{
    "summary": "同步语音合成",
    "responses": {
        "200": {
            "content": {
                "application/json": {
                    "schema": {
                        "type": "object",
                        "properties": {
                            "data": {
                                "type": "object",
                                "properties": {
                                    "audio": {
                                        "type": "string",
                                        "description": "合成后的音频数据，采用 hex 编码，格式与请求中指定的输出格式一致"
                                    },
                                    "status": {
                                        "type": "integer",
                                        "description": "当前音频流状态：1 表示合成中，2 表示合成结束"
                                    },
                                    "subtitle_file": {
                                        "type": "string",
                                        "description": "合成的字幕下载链接。音频文件对应的字幕，精确到句（不超过 50 字），单位为毫秒，格式为 json"
                                    }
                                },
                                "description": "返回的合成数据对象，可能为 null，需进行非空判断"
                            },
                            "trace_id": {
                                "type": "string"
                            },
                            "base_resp": {
                                "type": "object",
                                "required": [
                                    "status_code",
                                    "status_msg"
                                ],
                                "properties": {
                                    "status_msg": {
                                        "type": "string",
                                        "description": "状态详情"
                                    },
                                    "status_code": {
                                        "type": "integer",
                                        "description": "状态码。\n\n0: 请求结果正常\n1000: 未知错误\n1001: 超时\n1002: 触发限流\n1004: 鉴权失败\n1039: 触发 TPM 限流\n1042: 非法字符超过 10%\n2013: 输入参数信息不正常"
                                    }
                                }
                            },
                            "extra_info": {
                                "type": "object",
                                "properties": {
                                    "bitrate": {
                                        "type": "integer",
                                        "description": "音频比特率"
                                    },
                                    "audio_size": {
                                        "type": "integer",
                                        "description": "音频文件大小（字节）"
                                    },
                                    "word_count": {
                                        "type": "integer",
                                        "description": "已发音的字数统计，包含汉字、数字、字母，不包含标点符号"
                                    },
                                    "audio_format": {
                                        "type": "string",
                                        "description": "生成音频文件的格式。取值范围 [mp3, pcm, flac]"
                                    },
                                    "audio_length": {
                                        "type": "integer",
                                        "description": "音频时长（毫秒）"
                                    },
                                    "audio_channel": {
                                        "type": "integer",
                                        "description": "生成音频声道数,1：单声道，2：双声道"
                                    },
                                    "usage_characters": {
                                        "type": "integer",
                                        "description": "计费字符数"
                                    },
                                    "audio_sample_rate": {
                                        "type": "integer",
                                        "description": "音频采样率"
                                    },
                                    "invisible_character_ratio": {
                                        "type": "integer",
                                        "description": "非法字符占比.非法字符不超过 10%（包含 10%），音频会正常生成,并返回非法字符占比数据；如超过 10% 将进行报错"
                                    }
                                }
                            }
                        }
                    }
                }
            },
            "description": "成功"
        }
    },
    "parameters": [],
    "description": "### 同步语音合成\n[官方文档](\n\n通过提交 post请求{{BASE_URL}}/minimaxi/v1/voice_design\n并同步得到结果",
    "requestBody": {
        "content": {
            "application/json": {
                "schema": {
                    "type": "object",
                    "title": "同步语音合成",
                    "$schema": "",
                    "required": [
                        "model",
                        "text",
                        "voice_setting"
                    ],
                    "properties": {
                        "text": {
                            "type": "string",
                            "description": "需要合成语音的文本"
                        },
                        "model": {
                            "type": "string",
                            "description": "请求的模型版本，可选范围：speech-2.6-hd, speech-2.6-turbo, speech-02-hd, speech-02-turbo, speech-01-hd, speech-01-turbo."
                        },
                        "stream": {
                            "type": "boolean",
                            "description": "控制是否流式输出。默认 false，即不开启流式"
                        },
                        "voice_modify": {
                            "type": "object",
                            "properties": {
                                "pitch": {
                                    "type": "integer",
                                    "description": "音高调整（低沉/明亮），范围 [-100,100]，数值接近 -100，声音更低沉；接近 100，声音更明亮"
                                },
                                "timbre": {
                                    "type": "integer",
                                    "description": "音色调整（磁性/清脆），范围 [-100,100]，数值接近 -100，声音更浑厚；数值接近 100，声音更清脆"
                                },
                                "intensity": {
                                    "type": "integer",
                                    "description": "强度调整（力量感/柔和），范围 [-100,100]，数值接近 -100，声音更刚劲；接近 100，声音更轻柔"
                                },
                                "sound_effects": {
                                    "type": "string",
                                    "description": "音效设置，单次仅能选择一种，可选值：\n\nspacious_echo（空旷回音）\nauditorium_echo（礼堂广播）\nlofi_telephone（电话失真）\nrobotic（电音）\n可用选项: spacious_echo, auditorium_echo, lofi_telephone, robotic"
                                }
                            },
                            "description": "声音效果器设置，该参数支持的音频格式：\n\n非流式：mp3, wav, flac\n流式：mp3"
