weifeng2333/videocaptioner
Developer toolsThis page was translated automatically. Technical details may differ from the original. View the original
🎬 Kaka Subtitle Assistant | VideoCaptioner - LLM-based intelligent subtitle assistant - Full-process handling of video subtitle generation, sentence breaking, correction, and subtitle translation! - A powered tool for easy and efficient video subtitling.
Overview
VideoCaptioner is a large language model-based video subtitle processing tool — one-stop processing for speech recognition, subtitle optimization, translation, and video synthesis Configuration priority: Command line parameters > environment variable (VIDEOCAPTIONER_*) > configuration file > default values. Run VideoCaptioner Config Show to view the current configuration. Run videocaptioner --help to view full parameters. The full CLI documentation can be found at docs/cli.md. Just enter the API Base URL and API Key in the software settings or CLI. Detailed configuration tutorial This project provides Claude Code Skill, allowing AI programming assistants to directly call VideoCaptioner to process videos. Then enter /videocaptioner transcribe video.mp4 --asr bijian in Claude Code to use it. - Word-level timestamp + VAD speech activity detection, high recognition accuracy - LLM semantic understanding and sentence segmentation, natural and smooth subtitle reading experience - Context-aware translation, supports reflection optimization mechanism - batch concurrent processing with high efficiency
Overview (machine translated)
VideoCaptioner Video subtitle processing tools based on large language models — one-stop processing for speech recognition, subtitle optimization, translation, and video synthesis
Online documentation · CLI usage · GUI desktop version · Claude Code Skill
Installation
Free features (Bijian Voice Recognition, Bing/Google Translate) No configuration required, install and use.
CLI command line
When LLM functions (subtitle optimization, large model translation) are needed, configure the API Key:
Configuration priority: 命令行参数 > 环境变量 (VIDEOCAPTIONER_*) > 配置文件 > 默认值. Run videocaptioner config show to view the current configuration.
Overview of all CLI commands
| Command | Instructions |
|---|---|
gui |
Open the desktop version. You can also run videocaptioner-gui |
transcribe |
Speech-to-subtitles. Engines: faster-whisper, [T6]], bijian (free), jianying (free), whisper-cpp |
subtitle |
Subtitle optimization/translation. Translation services: llm, bing (free), google (free) |
dub |
Generate dubbed tracks or videos based on subtitles |
synthesize |
Subtitles are burned to the video (soft subtitles/hard subtitles). |
process |
Full-process handling |
download |
Download videos from platforms like YouTube and Bilibili |
config |
Configuration management (show, set, get, path, init) |
Run videocaptioner --help to view the full parameters. For the full CLI documentation, see docs/cli.md.
GUI Desktop Edition
Other installation methods: Windows installation package / macOS one-click script
Windows: Download the installation package from Release
macOS：
–>
LLM API Configuration
LLMs are only used for subtitle optimization and large model translation; free features (Bingjian recognition, Bing translation) require no configuration.
Service providers supporting all OpenAI-compatible interfaces:
| Service provider | Official website | |--------|------| | VideoCaptioner Transfer Station | api.videocaptioner.cn — High concurrency, cost-effective, supports GPT/Claude/Gemini, etc. | | SiliconCloud | cloud.siliconflow.cn | | DeepSeek | platform.deepseek.com |
This page was translated automatically. Technical details may differ from the original.
Recommended Tools
Try a different keyword or remove a filter.
Install
npx skillfish add weifeng2333/videocaptioner