Agent Plugins Marketplace
← All plugins

speech

v0.2.8

Text-to-speech narration. The narrate skill turns a script into narration.wav plus words.json, a start and end time for every word. The default kokoro backend runs Kokoro-82M locally with onnxruntime. The optional elevenlabs backend sends the text to the third-party ElevenLabs API (ELEVENLABS_API_KEY) after showing a cost estimate; an organization can forbid it. You install espeak-ng (GPL-3.0). A hook installs the Python packages; setup downloads the models; check reports missing prerequisites.

Claude Code3 Skills

By Melodic SoftwareLicense: MIT21 GitHub starsUpdated 2 days ago

Directory evidence

Runtimes
Claude Code
Parsed components
3 skill or MCP entries
Source updated
Oct 4, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install speech for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install speech@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/melodic-software/claude-code-plugins

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/speech/.

Plugin files

plugins/speech/
├── .claude-plugin/plugin.json
├── skills/check/SKILL.md
├── skills/narrate/SKILL.md
└── skills/setup/SKILL.md

Included Skills3

checkskills/check/SKILL.md

Read-only check of the speech plugin's text-to-speech prerequisites: Python 3.12+, Node.js, espeak-ng, the hook-installed numpy and onnxruntime, and the Kokoro model files. Use when: 'narrate stopped with exit 2', 'what is speech missing', 'is text to speech ready', a session-start notice named a speech prerequisite, or before assuming narration will run. Reports each missing prerequisite with its remedy. Does not install.

narrateskills/narrate/SKILL.md

Text-to-speech: turn a narration script into narration.wav plus words.json, a start and end time in seconds for every word of the script, so a video, caption track or page can sync to the voice. The default kokoro backend is local, with no network at run time. The optional elevenlabs backend sends the script text to the third-party ElevenLabs API (api.elevenlabs.io), only after showing its character count, host and cost estimate and getting the user's go-ahead. Use when: 'narrate this script', 'text to speech', 'read this aloud', 'make a voiceover', 'generate narration audio', 'TTS with word timings', 'I need audio for this explainer', 'narrate with elevenlabs'. Not for transcribing existing audio.

setupskills/setup/SKILL.md

Set up the speech plugin's text-to-speech prerequisites: check reports Python, espeak-ng, the hook-installed Python packages and the Kokoro model files; apply install-model downloads the pinned Kokoro-82M model, tokenizer and English voices (about 340 MB) into the plugin data directory. Use when: 'set up speech', 'set up text to speech', 'download the kokoro model', 'is narrate ready', or /speech:narrate stopped with exit 2. Never installs espeak-ng.

Plugin manifests1

plugins/speech/.claude-plugin/plugin.json
{
  "name": "speech",
  "version": "0.2.8",
  "description": "Text-to-speech narration. The narrate skill turns a script into narration.wav plus words.json, a start and end time for every word. The default kokoro backend runs Kokoro-82M locally with onnxruntime. The optional elevenlabs backend sends the text to the third-party ElevenLabs API (ELEVENLABS_API_KEY) after showing a cost estimate; an organization can forbid it. You install espeak-ng (GPL-3.0). A hook installs the Python packages; setup downloads the models; check reports missing prerequisites.",
  "author": {
    "name": "Melodic Software",
    "email": "[email protected]"
  },
  "license": "MIT",
  "keywords": [
    "speech",
    "text-to-speech",
    "tts",
    "narration",
    "kokoro",
    "elevenlabs",
    "word-timings",
    "skill"
  ]
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[speech on Agent Plugins Marketplace](https://pluginsmp.com/plugins/speech)