- getAnswer() - Method in class com.tencentcloudapi.aai.v20180522.models.ChatResponse
-
Get 聊天输出文本
- getAsrText() - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingResponse
-
Get 语音识别的结果
- getAudio() - Method in class com.tencentcloudapi.aai.v20180522.models.TextToVoiceResponse
-
Get base64编码的wav/mp3音频数据
- getCodec() - Method in class com.tencentcloudapi.aai.v20180522.models.TextToVoiceRequest
-
Get 返回音频格式，可取值：wav（默认），mp3
- getData() - Method in class com.tencentcloudapi.aai.v20180522.models.SentenceRecognitionRequest
-
Get 语音数据，当SourceType 值为1时必须填写，为0可不写。要base64编码(采用python语言时注意读取文件应该为string而不是byte，以byte格式读取后要decode()。编码后的数据不可带有回车换行符)。音频数据要小于600kB。
- getData() - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingRequest
-
Get 语音数据，要base64编码。
- getDataLen() - Method in class com.tencentcloudapi.aai.v20180522.models.SentenceRecognitionRequest
-
Get 数据长度，当 SourceType 值为1时必须填写，为0可不写（此数据长度为数据未进行base64编码时的数据长度）。
- getDataLen() - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingRequest
-
Get 数据长度。
- getEngSerViceType() - Method in class com.tencentcloudapi.aai.v20180522.models.SentenceRecognitionRequest
-
Get 引擎类型。8k：电话 8k 通用模型；16k：16k 通用模型。只支持单声道音频识别。
- getIsEnd() - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingRequest
-
Get 是否是一句话的结束。
- getModelType() - Method in class com.tencentcloudapi.aai.v20180522.models.TextToVoiceRequest
-
Get 模型类型，1-默认模型。
- getNmtText() - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingResponse
-
Get 机器翻译的结果
- getOpenTranslate() - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingRequest
-
Get 是否需要翻译结果，1表示需要翻译，0是不需要。
- getPrimaryLanguage() - Method in class com.tencentcloudapi.aai.v20180522.models.TextToVoiceRequest
-
Get 主语言类型：1-中文（默认）2-英文
- getProjectId() - Method in class com.tencentcloudapi.aai.v20180522.models.ChatRequest
-
Get 腾讯云项目 ID，可填 0，总长度不超过 1024 字节。
- getProjectId() - Method in class com.tencentcloudapi.aai.v20180522.models.SentenceRecognitionRequest
-
Get 腾讯云项目 ID，可填 0，总长度不超过 1024 字节。
- getProjectId() - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingRequest
-
Get 腾讯云项目 ID，可填 0，总长度不超过 1024 字节。
- getProjectId() - Method in class com.tencentcloudapi.aai.v20180522.models.TextToVoiceRequest
-
Get 项目id，用户自定义，默认为0。
- getRecEngineModelType() - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingRequest
-
Get 识别引擎类型。8k_zh： 8k 中文会场模型；16k_zh：16k 中文会场模型，8k_en： 8k 英文会场模型；16k_en：16k 英文会场模型。当前仅支持16K。
- getRequestId() - Method in class com.tencentcloudapi.aai.v20180522.models.ChatResponse
-
Get 唯一请求 ID，每次请求都会返回。定位问题时需要提供该次请求的 RequestId。
- getRequestId() - Method in class com.tencentcloudapi.aai.v20180522.models.SentenceRecognitionResponse
-
Get 唯一请求 ID，每次请求都会返回。定位问题时需要提供该次请求的 RequestId。
- getRequestId() - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingResponse
-
Get 唯一请求 ID，每次请求都会返回。定位问题时需要提供该次请求的 RequestId。
- getRequestId() - Method in class com.tencentcloudapi.aai.v20180522.models.TextToVoiceResponse
-
Get 唯一请求 ID，每次请求都会返回。定位问题时需要提供该次请求的 RequestId。
- getResult() - Method in class com.tencentcloudapi.aai.v20180522.models.SentenceRecognitionResponse
-
Get 识别结果。
- getSampleRate() - Method in class com.tencentcloudapi.aai.v20180522.models.TextToVoiceRequest
-
Get 音频采样率：16000：16k（默认）8000：8k
- getSeq() - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingRequest
-
Get 表明当前语音分片的索引，从0开始
