English Français العربية

VoiceCheap

Official registry Media and design

Transcribe, subtitle, dub and lip-sync media; create speech, voices, images and thumbnails.

Source code Website Documentation

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

Remote (streamable-http)
Claude Code 
claude mcp add --transport http voicecheap 'https://api.voicecheap.ai/mcp'
JSON configuration (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "voicecheap": {
            "type": "http",
            "url": "https://api.voicecheap.ai/mcp"
        }
    }
}

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. VoiceCheap MCP
  2. Connection
  3. Clients
  4. Links
  5. What is packaged
  6. License

VoiceCheap MCP

Connect an agent to your VoiceCheap account for audio, video, voice and visual workflows. Available tools depend on the permissions you grant and your account access.

  • Transcribe audio or video and retrieve or generate YouTube transcripts and timestamped chapters.
  • Create SRT subtitles, translate SRT/VTT while preserving timing, export saved subtitles, and burn subtitles into uploaded or YouTube videos.
  • Generate speech, design voices, and clone voices with explicit speaker permission.
  • Generate images and thumbnails, then retrieve your saved results.
  • Translate and dub projects, generate lip sync, and add dynamic subtitles to completed translated or lip-synced videos.
  • Manage permitted publishing to connected channels, account usage and settings, team access, glossaries, workspace folders and supported webhook settings.

This is a client configuration package. Each marketplace manages its own review and indexing. Package validation does not establish that the current production deployment contains the same code as this checkout, or that a provider connection has been tested.

Connection

The package connects to https://api.voicecheap.ai/mcp using Streamable HTTP. Authentication happens through VoiceCheap's browser-based OAuth consent flow. For a basic connection check, approve only account:read. Add only the read or write permissions needed for a requested workflow; a Read Only preset may also expose project and media data. Never paste passwords, API keys, authorization codes or tokens into the conversation or this package.

A VoiceCheap account with API and MCP access is required. API/MCP calls share the account's allowance; generation uses the applicable existing credits and allowances. The package does not initiate purchases or manage card payments.

First ask: "Show my VoiceCheap credits and the tools available to this connection." Check the actual tool response before treating the connection as working. Generating media, changing account data and publishing media require a user request that authorizes those actions. Voice cloning also requires explicit permission from the speaker.

Keep account data and media private. Public listings, examples and demo recordings must not disclose account or project identifiers, credentials or media links. Use synthetic content for reviews and grant only the permissions each review needs. Publishing or sharing an output requires the user's explicit destination and privacy choice; connecting an account does not make its videos public.

Clients

  • Cursor: plugin manifest in .cursor-plugin/plugin.json, remote connection in mcp.json.
  • Grok Build: plugin manifest in .grok-plugin/plugin.json, connection in .mcp.json.
  • Gemini CLI: gemini extensions install https://github.com/VoiceCheap/voicecheap-mcp
  • Other MCP clients: add the remote endpoint and complete OAuth.
  • OpenClaw: the standalone workflow skill is in openclaw/.

Marketplace approval and indexing are managed by each platform. The presence of these files does not establish approval or completed client testing.

Manage and revoke connections from VoiceCheap Integrations.

What is packaged

Client configuration, a workflow skill, documentation and existing VoiceCheap branding. There are no local executable hooks, backend source files or embedded credentials. Requests go to VoiceCheap's hosted service; generated result URLs may point to the storage locations returned by that service. No additional telemetry is introduced by this package.

The icon is the existing 512-pixel VoiceCheap landing icon, converted from its actual JPEG encoding to PNG without changing the design. The official public wrapper is VoiceCheap/voicecheap-mcp. Its client configuration, skills and documentation use the included MIT license. No trademark rights to the VoiceCheap name or logo are granted. Marketplace approval is separate from publication of this repository.

The separate ClawHub skill release uses that platform's required MIT-0 license.

Published by VOICECHEAP, SAS, France.

License

Client configuration, documentation and skills are distributed under the MIT license. No trademark rights to the VoiceCheap name or logo are granted. The hosted VoiceCheap service remains subject to its own terms. The separate ClawHub skill release is offered under that platform’s required MIT-0 license.

Frequently asked questions

What is VoiceCheap?

Transcribe, subtitle, dub and lip-sync media; create speech, voices, images and thumbnails.

How do I install VoiceCheap?

It runs as a remote server. In Claude Code: claude mcp add --transport http voicecheap 'https://api.voicecheap.ai/mcp'. For other clients, paste the JSON configuration from this page into their MCP settings.

Does VoiceCheap need an API key?

Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.

Is VoiceCheap open source?

Yes. Its code is on GitHub under the MIT license.

Who maintains VoiceCheap?

It is published by VoiceCheap. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.