                        },
                        "audio_setting": {
                            "type": "object",
                            "properties": {
                                "format": {
                                    "type": "string",
                                    "description": "生成音频的格式，wav 仅在非流式输出下支持\n\n可用选项: mp3, pcm, flac, wav"
                                },
                                "bitrate": {
                                    "type": "integer",
                                    "description": "生成音频的比特率。可选范围[32000，64000，128000，256000]，默认值为 128000。该参数仅对 mp3 格式的音频生效"
                                },
                                "channel": {
                                    "type": "integer",
                                    "description": "生成音频的声道数。可选范围：[1,2]，其中 1 为单声道，2 为双声道，默认值为 1"
                                },
                                "force_cbr": {
                                    "type": "boolean",
                                    "description": "对于音频恒定比特率（cbr）控制，可选 false、 true。当此参数设置为 true，将以恒定比特率方式进行音频编码。\n注意：本参数仅当音频设置为流式输出，且音频格式为 mp3 时生效。"
                                },
                                "sample_rate": {
                                    "type": "integer",
                                    "description": "生成音频的采样率。可选范围[8000，16000，22050，24000，32000，44100]，默认为 32000"
                                }
                            }
                        },
                        "output_format": {
                            "type": "string",
                            "description": "控制输出结果形式的参数，可选值范围为[url, hex]，默认值为 hex 。该参数仅在非流式场景生效，流式场景仅支持返回 hex 形式。返回的 url 有效期为 24 小时\n\n可用选项: url, hex"
                        },
                        "voice_setting": {
                            "type": "object",
                            "required": [
                                "voice_id"
                            ],
                            "properties": {
                                "vol": {
                                    "type": "number",
                                    "description": "合成音频的音量，取值越大，音量越高。取值范围 (0,10]，默认值为 1.0"
                                },
                                "pitch": {
                                    "type": "integer",
                                    "description": "合成音频的语调，取值范围 [-12,12]，默认值为 0，其中 0 为原音色输出"
                                },
                                "speed": {
                                    "type": "number",
                                    "description": "合成音频的语速，取值越大，语速越快。取值范围 [0.5,2]，默认值为1.0"
                                },
                                "emotion": {
                                    "type": "string",
                                    "description": "控制合成语音的情绪，参数范围 [\"happy\", \"sad\", \"angry\", \"fearful\", \"disgusted\", \"surprised\", \"calm\", \"fluent\"]，分别对应 8 种情绪：高兴，悲伤，愤怒，害怕，厌恶，惊讶，中性，生动\n\n模型会根据输入文本自动匹配合适的情绪，一般无需手动指定\n该参数仅对 speech-2.6-hd, speech-2.6-turbo, speech-02-hd, speech-02-turbo, speech-01-hd, speech-01-turbo 模型生效\n选项 fluent 仅对 speech-2.6-turbo, speech-2.6-hd 模型生效\n可用选项: happy, sad, angry, fearful, disgusted, surprised, calm, fluent"
                                },
                                "voice_id": {
                                    "type": "string"
                                },
                                "latex_read": {
                                    "type": "boolean",
                                    "description": "控制是否朗读 latex 公式，默认为 false"
                                },
                                "text_normalization": {
                                    "type": "boolean",
                                    "description": "是否启用中文、英语文本规范化，开启后可提升数字阅读场景的性能，但会略微增加延迟，默认值为 false"
                                }
                            }
                        },
                        "aigc_watermark": {
                            "type": "boolean",
                            "description": "控制在合成音频的末尾添加音频节奏标识，默认值为 False。该参数仅对非流式合成生效"
                        },
                        "language_boost": {
                            "type": "string",
                            "description": "是否增强对指定的小语种和方言的识别能力。默认值为 null，可设置为 auto 让模型自主判断。\n\n可用选项: 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, Persian, Slovak, Swedish, Croatian, Filipino, Hungarian, Norwegian, Slovenian, Catalan, Nynorsk, Tamil, Afrikaans, auto"
                        },
                        "stream_options": {
                            "type": "object",
                            "required": [
                                "exclude_aggregated_audio"
                            ],
                            "properties": {
                                "exclude_aggregated_audio": {
                                    "type": "string",
                                    "description": "设置最后一个 chunk 是否包含拼接后的语音 hex 数据。默认值为 False，即最后一个 chunk 中包含拼接后的完整语音 hex 数据"
                                }
                            }
                        },
                        "timber_weights": {
                            "type": "object",
                            "required": [
                                "voice_id",
                                "weight"
                            ],
                            "properties": {
                                "weight": {
                                    "type": "integer",
                                    "description": "合成音频各音色所占的权重，须与 voice_id 同步填写。可选值范围为[1, 100]，最多支持 4 种音色混合，单一音色取值占比越高，合成音色与该音色相似度越高."
                                },
                                " voice_id": {
                                    "type": "string"
                                }
                            }
                        },
                        "subtitle_enable": {
                            "type": "boolean"
                        },
                        " subtitle_enable": {
                            "type": "boolean",
                            "description": "控制是否开启字幕服务，默认值为 false。此参数仅在非流式输出场景下有效，且仅对 speech-2.6-hd speech-2.6-turbo speech-02-turbo speech-02-hd speech-01-turbo speech-01-hd 模型有效"
                        },
                        "pronunciation_dict": {
                            "type": "object",
                            "properties": {
                                "tone": {
                                    "type": "array",
                                    "items": {
                                        "type": "string",
                                        "description": "定义需要特殊标注的文字或符号对应的注音或发音替换规则。在中文文本中，声调用数字表示：\n一声为 1，二声为 2，三声为 3，四声为 4，轻声为 5\n示例如下：\n[\"燕少飞/(yan4)(shao3)(fei1)\", \"omg/oh my god\"]"
                                    }
                                }
                            }
                        }
                    },
                    "x-apifox-id": "379964423"
                }
            }
        },
        "required": true
    }
}