- getSessionId() - Method in class com.tencentcloudapi.aai.v20180522.models.TextToVoiceRequest
-
Get 一次请求对应一个SessionId，会原样返回，建议传入类似于uuid的字符串防止重复。
- getSessionId() - Method in class com.tencentcloudapi.aai.v20180522.models.TextToVoiceResponse
-
Get 一次请求对应一个SessionId
- getSourceLanguage() - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingRequest
-
Get 如果需要翻译，表示源语言类型，可取值：zh，en。
- getSourceType() - Method in class com.tencentcloudapi.aai.v20180522.models.SentenceRecognitionRequest
-
Get 语音数据来源。0：语音 URL；1：语音数据（post body）。
- getSpeed() - Method in class com.tencentcloudapi.aai.v20180522.models.TextToVoiceRequest
-
Get 语速，范围：[-2，2]，分别对应不同语速：-2代表0.6倍-1代表0.8倍0代表1.0倍（默认）1代表1.2倍2代表1.5倍输入除以上整数之外的其他参数不生效，按默认值处理。
- getSubServiceType() - Method in class com.tencentcloudapi.aai.v20180522.models.SentenceRecognitionRequest
-
Get 子服务类型。2，一句话识别。
- getSubServiceType() - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingRequest
-
Get 子服务类型。0：离线语音识别。1：实时流式识别，2，一句话识别。3：同传。
- getTargetLanguage() - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingRequest
-
Get 如果需要翻译，表示目标语言类型，可取值：zh，en。
- getText() - Method in class com.tencentcloudapi.aai.v20180522.models.ChatRequest
-
Get 聊天输入文本
- getText() - Method in class com.tencentcloudapi.aai.v20180522.models.TextToVoiceRequest
-
Get 合成语音的源文本，按UTF-8编码统一计算。
中文最大支持100个汉字（全角标点符号算一个汉字）；英文最大支持400个字母（半角标点符号算一个字母）。包含空格等字符时需要url encode再传输。
- getUrl() - Method in class com.tencentcloudapi.aai.v20180522.models.SentenceRecognitionRequest
-
Get 语音 URL，公网可下载。当 SourceType 值为 0 时须填写该字段，为 1 时不填；URL 的长度大于 0，小于 2048，需进行urlencode编码。音频时间长度要小于60s。
- getUser() - Method in class com.tencentcloudapi.aai.v20180522.models.ChatRequest
-
Get json格式，比如 {"id":"test","gender":"male"}。记录当前与机器人交互的用户id，非必须但强烈建议传入，否则多轮聊天功能会受影响
- getUsrAudioKey() - Method in class com.tencentcloudapi.aai.v20180522.models.SentenceRecognitionRequest
-
Get 用户端对此任务的唯一标识，用户自助生成，用于用户查找识别结果。
- getVoiceFormat() - Method in class com.tencentcloudapi.aai.v20180522.models.SentenceRecognitionRequest
-
Get 识别音频的音频格式（支持mp3,wav）。
- getVoiceFormat() - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingRequest
-
Get 声音编码的格式1:pcm，4:speex，6:silk，默认为1。
- getVoiceId() - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingRequest
-
Get 声音id，标识一句话。
- getVoiceType() - Method in class com.tencentcloudapi.aai.v20180522.models.TextToVoiceRequest
-
Get 音色0-亲和女声(默认)1-亲和男声2-成熟男声3-活力男声4-温暖女声5-情感女声6-情感男声
- getVolume() - Method in class com.tencentcloudapi.aai.v20180522.models.TextToVoiceRequest
-
Get 音量大小，范围：[0，10]，分别对应11个等级的音量，默认为0，代表正常音量。没有静音选项。
输入除以上整数之外的其他参数不生效，按默认值处理。
- SentenceRecognition(SentenceRecognitionRequest) - Method in class com.tencentcloudapi.aai.v20180522.AaiClient
-
识别60s内的短语音，当音频放在请求body中传输时整个请求大小不能超过600KB，当音频以url方式传输时，音频时长不可超过60s。所有请求参数放在post的body中采用x-www-form-urlencoded（数据转换成一个字符串（name1=value1&name2=value2…）进行urlencode后）编码传输。现暂只支持中文普通话识别，支持识别8k(16k)的16bit的mp3或者wav音频。
- SentenceRecognitionRequest - Class in com.tencentcloudapi.aai.v20180522.models
-
- SentenceRecognitionRequest() - Constructor for class com.tencentcloudapi.aai.v20180522.models.SentenceRecognitionRequest
-
- SentenceRecognitionRequest(SentenceRecognitionRequest) - Constructor for class com.tencentcloudapi.aai.v20180522.models.SentenceRecognitionRequest
-
NOTE: Any ambiguous key set via .set("AnyKey", "value") will be a shallow copy,
and any explicit key, i.e Foo, set via .setFoo("value") will be a deep copy.
