$ loading_
Generate speech and clone voices inside Claude Code for audio prototyping.
The available material is sparse, but the tool appears to provide local text-to-speech and voice cloning capabilities. It requires no secrets, declares no remote endpoints, and is open-source under MIT, so the overall risk is low-to-moderate; however, it is flagged as executing code and has low adoption with unknown maintenance, so it should be used cautiously in a constrained environment.
The material explicitly states that no keys or environment variables are required. No API keys, account credentials, or other sensitive secrets are requested, so credential exposure and abuse risk appears low.
The material declares no remote endpoints, and the README does not describe any online service, cloud inference, or upload flow. Based on the available facts, there is no clear user-data egress path.
The objective checks indicate this tool executes code, meaning it can run local code/processes. That is a common MCP capability, but the material does not define execution boundaries or system-call scope, so it should be treated cautiously as a local code-execution tool.
The description involves text-to-speech and voice cloning, which typically require access to input text, voice samples, and generated audio files. There is no stated overbroad permission request, but the file read/write scope is not defined, so access to local media data warrants caution.
The project is open source and MIT-licensed, which are meaningful risk-reducing factors. However, it comes from a third-party registry, has 0 GitHub stars, unknown maintenance status, and no README content, so transparency and maturity are limited and supply-chain confidence is only moderate.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "voxcpm-mcp" yet — see the docs or source repo.
Use voxcpm-mcp to convert the following product intro into Mandarin female speech with a professional, clear, natural tone, and output an audio file suitable for a demo video: "Welcome to our intelligent data platform. It helps teams analyze faster and make decisions with confidence."
A Chinese voiceover audio clip ready to use in a product demo video.
Use voxcpm-mcp to clone the speaker voice from my reference audio and read this ad copy: "Sign up now to enjoy 14 days of premium features for free." Preserve the original voice characteristics while improving pronunciation clarity.
An ad audio clip that preserves the reference speaker’s vocal identity.
Use voxcpm-mcp to generate 3 English speech versions for the following support message: 1) warm and friendly, 2) formal and professional, 3) youthful and energetic. Text: "Your request has been received and our team will contact you shortly."
Three English audio variants in different tones for comparison and selection.
Generate speech with cloned voices and preview it inline with visualization.
Clone custom voices for AI assistants and generate playable speech inline.
Generate speech, clone voices, and create dialogue through MCP AI assistants.
Convert text to speech with ElevenLabs and manage available voices.
Generate speech and animate a VRM avatar with AgentVRM.
Convert text to speech quickly and browse available voices and models.