agentleFS
paulpreibischpaulpreibisch/AgentVibes/.agents/skills/agentvibes-grokbot-tts-setup/SKILL.md

AgentVibes GrokBot TTS setup

Skill155 starsChanged 46 days agoApache-2.0View on GitHub

Use when installing AgentVibes TTS + Kokoro on Windows for a GrokBot fleet, or when each bot needs a unique spoken Kokoro voice and -llm identity.

  • Installs packages

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    If pip is missing:

    line 39
  2. Very specific:

    Prefer the AgentVibes TUI provider picker.

    line 47
  3. Very specific:

    Update %USERPROFILE%\.grokbot\agentvibes-tts.md if that cheat sheet exists

    line 72
  4. Distinctive:

    Keep spoken lines short; the pretext carries identity.

    line 84

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Install AgentVibes + Kokoro for a GrokBot fleet

Goal

Install AgentVibes and Kokoro on the user's Windows machine, set Kokoro as the TTS provider, and give each GrokBot a unique -llm identity, Kokoro voice, and spoken name so speech plays on local speakers.

Prerequisites

  • Windows machine available via Shell (Node.js + Python 3)
  • Permission to install npm/pip packages on that machine

Steps

1. Install AgentVibes

npx agentvibes install

Open the TUI anytime with:

npx agentvibes

2. Install Kokoro

pip install kokoro soundfile numpy

If pip is missing:

python -m pip install kokoro soundfile numpy

3. Set provider to Kokoro

Prefer the AgentVibes TUI provider picker. On Windows you can also run:

powershell -NoProfile -ExecutionPolicy Bypass -File "$env:USERPROFILE\.claude\hooks-windows\provider-manager.ps1" set kokoro

(If AgentVibes installed under a project .claude folder, use that hooks-windows path instead.)

4. Verify speech

Play a short test line via play-tts.ps1 (under AgentVibes .claude\hooks-windows) and confirm audio on the local speakers.

5. Assign fleet voices

For each GrokBot, add one row to audio-effects.cfg:

llm:<key>|light||0.20|<kokoro_voice>|<Spoken Name> GrokBot|kokoro

Rules:

  • One unique Kokoro voice per bot (no reuse)
  • Spoken pretext must identify the bot (e.g. Chief of Staff GrokBot)
  • Mirror rows into both project and user .claude\config\audio-effects.cfg when both exist
  • Update %USERPROFILE%\.grokbot\agentvibes-tts.md if that cheat sheet exists

Example voices: am_michael, am_adam, bm_george, af_bella, af_nicole, af_sarah, bm_lewis.

6. Teach each bot to speak

Each bot should call:

& "<AgentVibes>\.claude\hooks-windows\play-tts.ps1" -Text "Short update." -llm "<their-key>"

Keep spoken lines short; the pretext carries identity.

7. Prove it

Play one short test line per bot with its -llm key so the user can hear the voice differences. Report the roster table (bot → key → voice → spoken name).

Do not

  • Publish website/blog content unless asked
  • Reuse Kokoro voices across bots
  • Rely on MCP for local speaker playback (GrokBot MCP runs off-machine)

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.