the box.

What is this?

Narrator AI CLI is the command-line tool for Narrator AI, an AI-powered video narration platform. Once installed in your AI agent (OpenClaw, Windsurf, WorkBuddy, etc.), just say:

"Create a movie narration video for Pegasus in a comedy style"

The AI handles everything automatically:

Select movie → Match narration style → Generate script → Compose video → Output download link

No manual steps required. The AI completes the entire pipeline for you.

What it can do

  • ✅ Movie narration videos: Input a movie name, get a complete narration video (script + voiceover + footage + BGM)
  • ✅ Multiple narration styles: Action, Comedy, Thriller and more — 12 genres, 90+ templates
  • ✅ Multi-language voiceover: 11 languages including English, Mandarin, Japanese, and 63 voice characters
  • ✅ Batch production: Tell the AI "make 10 narration videos" and it will process them one by one
  • ✅ Run unattended: Let the agent work while you sleep

Quick Start

Step 1: Install the CLI

Prerequisites: Python 3.10+ (check "Add to PATH"), Git

macOS / Linux

curl -fsSL https://raw.githubusercontent.com/NarratorAI-Studio/narrator-ai-cli/main/install.py | python3

Windows (CMD / PowerShell)

python -c "import urllib.request; exec(urllib.request.urlopen('https://raw.githubusercontent.com/NarratorAI-Studio/narrator-ai-cli/main/install.py').read())"

Verify:

narrator-ai-cli --version

Step 2: Get an API Key

📧 Email merlinyang@gridltd.com or scan the QR code below to get your API key.

Contact us

Step 3: Configure

narrator-ai-cli config set app_key your_api_key

Step 4: Start creating videos!

If using with an AI agent (OpenClaw, etc.), just use natural language:

"Create a narration video for The Shawshank Redemption with an inspirational style"

For terminal usage, see Command Reference below.


Using with AI Agents (Recommended)

This tool works best with AI agents. Install the Skill so the agent knows how to use these commands.

👉 Install the Skill: narrator-ai-cli-skill

Tested Platforms

PlatformSetupExperience
WindsurfCLI repo only⭐⭐⭐⭐⭐ Auto-understands
WorkBuddy (Tencent)CLI + Skill repos⭐⭐⭐⭐⭐ Smooth
Youdao LobsterCLI + Skill repos⭐⭐⭐⭐ Reliable
QClaw (Tencent)CLI + Skill repos⭐⭐⭐⭐ Reliable
Yuanqi AICLI + Skill repos⭐⭐⭐ Functional

💡 Note: Most domestic Chinese AI agents require both CLI and Skill repo URLs. Windsurf can work with just the CLI repo.


Built-in Resources

No uploads needed — all of these are ready to use:

ResourceCountCommand
🎬 Movie materials93 moviesnarrator-ai-cli material list
🎵 Background music146 tracksnarrator-ai-cli bgm list
🎙️ Dubbing voices63 voices (11 languages)narrator-ai-cli dubbing list
📝 Narration templates90+ (12 genres)narrator-ai-cli task narration-styles

🔗 Preview all resources: Feishu Docs


Two Workflow Paths

Original Narration (Recommended — faster & cheaper)

Search movie → Fast writing → Fast clip data → Video composing → Magic video (optional)

3 modes:

  • Hot Drama: Well-known movies with full info available
  • Original Mix: Mix original audio with narration
  • New Drama: Short dramas or movies without full info

Adapted Narration

Popular learning → Generate writing → Clip data → Video composing → Magic video (optional)

Command Reference

Config

CommandDescription
config initInteractive setup (server URL + API key)
config showShow current config (key masked)
config set <key> <value>Set a config value

User

CommandDescription
user balanceQuery account balance
user loginLogin with username/password
user keysList sub API keys
user create-keyCreate a sub API key

Task

CommandDescription
task typesList task types (-V for details)
task create <type> -d '{...}'Create a task
task query <task_id>Query task status and results
task listList tasks with filters
task budget -d '{...}'Estimate credits consumption
task verify -d '{...}'Verify materials before creation
task search-movie "<name>"Search movie info
task narration-stylesList narration templates (90+)
task templatesList visual templates for magic-video
task get-writingRetrieve generated script
task save-writing -d '{...}'Save modified script
task save-clip -d '{...}'Save modified clip data

Task Types:

TypeWorkflow Position
popular-learningAdapted Narration Step 1
generate-writingAdapted Narration Step 2
fast-writingOriginal Narration Step 1
clip-dataAdapted Narration Step 3
fast-clip-dataOriginal Narration Step 2
video-composingVideo composing (both paths)
magic-videoOptional final step (visual template)
voice-cloneStandalone
ttsStandalone

File

CommandDescription
file upload <path>Upload file (returns file_id)
file transfer --link <url>Transfer remote file by link (HTTP / Baidu Netdisk / PikPak)
file listList uploaded files
file info <file_id>Get file details
file download <file_id>Get presigned download URL
file storageShow storage usage (3GB limit)
file delete <file_id>Delete a file

Materials / BGM / Dubbing

CommandDescription
material listList 93 pre-built movies (--genre, --search)
material genresList movie genres with counts
bgm listList 146 BGM tracks (--search)
dubbing listList 63 voices (--lang, --tag, --search)
dubbing languagesList supported languages
dubbing tagsList genre recommendation tags

Data Flow

                     file upload / file list / material list
                     -> video_file_id, srt_file_id
                     bgm list -> bgm_id
                     dubbing list -> dubbing, dubbing_type

    Adapted Narration                    Original Narration (faster)
    ─────────────────                    ────────────────────────────
    popular-learning (optional)          search-movie
    OUT: learning_model_id               OUT: confirmed_movie_json
      OR use pre-built template                  │
              │                          fast-writing (3 modes)
              ▼                          IN:  learning_model_id + movie_json
    generate-writing                     OUT: task_id, file_ids[0]
    IN:  learning_model_id, episodes              │
    OUT: task_order_num, file_ids[0]     fast-clip-data
              │                          IN:  task_id, file_id, episodes
              ▼                          OUT: task_order_num
    clip-data                                     │
    IN:  order_num, bgm, dubbing                  │
    OUT: file_ids[0]                              │
              │                                   │
              ▼                                   ▼
         video-composing
         IN:  order_num (from writing step), bgm, dubbing
         OUT: task_id, video URLs
                    │
                    ▼
         magic-video (optional)
         IN:  task_id or file_id + template_name
         OUT: rendered video URLs

JSON Output

All commands support --json for structured output (recommended for AI agents):

narrator-ai-cli task list --json
narrator-ai-cli task query <task_id> --json

Environment Variables

VariableDescription
NARRATOR_SERVERAPI server URL
NARRATOR_APP_KEYAPI key
NARRATOR_TIMEOUTTimeout in seconds (default: 30)

AI Agent Integration

See narrator-ai-cli-skill for the complete SKILL.md that teaches AI agents how to use this tool automatically.

Contact

Need an API key or help? Reach out:

Contact us

Ver o original no GitHub

Bom para

Relacionados