Formerly KrillinAI, VideoTranslation and Dubbing Tool for 120+ Languages. Open-source AI workspace for creators, powered by Codex. Video downloader, video translation, create videos, images, audios, and edits with Agents in one place. For your Social Media like YouTube, TikTok, Instagram, etc.
TypeScript agent-skillscodex-clideskop-appdubbingimage-generationlocalizationskillsttsvideo-editingvideo-generationvideo-transcriptionvideo-translation
docs: update readme
沈浩41249fa69bb0
diff --git a/README.md b/README.mdindex 70764d54..fa98dc08 100644--- a/README.md+++ b/README.md@@ -69,6 +69,25 @@ https://github.com/user-attachments/assets/c2c7b528-0ef8-4ba9-b8ac-f9f92f6d4e71</tr></table>+## 🔍 Speech Recognition Support+_**All local models in the table below support automatic installation of executable files + model files. Just make your selection, and KrillinAI will handle everything else for you.**_++| Service | Supported Platforms | Model Options | Local/Cloud | Notes |+|-----------------|------------------------------|-----------------------------------|-------------|----------------|+| **OpenAI Whisper** | Cross-platform | - | Cloud | Fast with excellent results |+| **FasterWhisper** | Windows/Linux | `tiny`/`medium`/`large-v2` (recommend medium+) | Local | Faster speed, no cloud service overhead |+| **WhisperKit** | macOS (Apple Silicon only) | `large-v2` | Local | Native optimization for Apple chips |+| **Alibaba Cloud ASR** | Cross-platform | - | Cloud | Bypasses China mainland network issues |++## 🚀 Large Language Model Support++✅ Compatible with all **OpenAI API-compatible** cloud/local LLM services including but not limited to:+- OpenAI+- DeepSeek+- Qwen (Tongyi Qianwen)+- Self-hosted open-source models+- Other OpenAI-format compatible API services+## 🌍 Language SupportInput languages: Chinese, English, Japanese, German, Turkish supported (more languages being added)Translation languages: 56 languages supported, including English, Chinese, Russian, Spanish, French, etc.diff --git a/docs/README_zh.md b/docs/README_zh.mdindex 71785405..2eb81dc0 100644--- a/docs/README_zh.md+++ b/docs/README_zh.md@@ -70,6 +70,24 @@ https://github.com/user-attachments/assets/c2c7b528-0ef8-4ba9-b8ac-f9f92f6d4e71</tr></table>+## 🔍 语音识别服务支持+_**下表中的本地模型全部支持自动安装可执行文件+模型文件,你只要选择,其它的KrillinAI帮你全部准备完毕。**_++| 服务源 | 支持平台 | 模型可选项 | 本地/云端 | 备注 |+|----------------|------------------------------|-----------------------------------|-------|-------------|+| **OpenAI Whisper** | 全平台 | - | 云端 | 速度快效果好 |+| **FasterWhisper** | Windows/Linux | `tiny`/`medium`/`large-v2` (推荐medium+) | 本地 | 速度更快,无云服务开销 |+| **WhisperKit** | macOS (仅限M系列芯片) | `large-v2` | 本地 | Apple芯片原生优化 |+| **阿里云ASR** | 全平台 | - | 云端 | 避免中国大陆网络问题 |++## 🚀 大模型支持++✅ 兼容所有符合 **OpenAI API规范** 的云端/本地大模型服务,包括但不限于:+- OpenAI+- DeepSeek+- 通义千问+- 本地部署的开源模型+- 其他兼容OpenAI格式的API服务## 语言支持输入语言支持:中文,英文,日语,德语,土耳其语(持续增加中)diff --git a/docs/images/ui_desktop.png b/docs/images/ui_desktop.pngindex fec2f44e..9f753972 100644Binary files a/docs/images/ui_desktop.png and b/docs/images/ui_desktop.png differ