Answers from the documentation; checking which model is on duty
Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
duby - Skill - OpenSmartRoute
Skillv1.0.0
duby
Convert text to speech using Duby.so API. Supports various voices and emotions.
Imported from kunwl123456/zeroclaw-skills-collection (duby/SKILL.md). Install upstream with npx skills add kunwl123456/zeroclaw-skills-collection --skill duby. Copyright stays with the author.
Duby TTS Skill
Convert text to speech using Duby.so API.
Tools
duby_tts
Convert text to speech and return a media file path.
text (required): The text to convert.
voice_id (optional): The Voice ID to use. Defaults to 2719350d-9f0c-40af-83aa-b3879a115ca1 (Xinduo).
Examples
# Default voiceduby_tts "Hello world"# Specific voiceduby_tts "Hello world" "some-voice-id"
Implementation
Uses tts.sh script with curl and jq.
Requires API_KEY to be set in the script.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - a plan picks it for its slotcurl-s-X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
Installed into a catalogue, chosen by a router
Install duby and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.
{
"ocm": "1",
"id": "kunwl123456-zeroclaw-skills-collection-duby",
"kind": "skill",
"name": "duby",
"description": "Convert text to speech using Duby.so API. Supports various voices and emotions.",
"publisher": "kunwl123456",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding"
],
"tags": [
"skill-md",
"tts",
"audio",
"voice",
"duby",
"github"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Convert text to speech using Duby.so API. Supports various voices and emotions."
],
"primary": false,
"metadata": {
"source": {
"provider": "github",
"repository": "https://github.com/kunwl123456/zeroclaw-skills-collection",
"path": "duby/SKILL.md",
"ref": "2b68cb5c6611b4077385d98e8bc9831fac9ddff9",
"url": "https://github.com/kunwl123456/zeroclaw-skills-collection/blob/2b68cb5c6611b4077385d98e8bc9831fac9ddff9/duby/SKILL.md",
"key": "kunwl123456/zeroclaw-skills-collection/duby/SKILL.md"
}
},
"instructions": "# Duby TTS Skill\n\nConvert text to speech using Duby.so API.\n\n## Tools\n\n### duby_tts\nConvert text to speech and return a media file path.\n\n- **text** (required): The text to convert.\n- **voice_id** (optional): The Voice ID to use. Defaults to `2719350d-9f0c-40af-83aa-b3879a115ca1` (Xinduo).\n\n## Examples\n\n```bash\n# Default voice\nduby_tts \"Hello world\"\n\n# Specific voice\nduby_tts \"Hello world\" \"some-voice-id\"\n```\n\n## Implementation\nUses `tts.sh` script with curl and jq.\nRequires `API_KEY` to be set in the script.",
"cost": {
"context_tokens": 128
}
}
Fetch it by URL: GET /api/v1/registry/kunwl123456-zeroclaw-skills-collection-duby/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.