openapi.json

{"openapi":"3.0.2","info":{"title":"VOICEVOX ENGINE","description":"VOICEVOXの音声合成エンジンです。","version":"0.10.4"},"paths":{"/audio_query":{"post":{"tags":["クエリ作成"],"summary":"音声合成用のクエリを作成する","description":"クエリの初期値を得ます。ここで得られたクエリはそのまま音声合成に利用できます。各値の意味は`Schemas`を参照してください。","operationId":"audio_query_audio_query_post","parameters":[{"required":true,"schema":{"title":"Text","type":"string"},"name":"text","in":"query"},{"required":true,"schema":{"title":"Speaker","type":"integer"},"name":"speaker","in":"query"},{"required":false,"schema":{"title":"Core Version","type":"string"},"name":"core_version","in":"query"}],"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/AudioQuery"}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/audio_query_from_preset":{"post":{"tags":["クエリ作成"],"summary":"音声合成用のクエリをプリセットを用いて作成する","description":"クエリの初期値を得ます。ここで得られたクエリはそのまま音声合成に利用できます。各値の意味は`Schemas`を参照してください。","operationId":"audio_query_from_preset_audio_query_from_preset_post","parameters":[{"required":true,"schema":{"title":"Text","type":"string"},"name":"text","in":"query"},{"required":true,"schema":{"title":"Preset Id","type":"integer"},"name":"preset_id","in":"query"},{"required":false,"schema":{"title":"Core Version","type":"string"},"name":"core_version","in":"query"}],"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/AudioQuery"}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/accent_phrases":{"post":{"tags":["クエリ編集"],"summary":"テキストからアクセント句を得る","description":"テキストからアクセント句を得ます。\nis_kanaが`true`のとき、テキストは次のようなAquesTalkライクな記法に従う読み仮名として処理されます。デフォルトは`false`です。\n* 全てのカナはカタカナで記述される\n* アクセント句は`/`または`、`で区切る。`、`で区切った場合に限り無音区間が挿入される。\n* カナの手前に`_`を入れるとそのカナは無声化される\n* アクセント位置を`'`で指定する。全てのアクセント句にはアクセント位置を1つ指定する必要がある。\n* アクセント句末に`？`(全角)を入れることにより疑問文の発音ができる。","operationId":"accent_phrases_accent_phrases_post","parameters":[{"required":true,"schema":{"title":"Text","type":"string"},"name":"text","in":"query"},{"required":true,"schema":{"title":"Speaker","type":"integer"},"name":"speaker","in":"query"},{"required":false,"schema":{"title":"Is Kana","type":"boolean","default":false},"name":"is_kana","in":"query"},{"required":false,"schema":{"title":"Core Version","type":"string"},"name":"core_version","in":"query"}],"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"title":"Response Accent Phrases Accent Phrases Post","type":"array","items":{"$ref":"#/components/schemas/AccentPhrase"}}}}},"400":{"description":"読み仮名のパースに失敗","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ParseKanaBadRequest"}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/mora_data":{"post":{"tags":["クエリ編集"],"summary":"アクセント句から音高・音素長を得る","operationId":"mora_data_mora_data_post","parameters":[{"required":true,"schema":{"title":"Speaker","type":"integer"},"name":"speaker","in":"query"},{"required":false,"schema":{"title":"Core Version","type":"string"},"name":"core_version","in":"query"}],"requestBody":{"content":{"application/json":{"schema":{"title":"Accent Phrases","type":"array","items":{"$ref":"#/components/schemas/AccentPhrase"}}}},"required":true},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"title":"Response Mora Data Mora Data Post","type":"array","items":{"$ref":"#/components/schemas/AccentPhrase"}}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/mora_length":{"post":{"tags":["クエリ編集"],"summary":"アクセント句から音素長を得る","operationId":"mora_length_mora_length_post","parameters":[{"required":true,"schema":{"title":"Speaker","type":"integer"},"name":"speaker","in":"query"},{"required":false,"schema":{"title":"Core Version","type":"string"},"name":"core_version","in":"query"}],"requestBody":{"content":{"application/json":{"schema":{"title":"Accent Phrases","type":"array","items":{"$ref":"#/components/schemas/AccentPhrase"}}}},"required":true},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"title":"Response