{"info":{"title":"hexgrad/kokoro-82m","version":"1.0.0"},"paths":{"/":{"post":{"summary":"Generate","responses":{"200":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/Output"}}},"description":"Successful Response"}},"operationId":"hexgrad_kokoro_82m_generate","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/Input"}}},"required":true}}}},"openapi":"3.1.0","components":{"schemas":{"Input":{"type":"object","title":"Input","required":["text"],"properties":{"text":{"type":"string","title":"Text","x-order":0,"description":"Text to synthesize into speech. Long text is automatically split and synthesized in sequence."},"speed":{"type":"number","title":"Speed","default":1,"maximum":5,"minimum":0.1,"x-order":2,"description":"Speech speed multiplier (0.5 = half speed, 2.0 = double speed)."},"voice":{"allOf":[{"$ref":"#/components/schemas/VoiceEnum"}],"title":"Voice","default":"af_bella","x-order":1,"description":"Speaker voice. 46 voices across 6 languages, selected by one field: American and British English, French, Hindi, Italian, Japanese, and Mandarin Chinese. The two-letter prefix encodes language and gender (af_/am_ American English, bf_/bm_ British English, ff_ French, hf_/hm_ Hindi, if_/im_ Italian, jf_/jm_ Japanese, zf_/zm_ Mandarin Chinese; f = female, m = male). Pick a voice whose language matches your text."}}},"Output":{"type":"string","title":"Output","format":"uri","description":"URL of the generated speech audio file (WAV)."},"VoiceEnum":{"enum":["af_alloy","af_aoede","af_bella","af_jessica","af_kore","af_nicole","af_nova","af_river","af_sarah","af_sky","am_adam","am_echo","am_eric","am_fenrir","am_liam","am_michael","am_onyx","am_puck","bf_alice","bf_emma","bf_isabella","bf_lily","bm_daniel","bm_fable","bm_george","bm_lewis","ff_siwis","hf_alpha","hf_beta","hm_omega","hm_psi","if_sara","im_nicola","jf_alpha","jf_gongitsune","jf_nezumi","jf_tebukuro","jm_kumo","zf_xiaobei","zf_xiaoni","zf_xiaoxiao","zf_xiaoyi","zm_yunjian","zm_yunxi","zm_yunxia","zm_yunyang"],"type":"string","title":"VoiceEnum","description":"Kokoro voice identifier. The two-letter prefix encodes language and gender: af_/am_ American English, bf_/bm_ British English, ff_ French, hf_/hm_ Hindi, if_/im_ Italian, jf_/jm_ Japanese, zf_/zm_ Mandarin Chinese (f = female, m = male)."}}}}