{"skill":{"slug":"kokoro-tts","displayName":"Kokoro TTS","summary":"Generate spoken audio from text using the local Kokoro TTS engine. Use when the user asks to \"say\" something, requests a voice message, or wants text converted to speech.","description":"---\nname: kokoro-tts\ndescription: Generate spoken audio from text using the local Kokoro TTS engine. Use when the user asks to \"say\" something, requests a voice message, or wants text converted to speech.\n---\n\n# Kokoro TTS\n\nThis skill allows you to generate high-quality AI speech using a local or remote Kokoro-TTS instance.\n\n## Configuration\n\nThe skill uses the `KOKORO_API_URL` environment variable to locate the API.\n\n- **Default:** `http://localhost:8880/v1/audio/speech`\n- **To Configure:** Add `KOKORO_API_URL=http://your-server:port/v1/audio/speech` to your `.env` file or environment.\n\n## Usage\n\nTo generate speech, run the included Node.js script.\n\n### Command\n\n```bash\nnode skills/kokoro-tts/scripts/tts.js \"<text>\" [voice] [speed]\n```\n\n- **text**: The text to speak. Wrap in quotes.\n- **voice**: (Optional) The voice ID. Defaults to `af_heart`.\n- **speed**: (Optional) Speech speed (0.25 to 4.0). Defaults to `1.0`.\n\n### Example\n\n```bash\nnode skills/kokoro-tts/scripts/tts.js \"Hello Ed, this is Theosaurus speaking.\" af_nova\n```\n\n### Output\n\nThe script will output a single line starting with `MEDIA:` followed by the path to the generated MP3 file. OpenClaw will automatically pick this up and send it as an audio attachment.\n\nExample Output:\n`MEDIA: media/tts_1706745000000.mp3`\n\n## Available Voices\n\nCommon choices:\n- `af_heart` (Default, Female, Warm)\n- `af_nova` (Female, Professional)\n- `am_adam` (Male, Deep)\n- `bf_alice` (British Female)\n\nFor a full list, see [references/voices.md](references/voices.md) or query the API.\n","tags":{"latest":"0.1.0"},"stats":{"comments":0,"downloads":7071,"installsAllTime":37,"installsCurrent":37,"stars":1,"versions":1},"createdAt":1769905003380,"updatedAt":1778485932126},"latestVersion":{"version":"0.1.0","createdAt":1769905003380,"changelog":"kokoro-tts 0.1.0\n\n- Initial release of the Kokoro TTS skill for generating speech audio from text.\n- Supports configuration via the KOKORO_API_URL environment variable.\n- Includes a Node.js script for generating audio files with customizable voice and speed.\n- Outputs MP3 file paths in a format compatible with OpenClaw for automatic audio attachment.\n- Provides several built-in voice options and instructions for listing all available voices.","license":null},"metadata":null,"owner":{"handle":"edkief","userId":"s178bftbwy1x73a1va9pdtj9ax885qxa","displayName":"edkief","image":"https://avatars.githubusercontent.com/u/17440999?v=4"},"moderation":null}