Mora Length Mora Length Post","type":"array","items":{"$ref":"#/components/schemas/AccentPhrase"}}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/mora_pitch":{"post":{"tags":["クエリ編集"],"summary":"アクセント句から音高を得る","operationId":"mora_pitch_mora_pitch_post","parameters":[{"required":true,"schema":{"title":"Speaker","type":"integer"},"name":"speaker","in":"query"},{"required":false,"schema":{"title":"Core Version","type":"string"},"name":"core_version","in":"query"}],"requestBody":{"content":{"application/json":{"schema":{"title":"Accent Phrases","type":"array","items":{"$ref":"#/components/schemas/AccentPhrase"}}}},"required":true},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"title":"Response Mora Pitch Mora Pitch Post","type":"array","items":{"$ref":"#/components/schemas/AccentPhrase"}}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/synthesis":{"post":{"tags":["音声合成"],"summary":"音声合成する","operationId":"synthesis_synthesis_post","parameters":[{"required":true,"schema":{"title":"Speaker","type":"integer"},"name":"speaker","in":"query"},{"description":"疑問系のテキストが与えられたら語尾を自動調整する","required":false,"schema":{"title":"Enable Interrogative Upspeak","type":"boolean","description":"疑問系のテキストが与えられたら語尾を自動調整する","default":true},"name":"enable_interrogative_upspeak","in":"query"},{"required":false,"schema":{"title":"Core Version","type":"string"},"name":"core_version","in":"query"}],"requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/AudioQuery"}}},"required":true},"responses":{"200":{"description":"Successful Response","content":{"audio/wav":{"schema":{"type":"string","format":"binary"}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/cancellable_synthesis":{"post":{"tags":["音声合成"],"summary":"音声合成する（キャンセル可能）","operationId":"cancellable_synthesis_cancellable_synthesis_post","parameters":[{"required":true,"schema":{"title":"Speaker","type":"integer"},"name":"speaker","in":"query"}],"requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/AudioQuery"}}},"required":true},"responses":{"200":{"description":"Successful Response","content":{"audio/wav":{"schema":{"type":"string","format":"binary"}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/multi_synthesis":{"post":{"tags":["音声合成"],"summary":"複数まとめて音声合成する","operationId":"multi_synthesis_multi_synthesis_post","parameters":[{"required":true,"schema":{"title":"Speaker","type":"integer"},"name":"speaker","in":"query"},{"required":false,"schema":{"title":"Core Version","type":"string"},"name":"core_version","in":"query"}],"requestBody":{"content":{"application/json":{"schema":{"title":"Queries","type":"array","items":{"$ref":"#/components/schemas/AudioQuery"}}}},"required":true},"responses":{"200":{"description":"Successful Response","content":{"application/zip":{"schema":{"type":"string","format":"binary"}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/synthesis_morphing":{"post":{"tags":["音声合成"],"summary":"2人の話者でモーフィングした音声を合成する","description":"指定された2人の話者で音声を合成、指定した割合でモーフィングした音声を得ます。\nモーフィングの割合は`morph_rate`で指定でき、0.0でベースの話者、1.0でターゲットの話者に近づきます。","operationId":"_synthesis_morphing_synthesis_morphing_post","parameters":[{"required":true,"schema":{"title":"Base Speaker","type":"integer"},"name":"base_speaker","in":"query"},{"required":true,"schema":{"title":"Target Speaker","type":"integer"},"name":"target_speaker","in":"query"},{"required":true,"schema":{"title":"Morph Rate","maximum":1.0,"minimum":0.0,"type":"number"},"name":"morph_rate","in":"query"},{"required":false,"schema":{"title":"Core Version","type":"string"},"name":"core_version","in":"query"}],"requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/AudioQuery"}}},"required":true},"responses":{"200":{"description":"Successful