{ "@context": { "@version": 1.1, "schema": "https://schema.org/", "lmnt": "https://docs.lmnt.com/vocabulary#", "xsd": "http://www.w3.org/2001/XMLSchema#", "Voice": { "@id": "lmnt:Voice", "@type": "@id", "comment": "A voice model available for text-to-speech synthesis in the LMNT platform." }, "id": { "@id": "schema:identifier", "@type": "xsd:string" }, "name": { "@id": "schema:name", "@type": "xsd:string" }, "description": { "@id": "schema:description", "@type": "xsd:string" }, "state": { "@id": "lmnt:voiceState", "@type": "xsd:string", "comment": "Lifecycle state of a voice: preparing, pending, training, ready, broken, cancelled." }, "owner": { "@id": "lmnt:voiceOwner", "@type": "xsd:string", "comment": "Ownership scope: system, me, or all." }, "type": { "@id": "lmnt:voiceType", "@type": "xsd:string", "comment": "Voice cloning type: instant, professional, or intrinsic." }, "gender": { "@id": "schema:gender", "@type": "xsd:string" }, "starred": { "@id": "lmnt:starred", "@type": "xsd:boolean" }, "tags": { "@id": "schema:keywords", "@container": "@set" }, "preview_url": { "@id": "schema:audio", "@type": "@id" }, "SpeechSynthesisRequest": { "@id": "lmnt:SpeechSynthesisRequest", "@type": "@id", "comment": "A request to synthesize text into audio using the LMNT Speech API." }, "voice": { "@id": "lmnt:usesVoice", "@type": "xsd:string" }, "text": { "@id": "schema:text", "@type": "xsd:string" }, "format": { "@id": "schema:encodingFormat", "@type": "xsd:string" }, "sample_rate": { "@id": "lmnt:sampleRate", "@type": "xsd:integer" }, "speed": { "@id": "lmnt:speechSpeed", "@type": "xsd:decimal" }, "temperature": { "@id": "lmnt:speechTemperature", "@type": "xsd:decimal" }, "language": { "@id": "schema:inLanguage", "@type": "xsd:string" }, "return_timestamps": { "@id": "lmnt:returnTimestamps", "@type": "xsd:boolean" }, "conversational": { "@id": "lmnt:conversationalMode", "@type": "xsd:boolean" }, "model": { "@id": "lmnt:modelId", "@type": "xsd:string" }, "SpeechSession": { "@id": "lmnt:SpeechSession", "@type": "@id", "comment": "A WebSocket-based real-time streaming session for text-to-speech generation." }, "voices": { "@id": "lmnt:voices", "@container": "@list" } } }