NarratoAI: All-in-One AI Video Commentary and Automated Editing Tool 266

📌 What is NarratoAI

NarratoAI is an open-source automated film and video commentary tool based on LLM, which integrates the complete workflow of "scriptwriting - video editing - AI voiceover - subtitle generation" into automated operations. It is mainly aimed at short video creators, film and TV commentary UP hosts, MCN teams, and self-media operators.

NarratoAI is developed by GitHub user linyqh, currently has about 7K Stars and 880 Forks, and supports both local deployment and Docker deployment.

✨ NarratoAI Features

🎬 Intelligent Scriptwriting: Uses LLM to automatically generate video commentary scripts, supports multiple languages

🎞️ Automated Video Editing: Automatically edits videos based on scripts, supports random splicing mode, allows customization of clip duration and video ratio (e.g., 9:16 vertical screen)

🗣️ AI Voiceover Generation: Built-in multilingual TTS speech synthesis, supports volume and speed adjustment, offers multiple voice styles

📝 Intelligent Subtitle Creation: Automatically generates subtitles synchronized with voice, supports custom fonts, positions, colors, and outlines

👀 Content Preview Optimization: Preview clip timestamps, frame descriptions, and corresponding narration before generation, supports regenerating individual segments

🚀 Multi-Model Adaptation: Supports Alibaba Qwen2-VL, DeepSeek R1/V3, Google Gemini and other models

💻 Multi-Scenario Support: Covers popular creation scenarios such as general film and TV commentary, short drama commentary, and short drama mashups

🔍 SEO Optimization: Optimizes content structure based on keywords to improve search engine visibility

🎯 NarratoAI Use Cases

• Film and TV Commentary Creation: Quickly produce professional commentary videos for movies, TV series, and short dramas

• Short Video Production: Mass-produce short video content suitable for platforms like Douyin, Kuaishou, Bilibili, and WeChat Channels

• Education and Training Videos: Teachers or training institutions can quickly create teaching demonstration materials

• Commercial Product Showcase: Enterprises create product introduction videos to highlight product features and advantages

• Self-Media Operations: Individual creators can publish multiple pieces of content daily to enhance account influence

✅ NarratoAI Pros and Cons

Pros

• Full Workflow Automation: From script to finished video with one click, complete video generated within 10 minutes, efficiency improved by over 80%

• Zero Barrier to Entry: No professional editing skills required, beginners can get started quickly

• Very Low Cost: Editing a 10-minute video costs only about 0.1 yuan (API call fees)

• Open Source and Free: Completely free to use, transparent code, supports secondary development

• Flexible Customization: Supports manual parameter adjustment to meet personalized creation needs

Cons

• Model Dependency: Earlier versions primarily rely on Google Gemini model, with limited support for other models (improved in newer versions)

• Hardware Requirements: While GPU is not required, needs 4-core CPU + 8GB RAM configuration

• Chinese Support Limitations: Earlier versions have limitations on Chinese video processing, file names cannot contain Chinese, special characters, or spaces

• Effect Consistency: Automatically generated content may require manual fine-tuning to achieve optimal results

🛠️ How to Use NarratoAI

Environment Preparation

• System Requirements: Windows 10+ / MacOS 11.0+ / Linux

• Hardware Configuration: 4-core CPU, 8GB RAM (GPU not required)

• Python Version: 3.10 or higher

Deployment Method (Choose one)

Method 1: Local Deployment

git clone https://github.com/linyqh/NarratoAI.git
cd NarratoAI
pip install -r requirements.txt
cp config.example.toml config.toml
# 编辑 config.toml 填入 API Key
streamlit run webui.py --server.maxUploadSize=2048

Method 2: Docker Deployment

git clone https://github.com/linyqh/NarratoAI.git
cd NarratoAI
docker-compose up -d

Usage Workflow

1. Basic Configuration: Visit http://localhost:8501, configure API Key and select AI model

2. Upload Video: Place mp4 file in resource/videos directory (file names cannot contain Chinese or special characters)

3. Generate Script: AI automatically analyzes video content and generates commentary script

4. Preview and Adjust: Check whether clips match commentary, regenerate unsatisfactory parts

5. Configure Parameters: Set video ratio, voiceover style, subtitle style, etc.

6. Generate Video: Click start, wait for AI to automatically complete editing, voiceover, and subtitle composition

❓ Frequently Asked Questions

Q1: Why can't Chinese video file names be recognized?

A: The system has restrictions on file names. It is recommended to use English, numbers, or underscores for naming, avoiding Chinese, spaces, and special characters.

Q2: Which AI models does NarratoAI support?

A: Currently supports Google Gemini, Alibaba Qwen2-VL, DeepSeek R1/V3, etc. Qwen series models are recommended for video analysis.

Q3: Can the generated videos be used commercially?

A: Attention should be paid to the copyright of the original video materials. For commercial rights of AI-generated content, please refer to the specific model service terms used.

Q4: What if the editing effect is not ideal?

A: You can regenerate individual segments during the preview stage, or manually edit the script for adjustments.

Q5: Is export to Jianying supported?

A: Future versions plan to support exporting Jianying drafts.

Q6: Is remote deployment secure?

A: Advanced encryption technology is used to ensure data transmission and storage security, but it is recommended to obtain the software through official channels.

🔗 Related Links

GitHub Repository:https://github.com/linyqh/NarratoAI

Official Documentation:https://www.narratoai.cn/

API Documentation:Visit http://localhost:8080/docs after deployment