Response","content":{"audio/wav":{"schema":{"type":"string","format":"binary"}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/connect_waves":{"post":{"tags":["その他"],"summary":"base64エンコードされた複数のwavデータを一つに結合する","description":"base64エンコードされたwavデータを一纏めにし、wavファイルで返します。","operationId":"connect_waves_connect_waves_post","requestBody":{"content":{"application/json":{"schema":{"title":"Waves","type":"array","items":{"type":"string"}}}},"required":true},"responses":{"200":{"description":"Successful Response","content":{"audio/wav":{"schema":{"type":"string","format":"binary"}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/presets":{"get":{"tags":["その他"],"summary":"Get Presets","description":"エンジンが保持しているプリセットの設定を返します\n\nReturns\n-------\npresets: List[Preset]\n    プリセットのリスト","operationId":"get_presets_presets_get","responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"title":"Response Get Presets Presets Get","type":"array","items":{"$ref":"#/components/schemas/Preset"}}}}}}}},"/version":{"get":{"tags":["その他"],"summary":"Version","operationId":"version_version_get","responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{}}}}}}},"/core_versions":{"get":{"tags":["その他"],"summary":"Core Versions","operationId":"core_versions_core_versions_get","responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"title":"Response Core Versions Core Versions Get","type":"array","items":{"type":"string"}}}}}}}},"/speakers":{"get":{"tags":["その他"],"summary":"Speakers","operationId":"speakers_speakers_get","parameters":[{"required":false,"schema":{"title":"Core Version","type":"string"},"name":"core_version","in":"query"}],"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"title":"Response Speakers Speakers Get","type":"array","items":{"$ref":"#/components/schemas/Speaker"}}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/speaker_info":{"get":{"tags":["その他"],"summary":"Speaker Info","description":"指定されたspeaker_uuidに関する情報をjson形式で返します。\n画像や音声はbase64エンコードされたものが返されます。\n\nReturns\n-------\nret_data: SpeakerInfo","operationId":"speaker_info_speaker_info_get","parameters":[{"required":true,"schema":{"title":"Speaker Uuid","type":"string"},"name":"speaker_uuid","in":"query"},{"required":false,"schema":{"title":"Core Version","type":"string"},"name":"core_version","in":"query"}],"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/SpeakerInfo"}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/user_dict":{"get":{"tags":["ユーザー辞書"],"summary":"Get User Dict Words","description":"ユーザ辞書に登録されている単語の一覧を返します。\n単語の表層形(surface)は正規化済みの物を返します。\n\nReturns\n-------\nDict[str, UserDictWord]\n    単語のUUIDとその詳細","operationId":"get_user_dict_words_user_dict_get","responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"title":"Response Get User Dict Words User Dict Get","type":"object","additionalProperties":{"$ref":"#/components/schemas/UserDictWord"}}}}}}}},"/user_dict_word":{"post":{"tags":["ユーザー辞書"],"summary":"Add User Dict Word","description":"ユーザ辞書に言葉を追加します。\n\nParameters\n----------\nsurface : str\n    言葉の表層形\npronunciation: str\n    言葉の発音（カタカナ）\naccent_type: int\n    アクセント型（音が下がる場所を指す）","operationId":"add_user_dict_word_user_dict_word_post","parameters":[{"required":true,"schema":{"title":"Surface","type":"string"},"name":"surface","in":"query"},{"required":true,"schema":{"title":"Pronunciation","type":"string"},"name":"pronunciation","in":"query"},{"required":true,"schema":{"title":"Accent Type","type":"integer"},"name":"accent_type","in":"query"}],"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"title":"Response Add User Dict Word User Dict Word Post","type":"string"}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/user_dict_word/{word_uuid}":{"put":{"tags":["ユーザー辞書"],"summary":"Rewrite User Dict Word","description":"ユーザ辞書に登録されている言葉を更新します。