- SentenceRecognitionResponse - Class in com.tencentcloudapi.aai.v20180522.models
-
- SentenceRecognitionResponse() - Constructor for class com.tencentcloudapi.aai.v20180522.models.SentenceRecognitionResponse
-
- SentenceRecognitionResponse(SentenceRecognitionResponse) - Constructor for class com.tencentcloudapi.aai.v20180522.models.SentenceRecognitionResponse
-
NOTE: Any ambiguous key set via .set("AnyKey", "value") will be a shallow copy,
and any explicit key, i.e Foo, set via .setFoo("value") will be a deep copy.
- setAnswer(String) - Method in class com.tencentcloudapi.aai.v20180522.models.ChatResponse
-
Set 聊天输出文本
- setAsrText(String) - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingResponse
-
Set 语音识别的结果
- setAudio(String) - Method in class com.tencentcloudapi.aai.v20180522.models.TextToVoiceResponse
-
Set base64编码的wav/mp3音频数据
- setCodec(String) - Method in class com.tencentcloudapi.aai.v20180522.models.TextToVoiceRequest
-
Set 返回音频格式，可取值：wav（默认），mp3
- setData(String) - Method in class com.tencentcloudapi.aai.v20180522.models.SentenceRecognitionRequest
-
Set 语音数据，当SourceType 值为1时必须填写，为0可不写。要base64编码(采用python语言时注意读取文件应该为string而不是byte，以byte格式读取后要decode()。编码后的数据不可带有回车换行符)。音频数据要小于600kB。
- setData(String) - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingRequest
-
Set 语音数据，要base64编码。
- setDataLen(Long) - Method in class com.tencentcloudapi.aai.v20180522.models.SentenceRecognitionRequest
-
Set 数据长度，当 SourceType 值为1时必须填写，为0可不写（此数据长度为数据未进行base64编码时的数据长度）。
- setDataLen(Long) - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingRequest
-
Set 数据长度。
- setEngSerViceType(String) - Method in class com.tencentcloudapi.aai.v20180522.models.SentenceRecognitionRequest
-
Set 引擎类型。8k：电话 8k 通用模型；16k：16k 通用模型。只支持单声道音频识别。
- setIsEnd(Long) - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingRequest
-
Set 是否是一句话的结束。
- setModelType(Long) - Method in class com.tencentcloudapi.aai.v20180522.models.TextToVoiceRequest
-
Set 模型类型，1-默认模型。
- setNmtText(String) - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingResponse
-
Set 机器翻译的结果
- setOpenTranslate(Long) - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingRequest
-
Set 是否需要翻译结果，1表示需要翻译，0是不需要。
- setPrimaryLanguage(Long) - Method in class com.tencentcloudapi.aai.v20180522.models.TextToVoiceRequest
-
Set 主语言类型：1-中文（默认）2-英文
- setProjectId(Long) - Method in class com.tencentcloudapi.aai.v20180522.models.ChatRequest
-
Set 腾讯云项目 ID，可填 0，总长度不超过 1024 字节。
- setProjectId(Long) - Method in class com.tencentcloudapi.aai.v20180522.models.SentenceRecognitionRequest
-
Set 腾讯云项目 ID，可填 0，总长度不超过 1024 字节。
- setProjectId(Long) - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingRequest
-
Set 腾讯云项目 ID，可填 0，总长度不超过 1024 字节。
- setProjectId(Long) - Method in class com.tencentcloudapi.aai.v20180522.models.TextToVoiceRequest
-
Set 项目id，用户自定义，默认为0。
- setRecEngineModelType(String) - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingRequest
-
Set 识别引擎类型。8k_zh： 8k 中文会场模型；16k_zh：16k 中文会场模型，8k_en： 8k 英文会场模型；16k_en：16k 英文会场模型。当前仅支持16K。
- setRequestId(String) - Method in class com.tencentcloudapi.aai.v20180522.models.ChatResponse
-
Set 唯一请求 ID，每次请求都会返回。定位问题时需要提供该次请求的 RequestId。
- setRequestId(String) - Method in class com.tencentcloudapi.aai.v20180522.models.SentenceRecognitionResponse
-
Set 唯一请求 ID，每次请求都会返回。定位问题时需要提供该次请求的 RequestId。
- setRequestId(String) - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingResponse
-
Set 唯一请求 ID，每次请求都会返回。定位问题时需要提供该次请求的 RequestId。
- setRequestId(String) - Method in class com.tencentcloudapi.aai.v20180522.models.TextToVoiceResponse
-
Set 唯一请求 ID，每次请求都会返回。定位问题时需要提供该次请求的 RequestId。
- setResult(String) - Method in class com.tencentcloudapi.aai.v20180522.models.SentenceRecognitionResponse
