{"openapi":"3.1.0","info":{"title":"Qwen3 Voice Design API","version":"0.1.0"},"paths":{"/v1/voice/design":{"post":{"tags":["voice"],"summary":"Voice Design","operationId":"voice_design_v1_voice_design_post","parameters":[{"name":"authorization","in":"header","required":false,"schema":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Authorization"}}],"requestBody":{"required":true,"content":{"application/json":{"schema":{"$ref":"#/components/schemas/VoiceDesignRequest"}}}},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/v1/voice/synthesize":{"post":{"tags":["voice"],"summary":"Voice Synthesize","operationId":"voice_synthesize_v1_voice_synthesize_post","parameters":[{"name":"authorization","in":"header","required":false,"schema":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Authorization"}}],"requestBody":{"required":true,"content":{"application/json":{"schema":{"$ref":"#/components/schemas/VoiceSynthesizeRequest"}}}},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/v1/voice/clone":{"post":{"tags":["voice"],"summary":"Voice Clone","operationId":"voice_clone_v1_voice_clone_post","parameters":[{"name":"authorization","in":"header","required":false,"schema":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Authorization"}}],"requestBody":{"content":{"multipart/form-data":{"schema":{"$ref":"#/components/schemas/Body_voice_clone_v1_voice_clone_post"}}}},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/v1/asr/transcribe":{"post":{"tags":["asr"],"summary":"Asr Transcribe","operationId":"asr_transcribe_v1_asr_transcribe_post","parameters":[{"name":"authorization","in":"header","required":false,"schema":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Authorization"}}],"requestBody":{"content":{"multipart/form-data":{"schema":{"$ref":"#/components/schemas/Body_asr_transcribe_v1_asr_transcribe_post"}}}},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/v1/audio/denoise":{"post":{"tags":["audio"],"summary":"Audio Enhance","operationId":"audio_enhance_v1_audio_denoise_post","parameters":[{"name":"authorization","in":"header","required":false,"schema":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Authorization"}}],"requestBody":{"content":{"multipart/form-data":{"schema":{"$ref":"#/components/schemas/Body_audio_enhance_v1_audio_denoise_post"}}}},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/v1/audio/enhance":{"post":{"tags":["audio"],"summary":"Audio Enhance","operationId":"audio_enhance_v1_audio_enhance_post","parameters":[{"name":"authorization","in":"header","required":false,"schema":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Authorization"}}],"requestBody":{"content":{"multipart/form-data":{"schema":{"$ref":"#/components/schemas/Body_audio_enhance_v1_audio_enhance_post"}}}},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/v1/audio/reuse":{"post":{"tags":["audio"],"summary":"Audio Reuse","operationId":"audio_reuse_v1_audio_reuse_post","parameters":[{"name":"authorization","in":"header","required":false,"schema":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Authorization"}}],"requestBody":{"content":{"multipart/form-data":{"schema":{"$ref":"#/components/schemas/Body_audio_reuse_v1_audio_reuse_post"}}}},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/v1/audio/music":{"post":{"tags":["audio"],"summary":"Audio Music","operationId":"audio_music_v1_audio_music_post","parameters":[{"name":"authorization","in":"header","required":false,"schema":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Authorization"}}],"requestBody":{"required":true,"content":{"application/json":{"schema":{"$ref":"#/components/schemas/StableAudio3GenerationRequest"}}}},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/v1/audio/music/yue2":{"post":{"tags":["audio"],"summary":"Audio Music Yue2","operationId":"audio_music_yue2_v1_audio_music_yue2_post","parameters":[{"name":"authorization","in":"header","required":false,"schema":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Authorization"}}],"requestBody":{"required":true,"content":{"application/json":{"schema":{"$ref":"#/components/schemas/Yue2GenerationRequest"}}}},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/v1/audio/music/acestep":{"post":{"tags":["audio"],"summary":"Audio Music Acestep","operationId":"audio_music_acestep_v1_audio_music_acestep_post","parameters":[{"name":"authorization","in":"header","required":false,"schema":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Authorization"}}],"requestBody":{"required":true,"content":{"application/json":{"schema":{"$ref":"#/components/schemas/AceStepGenerationRequest"}}}},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/v1/audio/sfx":{"post":{"tags":["audio"],"summary":"Audio Sfx","operationId":"audio_sfx_v1_audio_sfx_post","parameters":[{"name":"authorization","in":"header","required":false,"schema":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Authorization"}}],"requestBody":{"required":true,"content":{"application/json":{"schema":{"$ref":"#/components/schemas/StableAudio3SfxRequest"}}}},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/health":{"get":{"tags":["system"],"summary":"Health","operationId":"health_health_get","responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"additionalProperties":true,"type":"object","title":"Response