\n\nParameters\n----------\nsurface : str\n    言葉の表層形\npronunciation: str\n    言葉の発音（カタカナ）\naccent_type: int\n    アクセント型（音が下がる場所を指す）\nword_uuid: str\n    更新する言葉のUUID","operationId":"rewrite_user_dict_word_user_dict_word__word_uuid__put","parameters":[{"required":true,"schema":{"title":"Word Uuid","type":"string"},"name":"word_uuid","in":"path"},{"required":true,"schema":{"title":"Surface","type":"string"},"name":"surface","in":"query"},{"required":true,"schema":{"title":"Pronunciation","type":"string"},"name":"pronunciation","in":"query"},{"required":true,"schema":{"title":"Accent Type","type":"integer"},"name":"accent_type","in":"query"}],"responses":{"204":{"description":"Successful Response"},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}},"delete":{"tags":["ユーザー辞書"],"summary":"Delete User Dict Word","description":"ユーザ辞書に登録されている言葉を削除します。\n\nParameters\n----------\nword_uuid: str\n    削除する言葉のUUID","operationId":"delete_user_dict_word_user_dict_word__word_uuid__delete","parameters":[{"required":true,"schema":{"title":"Word Uuid","type":"string"},"name":"word_uuid","in":"path"}],"responses":{"204":{"description":"Successful Response"},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}},"/supported_devices":{"get":{"tags":["その他"],"summary":"Supported Devices","operationId":"supported_devices_supported_devices_get","parameters":[{"required":false,"schema":{"title":"Core Version","type":"string"},"name":"core_version","in":"query"}],"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/SupportedDevicesInfo"}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}}}}},"components":{"schemas":{"AccentPhrase":{"title":"AccentPhrase","required":["moras","accent"],"type":"object","properties":{"moras":{"title":"モーラのリスト","type":"array","items":{"$ref":"#/components/schemas/Mora"}},"accent":{"title":"アクセント箇所","type":"integer"},"pause_mora":{"title":"後ろに無音を付けるかどうか","allOf":[{"$ref":"#/components/schemas/Mora"}]},"is_interrogative":{"title":"疑問系かどうか","type":"boolean","default":false}},"description":"アクセント句ごとの情報"},"AudioQuery":{"title":"AudioQuery","required":["accent_phrases","speedScale","pitchScale","intonationScale","volumeScale","prePhonemeLength","postPhonemeLength","outputSamplingRate","outputStereo"],"type":"object","properties":{"accent_phrases":{"title":"アクセント句のリスト","type":"array","items":{"$ref":"#/components/schemas/AccentPhrase"}},"speedScale":{"title":"全体の話速","type":"number"},"pitchScale":{"title":"全体の音高","type":"number"},"intonationScale":{"title":"全体の抑揚","type":"number"},"volumeScale":{"title":"全体の音量","type":"number"},"prePhonemeLength":{"title":"音声の前の無音時間","type":"number"},"postPhonemeLength":{"title":"音声の後の無音時間","type":"number"},"outputSamplingRate":{"title":"音声データの出力サンプリングレート","type":"integer"},"outputStereo":{"title":"音声データをステレオ出力するか否か","type":"boolean"},"kana":{"title":"[読み取り専用]AquesTalkライクな読み仮名。音声合成クエリとしては無視される","type":"string"}},"description":"音声合成用のクエリ"},"HTTPValidationError":{"title":"HTTPValidationError","type":"object","properties":{"detail":{"title":"Detail","type":"array","items":{"$ref":"#/components/schemas/ValidationError"}}}},"Mora":{"title":"Mora","required":["text","vowel","vowel_length","pitch"],"type":"object","properties":{"text":{"title":"文字","type":"string"},"consonant":{"title":"子音の音素","type":"string"},"consonant_length":{"title":"子音の音長","type":"number"},"vowel":{"title":"母音の音素","type":"string"},"vowel_length":{"title":"母音の音長","type":"number"},"pitch":{"title":"音高","type":"number"}},"description":"モーラ（子音＋母音）ごとの情報"},"ParseKanaBadRequest":{"title":"ParseKanaBadRequest","required":["text","error_name","error_args"],"type":"object","properties":{"text":{"title":"エラーメッセージ","type":"string"},"error_name":{"title":"エラー名","type":"string","description":"|name|description|\n|---|---|\n| UNKNOWN_TEXT | 判別できない読み仮名があります: {text} |\n| ACCENT_TOP | 句頭にアクセントは置けません: {text} |\n| ACCENT_TWICE | 1つのアクセント句に二つ以上のアクセントは置けません: {text} |\n| ACCENT_NOTFOUND | アクセントを指定していないアクセント句があります: {text} |\n| EMPTY_PHRASE | {position}番目のアクセント句が空白です |\n| INTERROGATION_MARK_NOT_AT_END | アクセント句末以外に「？」