Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
NO_PROXYNo不使用代理的主机列表,建议写成 localhost,127.0.0.1,::1
YTS_MODELNoWhisper 模型名:tiny/base/small/medium/large-v3/large-v3-turbolarge-v3-turbo
YTS_YTDLPNoyt-dlp 路径(默认使用项目 venv)
HTTP_PROXYNoHTTP 代理,需要代理访问 YouTube 时设置
YTS_DEVICENocpu 或 cudacpu
YTS_FFMPEGNoffmpeg 路径(默认自动探测)
YTS_PYTHONNoPython 解释器路径(默认使用项目 venv)
HF_ENDPOINTNo模型下载源https://hf-mirror.com
HTTPS_PROXYNoHTTPS 代理,需要代理访问 YouTube 时设置
YTS_THREADSNo转录线程数(默认 CPU 核数-4)
YTS_TMP_DIRNo下载音频的临时目录
YTS_HOTWORDSNo手工叠加的领域词表(人名/术语),简体、空格分隔
YTS_LANGUAGENo强制语种,如 zh / enauto
YTS_AUDIO_DIRNo音频保留位置(仅 YTS_KEEP_AUDIO=1 时使用)
YTS_BEAM_SIZENobeam search 宽度5
YTS_CACHE_DIRNo缓存目录
YTS_HF_RETRIESNo模型权重下载失败时的重试次数6
YTS_KEEP_AUDIONo保留 Whisper 用到的音频,便于换模型重跑0
YTS_OUTPUT_DIRNo转录 Markdown 落盘目录(相对路径按项目目录解析)
YTS_IMPERSONATENoyt-dlp 的浏览器指纹伪装目标chrome
YTS_COMPUTE_TYPENoCPU 上 int8 最快;有 GPU 可换 float16int8
YTS_AUTO_HOTWORDSNo1=自动从标题/简介抽词,0=关闭1
YTS_SUBTITLE_LANGNo想要的字幕语种,如 zh / zh-Hans / en;不设则用视频原声语种
YTS_TO_SIMPLIFIEDNo中文内容繁→简转换,设 0 关闭1
HF_HUB_DISABLE_XETNo禁用 hf-xet 后端(国内镜像下会 401)1
YTS_CONVERT_CONFIGNoOpenCC 档:auto=按输入脚本自动挑;也可写死 tw2sp(含词汇本地化)/ t2s(纯字形)auto
YTS_GAP_MIN_SECONDSNo时间轴缺口超过这么多秒就单独补录一遍(整窗丢失兜底),0=关闭10
YTS_OUTPUT_LANGUAGENo后续总结用什么语言(auto/zh/en)auto
YTS_PREFER_SUBTITLESNoauto=人工>自动>Whisper;manual=只认人工字幕;off=永远用 Whisperauto
YTS_SUBTITLE_CHUNK_MSNo字幕合并成几秒一块10000
YTS_CONVERT_TIMEOUT_MSNo繁简转换超时(毫秒)120000
YTS_DOWNLOAD_TIMEOUT_MSNo下载音频超时(毫秒)1200000
YTS_METADATA_TIMEOUT_MSNo取元数据超时(毫秒)300000
YTS_SUBTITLE_TIMEOUT_MSNo下载单条字幕超时(毫秒)180000
YTS_TRANSCRIBE_TIMEOUT_MSNo转录超时(毫秒)10800000

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
get_video_transcriptA

把 YouTube 视频转成文字稿:优先拉取现成字幕(人工 > 自动),秒级完成、不占 CPU;只有在没有合适字幕时才回退到本地 faster-whisper 从音频转录。结果落盘成 Obsidian 友好的 Markdown(frontmatter + 带时间戳章节),并缓存供重复调用秒级命中。 转录质量:Whisper 的模型档位可调。默认 large-v3-turbo 更准;要快速草稿可传 model="small"(快约 1.8 倍,但会听错常用词、甚至整段丢失)。换模型会自动让该视频的缓存失效,所以「先用 small 试、再用大模型重跑」不会重复下载。 注意:正文在 savedTo 指向的文件里,本工具只返回元数据 + 预览 + 供下一步使用的提示,不要期待它返回全文。

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4.6/5.0

Scored across 1 tool

Disambiguation5/5

Only one tool exists, so there is no possibility of confusing it with another tool. Its purpose is clearly defined in the description.

Naming Consistency5/5

The single tool name follows a clear and conventional verb_noun pattern (get_video_transcript), and there are no other names to cause inconsistency.

Tool Count3/5

With just one tool, the surface feels minimal but acceptable for a focused transcript-extraction service. Additional tools for cache management or language listing could be added, but the single tool covers the core request.

Completeness5/5

The tool covers the full workflow from retrieving subtitles to generating Markdown, including model selection and caching. There are no obvious missing operations within its stated purpose.

Maintenance

ActivityMaintained
ResponsivenessNo issues