agentleFS
umakhanproumakhanpro/vocalingo-mcp/skills/speak-in-your-voice/SKILL.md

speak-in-your-voice

Skill0 starsChanged 16 days agoMITView on GitHub

Read a text aloud in the user's own cloned voice, or in an OpenAI or ElevenLabs voice, with the VocaLingo MCP server. Can save a new voice from a 10 to 60 second sample. Use when the user wants a voice-over, an audio version of an article or post, a voice reply, narration for a video, or asks to "say this in my voice".

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 0 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Call list_voices. ownVoices are the voices the user saved in VocaLingo.

    line 12
  2. Very specific:

    No own voice and the user wants theirs: ask for a 10 to 60 second recording of clean speech, then save_voice { name, source } (see "Files" …

    line 13
  3. Very specific:

    Every error has a code and a nextStep: follow nextStep.

    line 37
  4. Very specific:

    If no VocaLingo tools are available, the server is not connected yet.

    line 41

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Voice a text in the user's own voice

Works through the VocaLingo MCP server (https://nodejs.vocalingo.app/mcp). Tools: list_voices, save_voice, text_to_speech, delete_voice, check_job, get_upload_url.

Steps

  1. Call list_voices. ownVoices are the voices the user saved in VocaLingo; stockVoices are OpenAI and ElevenLabs voices.
  2. No own voice and the user wants theirs: ask for a 10 to 60 second recording of clean speech, then save_voice { name, source } (see "Files" below). Only clone a voice the user owns or has explicit consent to use. The voice also appears in the VocaLingo app.
  3. Call text_to_speech { text, voice: "<voiceId>" }.
    • Own voices speak en, ru, zh, de, fr, es, it, ja, ko, pt, up to 10,000 characters. Pass language for the text's language and optionally emotion (happy, sad, angry, neutral…) or speed (0.5 to 2.0).
    • OpenAI voices (cedar, marin, alloy, coral, sage…): up to 4,000 characters, instructions sets the style ("calm and slow").
    • ElevenLabs voices: a name like George or an id from list_voices.
  4. The reply has audioUrl. A long text can return status: "processing" with a jobId: call check_job { jobId } until it finishes.

Cost

Own voice: about 11 to 12 VocaLingo tokens per 1,000 characters. Saving a voice: about 1 token. delete_voice is free and irreversible: ask before calling it.

Files

  • Public link: pass it as source.
  • Agent with a shell (Claude Code, Cursor, Codex, Gemini CLI): call get_upload_url { filename }, run the returned curlCommand with the local path, then pass the fileId as source. A fileId stays valid for 48 hours, so reuse it instead of uploading again.
  • Chat app (claude.ai, Claude apps): call get_upload_url and the user gets an upload button in the chat (if there is no button, give them browserUploadUrl). Wait for their message with the fileId. Do not upload from a code sandbox: its network blocks the upload domain.
  • ChatGPT: a file attached to the message reaches the tool through its file parameter, no upload step needed.

Tokens and confirmation

Tools spend VocaLingo tokens, the currency of the user's VocaLingo account (unrelated to LLM tokens). A call that would cost 50 tokens or more does not start: it returns status: "confirmation_required" with the price and a confirmToken. Show the price and ask. Only after the user agrees, repeat the same call with confirmToken added. Never confirm on the user's behalf. dryRun: true returns the estimate without starting anything. On insufficient_balance, tell the user to top up in the VocaLingo app and stop.

Errors

Every error has a code and a nextStep: follow nextStep. If the same call fails twice, show the error to the user and stop.

Not connected

If no VocaLingo tools are available, the server is not connected yet. Send the user to https://github.com/umakhanpro/vocalingo-mcp#connect. They need a VocaLingo account (https://vocalingo.app) and sign in through the browser.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.