は置けません: {text} |\n| INFINITE_LOOP | 処理時に無限ループになってしまいました...バグ報告をお願いします。 |"},"error_args":{"title":"エラーを起こした箇所","type":"object","additionalProperties":{"type":"string"}}}},"Preset":{"title":"Preset","required":["id","name","speaker_uuid","style_id","speedScale","pitchScale","intonationScale","volumeScale","prePhonemeLength","postPhonemeLength"],"type":"object","properties":{"id":{"title":"プリセットID","type":"integer"},"name":{"title":"プリセット名","type":"string"},"speaker_uuid":{"title":"スピーカーのUUID","type":"string"},"style_id":{"title":"スタイルID","type":"integer"},"speedScale":{"title":"全体の話速","type":"number"},"pitchScale":{"title":"全体の音高","type":"number"},"intonationScale":{"title":"全体の抑揚","type":"number"},"volumeScale":{"title":"全体の音量","type":"number"},"prePhonemeLength":{"title":"音声の前の無音時間","type":"number"},"postPhonemeLength":{"title":"音声の後の無音時間","type":"number"}},"description":"プリセット情報"},"Speaker":{"title":"Speaker","required":["name","speaker_uuid","styles"],"type":"object","properties":{"name":{"title":"名前","type":"string"},"speaker_uuid":{"title":"スピーカーのUUID","type":"string"},"styles":{"title":"スピーカースタイルの一覧","type":"array","items":{"$ref":"#/components/schemas/SpeakerStyle"}},"version":{"title":"Version","type":"string","default":"スピーカーのバージョン"}},"description":"スピーカー情報"},"SpeakerInfo":{"title":"SpeakerInfo","required":["policy","portrait","style_infos"],"type":"object","properties":{"policy":{"title":"policy.md","type":"string"},"portrait":{"title":"portrait.pngをbase64エンコードしたもの","type":"string"},"style_infos":{"title":"スタイルの追加情報","type":"array","items":{"$ref":"#/components/schemas/StyleInfo"}}},"description":"話者の追加情報"},"SpeakerStyle":{"title":"SpeakerStyle","required":["name","id"],"type":"object","properties":{"name":{"title":"スタイル名","type":"string"},"id":{"title":"スタイルID","type":"integer"}},"description":"スピーカーのスタイル情報"},"StyleInfo":{"title":"StyleInfo","required":["id","icon","voice_samples"],"type":"object","properties":{"id":{"title":"スタイルID","type":"integer"},"icon":{"title":"当該スタイルのアイコンをbase64エンコードしたもの","type":"string"},"voice_samples":{"title":"voice_sampleのwavファイルをbase64エンコードしたもの","type":"array","items":{"type":"string"}}},"description":"スタイルの追加情報"},"SupportedDevicesInfo":{"title":"SupportedDevicesInfo","required":["cpu","cuda"],"type":"object","properties":{"cpu":{"title":"CPUに対応しているか","type":"boolean"},"cuda":{"title":"CUDA(GPU)に対応しているか","type":"boolean"}},"description":"対応しているデバイスの情報"},"UserDictWord":{"title":"UserDictWord","required":["surface","cost","part_of_speech","part_of_speech_detail_1","part_of_speech_detail_2","part_of_speech_detail_3","inflectional_type","inflectional_form","stem","yomi","pronunciation","accent_type","accent_associative_rule"],"type":"object","properties":{"surface":{"title":"表層形","type":"string"},"cost":{"title":"コストの値","type":"integer"},"part_of_speech":{"title":"品詞","type":"string"},"part_of_speech_detail_1":{"title":"品詞細分類1","type":"string"},"part_of_speech_detail_2":{"title":"品詞細分類2","type":"string"},"part_of_speech_detail_3":{"title":"品詞細分類3","type":"string"},"inflectional_type":{"title":"活用型","type":"string"},"inflectional_form":{"title":"活用形","type":"string"},"stem":{"title":"原形","type":"string"},"yomi":{"title":"読み","type":"string"},"pronunciation":{"title":"発音","type":"string"},"accent_type":{"title":"アクセント型","type":"integer"},"mora_count":{"title":"モーラ数","type":"integer"},"accent_associative_rule":{"title":"アクセント結合規則","type":"string"}},"description":"辞書のコンパイルに使われる情報"},"ValidationError":{"title":"ValidationError","required":["loc","msg","type"],"type":"object","properties":{"loc":{"title":"Location","type":"array","items":{"type":"string"}},"msg":{"title":"Message","type":"string"},"type":{"title":"Error Type","type":"string"}}}}}}