local-theater-auto
by MWnv1
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VIDEO_H | No | 输出视频高度 | 1080 |
| VIDEO_W | No | 输出视频宽度 | 1920 |
| TTS_RATE | No | TTS 语速 | 180 |
| X264_CRF | No | 回退 x264 时的 CRF | 20 |
| DRAW_SIZE | No | 出图边长 | 1024 |
| TTS_VOICE | No | TTS 发音人 | |
| VIDEO_FPS | No | 输出视频帧率 | 30 |
| DRAW_STEPS | No | 采样步数 | 4 |
| LLM_DEVICE | No | 剧本生成 LLM 设备 | NPU |
| MODEL_ROOT | No | 模型根目录 | D:\ai_models |
| DRAW_DEVICE | No | 绘图设备：GPU / CPU / AUTO | GPU |
| FFMPEG_PATH | No | ffmpeg 可执行文件绝对路径；不设置时使用 PATH 中的 ffmpeg | PATH 中 |
| QSV_QUALITY | No | QSV 的 -global_quality | 23 |
| FFPROBE_PATH | No | ffprobe 可执行文件绝对路径；不设置时使用 PATH 中的 ffprobe | PATH 中 |
| LLM_MODEL_DIR | No | 剧本生成 LLM 模型目录 | $MODEL_ROOT\qwen3-4b-int4-ov |
| THEATER_CACHE | No | 缓存根目录 | <项目>\cache |
| TTS_VOICE_MAP | No | TTS 发音人映射，例如 小林=Huihui,阿杰=Kangkang | |
| VIDEO_ENCODER | No | 视频编码器；不可用时自动回退 libx264 | h264_qsv |
| DRAW_MODEL_DIR | No | 绘图模型目录 | $MODEL_ROOT\flux-schnell-int4-ov |
| HF_HUB_OFFLINE | No | MCP 配置示例中设置为 1，用于离线运行 | 1 |
| TRANSFORMERS_OFFLINE | No | MCP 配置示例中设置为 1，用于离线运行 | 1 |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo recent community issues