-
Set 识别结果。
- setSampleRate(Long) - Method in class com.tencentcloudapi.aai.v20180522.models.TextToVoiceRequest
-
Set 音频采样率：16000：16k（默认）8000：8k
- setSeq(Long) - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingRequest
-
Set 表明当前语音分片的索引，从0开始
- setSessionId(String) - Method in class com.tencentcloudapi.aai.v20180522.models.TextToVoiceRequest
-
Set 一次请求对应一个SessionId，会原样返回，建议传入类似于uuid的字符串防止重复。
- setSessionId(String) - Method in class com.tencentcloudapi.aai.v20180522.models.TextToVoiceResponse
-
Set 一次请求对应一个SessionId
- setSourceLanguage(String) - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingRequest
-
Set 如果需要翻译，表示源语言类型，可取值：zh，en。
- setSourceType(Long) - Method in class com.tencentcloudapi.aai.v20180522.models.SentenceRecognitionRequest
-
Set 语音数据来源。0：语音 URL；1：语音数据（post body）。
- setSpeed(Float) - Method in class com.tencentcloudapi.aai.v20180522.models.TextToVoiceRequest
-
Set 语速，范围：[-2，2]，分别对应不同语速：-2代表0.6倍-1代表0.8倍0代表1.0倍（默认）1代表1.2倍2代表1.5倍输入除以上整数之外的其他参数不生效，按默认值处理。
- setSubServiceType(Long) - Method in class com.tencentcloudapi.aai.v20180522.models.SentenceRecognitionRequest
-
Set 子服务类型。2，一句话识别。
- setSubServiceType(Long) - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingRequest
-
Set 子服务类型。0：离线语音识别。1：实时流式识别，2，一句话识别。3：同传。
- setTargetLanguage(String) - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingRequest
-
Set 如果需要翻译，表示目标语言类型，可取值：zh，en。
- setText(String) - Method in class com.tencentcloudapi.aai.v20180522.models.ChatRequest
-
Set 聊天输入文本
- setText(String) - Method in class com.tencentcloudapi.aai.v20180522.models.TextToVoiceRequest
-
Set 合成语音的源文本，按UTF-8编码统一计算。
中文最大支持100个汉字（全角标点符号算一个汉字）；英文最大支持400个字母（半角标点符号算一个字母）。包含空格等字符时需要url encode再传输。
- setUrl(String) - Method in class com.tencentcloudapi.aai.v20180522.models.SentenceRecognitionRequest
-
Set 语音 URL，公网可下载。当 SourceType 值为 0 时须填写该字段，为 1 时不填；URL 的长度大于 0，小于 2048，需进行urlencode编码。音频时间长度要小于60s。
- setUser(String) - Method in class com.tencentcloudapi.aai.v20180522.models.ChatRequest
-
Set json格式，比如 {"id":"test","gender":"male"}。记录当前与机器人交互的用户id，非必须但强烈建议传入，否则多轮聊天功能会受影响
- setUsrAudioKey(String) - Method in class com.tencentcloudapi.aai.v20180522.models.SentenceRecognitionRequest
-
Set 用户端对此任务的唯一标识，用户自助生成，用于用户查找识别结果。
- setVoiceFormat(String) - Method in class com.tencentcloudapi.aai.v20180522.models.SentenceRecognitionRequest
-
Set 识别音频的音频格式（支持mp3,wav）。
- setVoiceFormat(Long) - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingRequest
-
Set 声音编码的格式1:pcm，4:speex，6:silk，默认为1。
- setVoiceId(String) - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingRequest
-
Set 声音id，标识一句话。
- setVoiceType(Long) - Method in class com.tencentcloudapi.aai.v20180522.models.TextToVoiceRequest
-
Set 音色0-亲和女声(默认)1-亲和男声2-成熟男声3-活力男声4-温暖女声5-情感女声6-情感男声
- setVolume(Float) - Method in class com.tencentcloudapi.aai.v20180522.models.TextToVoiceRequest
-
Set 音量大小，范围：[0，10]，分别对应11个等级的音量，默认为0，代表正常音量。没有静音选项。
输入除以上整数之外的其他参数不生效，按默认值处理。
- SimultaneousInterpreting(SimultaneousInterpretingRequest) - Method in class com.tencentcloudapi.aai.v20180522.AaiClient
-
该接口是实时流式识别，可同时返回语音识别文本及翻译文本，当前仅支持中文和英文。该接口可配合同传windows客户端，提供会议现场同传服务。
- SimultaneousInterpretingRequest - Class in com.tencentcloudapi.aai.v20180522.models
-
- SimultaneousInterpretingRequest() - Constructor for class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingRequest
-
- SimultaneousInterpretingRequest(SimultaneousInterpretingRequest) - Constructor for class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingRequest
-
NOTE: Any ambiguous key set via .set("AnyKey", "value") will be a shallow copy,
and any explicit key, i.e Foo, set via .setFoo("value") will be a deep copy.
