VoxCPM Audio MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FFMPEG | No | Path to the FFmpeg executable. | D:\Desktop\VoxCPM2\tools\ffmpeg\bin\ffmpeg.exe |
| SOULX_HOME | No | Installation directory of SoulX-Singer (e.g. D:\Desktop\SoulX-Singer). | |
| VOXCPM_URL | No | URL of the local VoxCPM2 service. | http://127.0.0.1:8808 |
| VOXCPM_HOME | No | Installation directory of VoxCPM2 (e.g. D:\Desktop\VoxCPM2). | |
| MIN_FREE_VRAM_MB | No | Minimum free VRAM (MB) required before sing_notes uses the GPU in device=auto mode; below this it falls back to CPU. | 6000 |
| SOULX_MODEL_PATH | No | Path to the SoulX-Singer model file (e.g. D:\Desktop\SoulX-Singer\pretrained_models\SoulX-Singer\model.pt). | |
| VOXCPM_START_SCRIPT | No | Path to the script used to start the VoxCPM2 service. | D:\Desktop\VoxCPM2\Start-VoxCPM.ps1 |
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
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| speakC | 用本地 VoxCPM2 生成说话或情感旁白。返回音频文件路径。 |
| speak_segmentsC | 把多段文字分别用 VoxCPM2 合成，并按停顿拼接成一条情感旁白。 |
| sing_metadataC | 用 SoulX-Singer 根据已写好的目标元数据生成带旋律的歌声。 |
| sing_notesC | 用音素、MIDI 音高和每字时长直接生成唱歌，不需要手写完整元数据。 |
| healthA | 检查本地模型、FFmpeg、VoxCPM2 服务和 GPU 显存状态。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
speak and speak_segments both synthesize speech, and sing_metadata/sing_notes both synthesize singing; however, descriptions distinguish single vs. multi-segment speech and metadata vs. note-level singing input. An agent can generally tell them apart, though the overlapping pairs may cause occasional misselection.
Most names follow a snake_case verb_noun or verb_object pattern (speak_segments, sing_metadata, sing_notes), with speak as a bare verb and health as a noun utility. The convention is consistent enough to be predictable.
Five tools are well-scoped for an audio synthesis server: two speech modes, two singing modes, and a health check. No obvious bloat or thinness.
The surface covers single and segmented speech, metadata-based and note-based singing, plus system health, which is strong for the stated purpose. Minor gaps like voice/model listing or audio management are not fatal and can be worked around.