{"id":97025,"plugin_id":"plugin_asdk_app_6abd51b0891c81918954286cdd388fa3","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-11-15T06:36:30.154Z","digest":"5bc3c634bdc1f5a8f455f5302a6b025077af06c3ffe6b4b92e9b123b6128a5e1","against":null,"payload":{"description":"Turn text into natural speech. Use for voiceovers, narration, read-alouds, audio versions of an article and lines spoken in a chosen voice or language.","included_files":[{"relative_path":"agents/openai.yaml","size_in_bytes":236}],"name":"ai-voice-generator","skill_md_contents":"---\nname: ai-voice-generator\ndescription: Turn text into natural speech. Use for voiceovers, narration, read-alouds, audio versions of an article and lines spoken in a chosen voice or language.\n---\n# Voiceover\n\n1. Fix the exact text to speak. Ask only when it is missing.\n2. Choose a speech model: call `list_models` with `endpoint` set to `/v1/audio/speech`, unless the user names a model.\n3. Choose a voice: call `list_voices` with that `model`. Filter by `language`, written as its English name such as `Spanish`, or by `gender`, when the user asks for one. Pick a voice that fits the request.\n4. Call `text_to_speech` with the `model`, the text as `input` and the `voice`.\n5. Reply with the audio link, the voice and the model.\n\nFor a different voice, list the voices again and offer three by name.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}