- SimultaneousInterpretingResponse - Class in com.tencentcloudapi.aai.v20180522.models
-
- SimultaneousInterpretingResponse() - Constructor for class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingResponse
-
- SimultaneousInterpretingResponse(SimultaneousInterpretingResponse) - Constructor for class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingResponse
-
NOTE: Any ambiguous key set via .set("AnyKey", "value") will be a shallow copy,
and any explicit key, i.e Foo, set via .setFoo("value") will be a deep copy.
- TextToVoice(TextToVoiceRequest) - Method in class com.tencentcloudapi.aai.v20180522.AaiClient
-
腾讯云语音合成技术（TTS）可以将任意文本转化为语音，实现让机器和应用张口说话。
腾讯TTS技术可以应用到很多场景，比如，移动APP语音播报新闻；智能设备语音提醒；依靠网上现有节目或少量录音，快速合成明星语音，降低邀约成本；支持车载导航语音合成的个性化语音播报。
内测期间免费使用。
- TextToVoiceRequest - Class in com.tencentcloudapi.aai.v20180522.models
-
- TextToVoiceRequest() - Constructor for class com.tencentcloudapi.aai.v20180522.models.TextToVoiceRequest
-
- TextToVoiceRequest(TextToVoiceRequest) - Constructor for class com.tencentcloudapi.aai.v20180522.models.TextToVoiceRequest
-
NOTE: Any ambiguous key set via .set("AnyKey", "value") will be a shallow copy,
and any explicit key, i.e Foo, set via .setFoo("value") will be a deep copy.
- TextToVoiceResponse - Class in com.tencentcloudapi.aai.v20180522.models
-
- TextToVoiceResponse() - Constructor for class com.tencentcloudapi.aai.v20180522.models.TextToVoiceResponse
-
- TextToVoiceResponse(TextToVoiceResponse) - Constructor for class com.tencentcloudapi.aai.v20180522.models.TextToVoiceResponse
-
NOTE: Any ambiguous key set via .set("AnyKey", "value") will be a shallow copy,
and any explicit key, i.e Foo, set via .setFoo("value") will be a deep copy.
- toMap(HashMap<String, String>, String) - Method in class com.tencentcloudapi.aai.v20180522.models.ChatRequest
-
Internal implementation, normal users should not use it.
- toMap(HashMap<String, String>, String) - Method in class com.tencentcloudapi.aai.v20180522.models.ChatResponse
-
Internal implementation, normal users should not use it.
- toMap(HashMap<String, String>, String) - Method in class com.tencentcloudapi.aai.v20180522.models.SentenceRecognitionRequest
-
Internal implementation, normal users should not use it.
- toMap(HashMap<String, String>, String) - Method in class com.tencentcloudapi.aai.v20180522.models.SentenceRecognitionResponse
-
Internal implementation, normal users should not use it.
- toMap(HashMap<String, String>, String) - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingRequest
-
Internal implementation, normal users should not use it.
- toMap(HashMap<String, String>, String) - Method in class com.tencentcloudapi.aai.v20180522.models.SimultaneousInterpretingResponse
-
Internal implementation, normal users should not use it.
- toMap(HashMap<String, String>, String) - Method in class com.tencentcloudapi.aai.v20180522.models.TextToVoiceRequest
-
Internal implementation, normal users should not use it.
- toMap(HashMap<String, String>, String) - Method in class com.tencentcloudapi.aai.v20180522.models.TextToVoiceResponse
-
Internal implementation, normal users should not use it.