Health Health Get"}}}}}}},"/models":{"get":{"tags":["system"],"summary":"Models","operationId":"models_models_get","responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"additionalProperties":true,"type":"object","title":"Response Models Models Get"}}}}}}}},"components":{"schemas":{"AceStepGenerationRequest":{"properties":{"prompt":{"type":"string","maxLength":512,"minLength":1,"title":"Prompt"},"lyrics":{"type":"string","maxLength":4096,"title":"Lyrics","default":""},"instrumental":{"type":"boolean","title":"Instrumental","default":true},"seconds":{"type":"number","maximum":600.0,"minimum":10.0,"title":"Seconds","default":30.0},"steps":{"type":"integer","maximum":20.0,"minimum":1.0,"title":"Steps","default":8},"seed":{"anyOf":[{"type":"integer","maximum":4294967295.0,"minimum":0.0},{"type":"null"}],"title":"Seed"},"use_lm":{"type":"boolean","title":"Use Lm","default":true},"vocal_language":{"type":"string","enum":["ar","az","bg","bn","ca","cs","da","de","el","en","es","fa","fi","fr","he","hi","hr","ht","hu","id","is","it","ja","ko","la","lt","ms","ne","nl","no","pa","pl","pt","ro","ru","sa","sk","sr","sv","sw","ta","te","th","tl","tr","uk","ur","vi","yue","zh","unknown"],"title":"Vocal Language","default":"unknown"},"bpm":{"anyOf":[{"type":"integer","maximum":300.0,"minimum":30.0},{"type":"null"}],"title":"Bpm"},"keyscale":{"type":"string","maxLength":16,"title":"Keyscale","default":""},"timesignature":{"type":"string","enum":["","2","3","4","6"],"title":"Timesignature","default":""}},"additionalProperties":false,"type":"object","required":["prompt"],"title":"AceStepGenerationRequest","description":"Bounded text-to-music surface for the pinned 1.5 Turbo model only."},"Body_asr_transcribe_v1_asr_transcribe_post":{"properties":{"file":{"anyOf":[{"type":"string","contentMediaType":"application/octet-stream"},{"type":"null"}],"title":"File"},"language":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Language"},"temperature":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Temperature"},"max_tokens":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Max Tokens"},"top_k":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Top K"},"top_p":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Top P"},"repetition_penalty":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Repetition Penalty"}},"type":"object","title":"Body_asr_transcribe_v1_asr_transcribe_post"},"Body_audio_enhance_v1_audio_denoise_post":{"properties":{"file":{"anyOf":[{"type":"string","contentMediaType":"application/octet-stream"},{"type":"null"}],"title":"File"},"chunked":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Chunked"}},"type":"object","title":"Body_audio_enhance_v1_audio_denoise_post"},"Body_audio_enhance_v1_audio_enhance_post":{"properties":{"file":{"anyOf":[{"type":"string","contentMediaType":"application/octet-stream"},{"type":"null"}],"title":"File"},"chunked":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Chunked"}},"type":"object","title":"Body_audio_enhance_v1_audio_enhance_post"},"Body_audio_reuse_v1_audio_reuse_post":{"properties":{"file":{"anyOf":[{"type":"string","contentMediaType":"application/octet-stream"},{"type":"null"}],"title":"File"}},"type":"object","title":"Body_audio_reuse_v1_audio_reuse_post"},"Body_voice_clone_v1_voice_clone_post":{"properties":{"file":{"anyOf":[{"type":"string","contentMediaType":"application/octet-stream"},{"type":"null"}],"title":"File"},"text":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Text"},"ref_text":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Ref Text"},"language":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Language"},"temperature":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Temperature"},"max_tokens":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Max Tokens"},"top_k":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Top K"},"top_p":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Top P"},"repetition_penalty":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Repetition Penalty"},"provider":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Provider"},"instruct":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Instruct"},"cfg_value":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Cfg Value"},"inference_timesteps":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Inference Timesteps"},"normalize":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Normalize"},"denoise":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Denoise"},"retry_badcase":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Retry