dsh-vidi 0.9.5 → 0.10.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -12,6 +12,7 @@ A video tool for DeepSeek Harness: watch live streams, videos and podcasts with
12
12
  - **The subtitle model looks at the video**: polishing uses the page's title, description and comments, and — when the chosen model reads images — a frame of that stretch. It also keeps a glossary of names and terms for the video.
13
13
  - **Chat with DeepSeek beside the video**: grab this moment, cut this part, summarise, download the original — all in one conversation, with files saved in the video's folder.
14
14
  - **Restream**: push the video with its subtitles drawn into the picture to Bilibili, Douyin, Kuaishou, WeChat Channels, Douyu, Huya, YouTube, Twitch or any RTMP/SRT address — several at once; each platform connects and reconnects on its own.
15
+ - **Voiceover**: the subtitles spoken over the picture in another language — English in, Chinese out, or the other way round — with a voice from OpenAI, SiliconFlow, Gemini or ElevenLabs, or one made from a recording (your own voice read into the microphone, an audio file, or someone talking in the video). The original sound is lowered under it or turned off; restreams and clips carry it too.
15
16
  - **Download and export**: the original or a video with subtitle tracks, just the sound (M4A), SRT / VTT subtitles, transcripts by line or paragraph.
16
17
  - English and Chinese interface; works on phones.
17
18
 
package/README.zh-CN.md CHANGED
@@ -12,6 +12,7 @@ DeepSeek Harness 里的视频工具:看直播、视频和播客,同时出任
12
12
  - **字幕模型会看画面**:精修时结合视频页面的标题、简介、评论,所选模型能看图时还会带上那一段的画面,顺便整理这期视频的词表(人名、术语)。
13
13
  - **在视频旁边和 DeepSeek 对话**:截取此刻、剪下这段、总结要点、下载原片,都在同一个会话里完成,文件存在视频目录下。
14
14
  - **转播**:把视频连同画面里的字幕推到 B站、抖音、快手、视频号、斗鱼、虎牙、YouTube、Twitch 或任意 RTMP/SRT 地址,可以同时推多个平台;每个平台各自连接、断了各自重连。
15
+ - **配音**:把字幕用另一种语言念出来,叠在画面上:英文进、中文出,反过来也行。声音可以从 OpenAI、硅基流动、Gemini、ElevenLabs 里挑,也可以用一段录音做一个(对着麦克风读一段、给一个音频文件,或者取视频里某个人的声音)。原声可以压低或关掉;转播和剪出的片段也带配音。
15
16
  - **下载和导出**:原片或带字幕轨的视频、只要声音的音频(M4A)、SRT / VTT 字幕,逐句或按段落的文字稿。
16
17
  - 中英文界面,手机上也能用。
17
18