{"info":{"title":"ModelRunner OpenAPI schema for minimax/speech-02-hd","version":"0.1.0"},"paths":{"/health-check":{"get":{"summary":"Healthcheck","responses":{"200":{"content":{"application/json":{"schema":{"title":"Response Healthcheck Health Check Get"}}},"description":"Successful Response"}},"operationId":"healthcheck_health_check_get"}}},"openapi":"3.1.0","components":{"schemas":{"Input":{"type":"object","title":"Input","required":["text"],"properties":{"text":{"type":"string","title":"Text","x-order":0,"maxLength":5000,"minLength":1,"description":"The text to synthesize into speech. Up to 5000 characters."},"voice_setting":{"type":"object","title":"Voice Setting","x-order":1,"properties":{"vol":{"type":"number","title":"Vol","default":1,"maximum":10,"minimum":0.01,"x-order":2,"description":"Output volume multiplier."},"pitch":{"type":"integer","title":"Pitch","default":0,"maximum":12,"minimum":-12,"x-order":3,"description":"Pitch shift in semitones. 0 is the voice's natural pitch."},"speed":{"type":"number","title":"Speed","default":1,"maximum":2,"minimum":0.5,"x-order":1,"description":"Speaking speed. 1 is normal; lower is slower, higher is faster."},"emotion":{"allOf":[{"$ref":"#/components/schemas/EmotionEnum"}],"title":"Emotion","x-order":4,"description":"Emotional tone of the delivery. Leave unset for a neutral read."},"voice_id":{"type":"string","title":"Voice Id","default":"Wise_Woman","x-order":0,"description":"The voice to speak with. 300+ voices supported; pass the voice id as a string. Examples: Wise_Woman, Friendly_Person, Deep_Voice_Man, Calm_Woman, Casual_Guy, Lively_Girl, Patient_Man."},"english_normalization":{"type":"boolean","title":"English Normalization","default":false,"x-order":5,"description":"If true, normalize English text (e.g. numbers and units) before synthesis for more natural pronunciation."}},"description":"Voice selection and delivery controls.","x-fal-order-properties":["voice_id","speed","vol","pitch","emotion","english_normalization"]},"language_boost":{"allOf":[{"$ref":"#/components/schemas/LanguageBoostEnum"}],"title":"Language Boost","x-order":2,"description":"Hint the primary language/dialect to improve recognition for non-default or mixed-language text. Use a language name or 'auto'. Leave unset to let the model detect it."}},"x-fal-order-properties":["text","voice_setting","language_boost"]},"Output":{"type":"string","title":"Output","format":"uri","description":"Generated speech audio file URL (MP3)."},"EmotionEnum":{"enum":["happy","sad","angry","fearful","disgusted","surprised","neutral"],"type":"string","title":"EmotionEnum","description":"Emotional tone of speech delivery."},"LanguageBoostEnum":{"enum":["Chinese","Chinese,Yue","English","Arabic","Russian","Spanish","French","Portuguese","German","Turkish","Dutch","Ukrainian","Vietnamese","Indonesian","Japanese","Italian","Korean","Thai","Polish","Romanian","Greek","Czech","Finnish","Hindi","Bulgarian","Danish","Hebrew","Malay","Slovak","Swedish","Croatian","Hungarian","Norwegian","Slovenian","Catalan","Nynorsk","Afrikaans","auto"],"type":"string","title":"LanguageBoostEnum","description":"Primary language hint for improved recognition."}}}}