Free during launch: every app and tool is unlimited — no account, no card. Purchases open soon (then $9 once). Download · Free browser tools
GUI Hub
For Claude, Cursor, VS Code & other MCP clients

Can Claude make a voice-over in Spanish?

Not on its own. AI assistants have no voice of their own. Cloud voice services (ElevenLabs and others, some with MCP servers) sound excellent and can clone voices, but charge per character and need your text uploaded. This runs offline with no credits — good for drafts, private scripts and high volume; choose a cloud service when top voice quality or a cloned voice matters. With the GUI Hub Audio MCP server installed, Claude (Desktop or Code), Cursor, VS Code and other MCP clients can make a voice-over in Spanish, French, German, Japanese or 27 other languages locally: the assistant calls the dub_voiceover tool, which runs Supertonic voices (sherpa-onnx) + FFmpeg on your machine. Files are not uploaded.

Set it up (2 minutes)

  1. Claude Code / Cursor / VS Code / Windsurf: add the MCP server
    npx -y https://guihub.cc/mcp.tgz --product=audio
    Claude Code: claude mcp add gui-hub-audio -- npx -y https://guihub.cc/mcp.tgz --product=audio
  2. Claude Desktop: download the one-file extension and double-click it.
  3. No AI? GUI Hub Audio is also a point-and-click desktop app.

Agent with its own computer?

Grok Bot, ChatGPT dots, Claude Duet, OpenClaw, Manus or Codex can run it directly — no MCP needed:

npx -y https://guihub.cc/cli.tgz run dub_voiceover --text "…" --out /path/to/output.mp3

Options: npx -y https://guihub.cc/cli.tgz info dub_voiceover · skill file: SKILL.md · more for agents

Then ask

“Translate this script into Spanish and save it as voiceover.mp3 with a male voice.”

What the AI gets

dub_voiceover — Turn text into natural speech in any of 31 languages (Spanish, Portuguese, French, German, Italian, Dutch, Polish, Turkish, Russian, Ukrainian, Japanese, Korean, Vietnamese, Indonesian, Hindi, Arabic, English, …) and save an MP3 or WAV on the user's computer, offline (Supertonic 3). Use whenever the user wants a voice-over, narration or audio in a language other than English (for English, speak_speak has more voices). Write or translate the script yourself first; set `lang` to its language. Up to ~5,000 characters per call — split long texts into parts.

InputType
text*string
langstring (es, pt, fr, de, it, nl)
voicestring (0, 3, 6, 9)
speedstring (0.9, 1.0, 1.15)
out*string

Cost

Free to install; each tool has 3 free uses. Then $9 once for all of GUI Hub Audio (no subscription). The tool tells the assistant when free uses run out and how to unlock.

Powered by Supertonic voices (sherpa-onnx) + FFmpeg (MIT (Supertonic 3 model), Apache-2.0 (sherpa-onnx), GPL (FFmpeg static build)), the official release, verified by SHA-256. GUI Hub is independent and not affiliated with Supertonic voices (sherpa-onnx) + FFmpeg, Anthropic, Cursor or Microsoft.

Other things your AI can do with GUI Hub