Badcase"}},"type":"object","title":"Body_voice_clone_v1_voice_clone_post"},"HTTPValidationError":{"properties":{"detail":{"items":{"$ref":"#/components/schemas/ValidationError"},"type":"array","title":"Detail"}},"type":"object","title":"HTTPValidationError"},"StableAudio3GenerationRequest":{"properties":{"prompt":{"type":"string","maxLength":2000,"minLength":1,"title":"Prompt"},"negative_prompt":{"anyOf":[{"type":"string","maxLength":2000},{"type":"null"}],"title":"Negative Prompt"},"seconds":{"type":"number","maximum":380.0,"exclusiveMinimum":0.0,"title":"Seconds","default":30.0},"steps":{"type":"integer","maximum":64.0,"minimum":1.0,"title":"Steps","default":8},"seed":{"anyOf":[{"type":"integer","maximum":2147483647.0,"minimum":0.0},{"type":"null"}],"title":"Seed"},"cfg":{"type":"number","maximum":10.0,"minimum":0.0,"title":"Cfg","default":1.0},"apg":{"type":"number","maximum":1.0,"minimum":0.0,"title":"Apg","default":1.0}},"type":"object","required":["prompt"],"title":"StableAudio3GenerationRequest"},"StableAudio3SfxRequest":{"properties":{"prompt":{"type":"string","maxLength":2000,"minLength":1,"title":"Prompt"},"negative_prompt":{"anyOf":[{"type":"string","maxLength":2000},{"type":"null"}],"title":"Negative Prompt"},"seconds":{"type":"number","maximum":380.0,"exclusiveMinimum":0.0,"title":"Seconds","default":5.0},"steps":{"type":"integer","maximum":64.0,"minimum":1.0,"title":"Steps","default":8},"seed":{"anyOf":[{"type":"integer","maximum":2147483647.0,"minimum":0.0},{"type":"null"}],"title":"Seed"},"cfg":{"type":"number","maximum":10.0,"minimum":0.0,"title":"Cfg","default":1.0},"apg":{"type":"number","maximum":1.0,"minimum":0.0,"title":"Apg","default":1.0}},"type":"object","required":["prompt"],"title":"StableAudio3SfxRequest"},"ValidationError":{"properties":{"loc":{"items":{"anyOf":[{"type":"string"},{"type":"integer"}]},"type":"array","title":"Location"},"msg":{"type":"string","title":"Message"},"type":{"type":"string","title":"Error Type"},"input":{"title":"Input"},"ctx":{"type":"object","title":"Context"}},"type":"object","required":["loc","msg","type"],"title":"ValidationError"},"VoiceDesignRequest":{"properties":{"text":{"type":"string","maxLength":4096,"minLength":1,"title":"Text"},"instruct":{"type":"string","maxLength":1024,"minLength":1,"title":"Instruct"},"provider":{"type":"string","title":"Provider","default":"qwen"},"cfg_value":{"type":"number","maximum":10.0,"minimum":0.0,"title":"Cfg Value","default":2.0},"inference_timesteps":{"type":"integer","maximum":200.0,"minimum":1.0,"title":"Inference Timesteps","default":10},"normalize":{"type":"boolean","title":"Normalize","default":false},"denoise":{"type":"boolean","title":"Denoise","default":false},"retry_badcase":{"type":"boolean","title":"Retry Badcase","default":true},"language":{"type":"string","title":"Language","default":"auto"},"temperature":{"type":"number","maximum":2.0,"minimum":0.0,"title":"Temperature","default":0.9},"max_tokens":{"type":"integer","maximum":8192.0,"minimum":1.0,"title":"Max Tokens","default":4096},"top_k":{"type":"integer","maximum":1000.0,"minimum":0.0,"title":"Top K","default":50},"top_p":{"type":"number","maximum":1.0,"minimum":0.0,"title":"Top P","default":1.0},"repetition_penalty":{"type":"number","maximum":2.0,"minimum":0.1,"title":"Repetition Penalty","default":1.05}},"type":"object","required":["text","instruct"],"title":"VoiceDesignRequest"},"VoiceSynthesizeRequest":{"properties":{"text":{"type":"string","maxLength":4096,"minLength":1,"title":"Text"},"speaker":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Speaker"},"language":{"type":"string","title":"Language","default":"auto"},"temperature":{"type":"number","maximum":2.0,"minimum":0.0,"title":"Temperature","default":0.9},"max_tokens":{"type":"integer","maximum":8192.0,"minimum":1.0,"title":"Max Tokens","default":4096},"top_k":{"type":"integer","maximum":1000.0,"minimum":0.0,"title":"Top K","default":50},"top_p":{"type":"number","maximum":1.0,"minimum":0.0,"title":"Top P","default":1.0},"repetition_penalty":{"type":"number","maximum":2.0,"minimum":0.1,"title":"Repetition Penalty","default":1.05}},"type":"object","required":["text"],"title":"VoiceSynthesizeRequest"},"Yue2GenerationRequest":{"properties":{"style":{"type":"string","maxLength":4000,"minLength":1,"title":"Style"},"lyrics":{"type":"string","maxLength":30000,"minLength":1,"title":"Lyrics"},"mode":{"type":"string","enum":["direct","melody","full"],"title":"Mode","default":"full"},"abc":{"anyOf":[{"type":"string","maxLength":100000},{"type":"null"}],"title":"Abc"},"steps":{"type":"integer","maximum":64.0,"minimum":1.0,"title":"Steps","default":8},"seed":{"type":"integer","maximum":9.223372036854776e+18,"minimum":0.0,"title":"Seed","default":831001},"cfg_scale":{"type":"number","maximum":20.0,"minimum":0.0,"title":"Cfg Scale","default":1.0},"min_duration_seconds":{"type":"integer","maximum":360.0,"minimum":8.0,"title":"Min Duration Seconds","default":8},"max_duration_seconds":{"type":"integer","maximum":360.0,"minimum":8.0,"title":"Max Duration Seconds","default":120}},"additionalProperties":false,"type":"object","required":["style","lyrics"],"title":"Yue2GenerationRequest"}}}}