Vision provider route that transcribes attached images to text through a configurable model (15+ OpenAI-compatible and Anthropic vendors) while DeepSeek keeps answering.
View on GitHubBrowse similar plugins
Vision provider route that transcribes attached images to text through a configurable model (15+ OpenAI-compatible and Anthropic vendors) while DeepSeek keeps answering.
See the GitHub repository for installation instructions — this plugin does not publish a standard install command.
中文说明：Vision provider route that transcribes attached images to text through a configurable model (15+ OpenAI-compatible and Anthropic vendors) while DeepSeek keeps answering.（安装方式请参考 GitHub 仓库说明。）