Borrowing it
Nothing to install: this file belongs to OLGTX303/voxcpm-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/OLGTX303/voxcpm-mcp/master/.claude/commands/voxcpm.mdgit clone --depth 1 https://github.com/OLGTX303/voxcpm-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/olgtx303/voxcpm-mcp/voxcpm)<a href="https://agentmods.dev/commands/olgtx303/voxcpm-mcp/voxcpm"><img src="https://agentmods.dev/badge/commands/olgtx303/voxcpm-mcp/voxcpm/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/olgtx303/voxcpm-mcp/voxcpm"><img src="https://agentmods.dev/badge/commands/olgtx303/voxcpm-mcp/voxcpm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00468 |
| Opus 5.5 | $0.00000 | $0.00187 |
| Sonnet 5.5 | $0.00000 | $0.00094 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
voxcpm scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
VoxCPM — Synthesize speech with VoxCPM2
You are helping the user generate high-quality AI speech using VoxCPM2, a 2B-parameter diffusion TTS model running locally on CUDA.
What you have access to
The voxcpm-tts MCP server exposes four tools:
| Tool | Purpose |
|---|---|
synthesize |
Convert text to WAV using the default VoxCPM2 voice |
synthesize_with_clone |
Convert text to WAV cloning a reference speaker |
preload_model |
Load VoxCPM2 into VRAM before synthesis (call once to warm up) |
ping |
Verify the worker subprocess is running |
How to handle the user's request
- If the user says
/voxcpm <text>— synthesize that text directly. - If they provide a reference WAV path and transcript — use
synthesize_with_clone. - If no output filename is specified, generate a descriptive one (e.g.
intro_narration.wav). - After synthesis, report the output path and duration.
- If the tool returns an error about the model not loaded, call
preload_modelfirst, then retry.
Parameter guidance
steps: default 30 is a good balance. Use 20 for a quick draft, 50 for final quality.reference_wav_path: must be an absolute path to a 48 kHz mono WAV.- Output files go to the directory set in
VOXCPM_OUTPUT_DIR(default:./voxcpm_output/).
Example interactions
User: /voxcpm Hello, this is a test of the VoxCPM narration system.
→ Call synthesize with that text, output_filename="test.wav"
User: /voxcpm Narrate scene 3. Clone my voice from reference.wav — it says "Welcome to the demo."
→ Call synthesize_with_clone with reference_wav_path and reference_text
User: /voxcpm warm up
→ Call preload_model to load VoxCPM2 into VRAM
Now handle the user's request using the voxcpm-tts MCP tools.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 42 lines · 0 tokens per session scan A d14ab994fd68
voxcpm is a command published in the GitHub repository OLGTX303/voxcpm-mcp (0 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 468 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
voxcpm compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| voxcpmOLGTX303/voxcpm-mcp | Command | 0 | 5mo ago | MIT | A | 0 | Claude Code |
| checklistgithub/spec-kit | Command | 150k | today | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 150k | today | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 150k | today | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 150k | today | MIT | A | 26 | Claude Code |
| convergegithub/spec-kit | Command | 150k | today | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 150k | today | MIT | A | 14 | Claude Code |