Update to loudkit

{
  "description": "Help the user pick a loudkit voice by language or presentation, and let them hear it. Use when the user asks which voices or languages loudkit has, wants a voice for a given language, or wants to compare voices before generating audio.",
  "included_files": [
    {
      "relative_path": "references/voices.md",
      "size_in_bytes": 3325
    }
  ],
  "name": "choose-voice",
  "skill_md_contents": "---\nname: choose-voice\ndescription: Help the user pick a loudkit voice by language or presentation, and let them hear it. Use when the user asks which voices or languages loudkit has, wants a voice for a given language, or wants to compare voices before generating audio.\n---\n\n# Choose a voice\n\nloudkit ships 28 voices in 10 languages. Every voice is in both models,\n`loudreader/loudr-1` and `loudreader/loudr-1-turbo`, and loads by name.\nThe list with source and licence per voice is in\n[references/voices.md](references/voices.md).\n\n## Steps\n\n1. Ask for the language if the user did not name one. A voice carries its\n   language, so the language decides the shortlist.\n2. Offer the voices for that language from the list, with their presentation\n   (feminine or masculine). Do not\n   describe how a voice sounds: the list does not say, and you have not heard\n   it.\n3. Point the user to the voice gallery, which plays a sample of every voice:\n   https://loudkit.loudreader.io/demo/\n4. If you can run shell commands and loudkit is installed, offer to render the\n   same sentence in each shortlisted voice, one file per voice:\n\n   ```bash\n   loudkit speak \"A short sentence in the right language.\" --voice gosia -o gosia.wav\n   ```\n\n5. When the user picks a voice, say how to use it:\n   `--voice <name>` on the command line, `engine.voice(\"<name>\")` in code.\n\n## Be honest about quality\n\n- The project evaluated **English** by ear. For the other nine languages it\n  has no native-speaker evaluation. Say so when the user picks one of them.\n- Text handling (numbers, dates, abbreviations) covers 12 languages, more than\n  the 10 with voices.\n- No voice exists for a language not in the list. Do not offer a voice from\n  another language as if it spoke this one.\n\n## Licences\n\nEvery shipped voice is CC0 or CC-BY-4.0. A CC-BY-4.0 voice needs attribution\nwhen the user publishes audio made with it: name the source from the list.\n\nFor a voice that is not in the list, such as the user's own, use the\n`clone-voice` skill.\n"
}