tencentcloud-sdk-trtc 3.0.1115 → 3.0.1123

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 41641e4ea5026508abd16a9009d7c8d8873af3fb
-  data.tar.gz: be1261817c9cd80fc54b1ba976e88731a67b5cfc
+  metadata.gz: 4bd190712763744dfa0a90d9cde36e574c0f9703
+  data.tar.gz: 4306bc9b602c2ac3edcc06f4525b6278702dc225
 SHA512:
-  metadata.gz: 8e65ff7abfcbae384d812ca3770ed94c39c9cbb31e526a2195c8d88b6af4b96b75485ef4d8a973067129bff91e7da248493f06fcd200c1ae1043c077fee1ce62
-  data.tar.gz: 5854270f9264ce57921a98bd2fe6fdd8e7ea174c7663820b516ef4f495dea8a7d581cbde13856acd1e4312ffee02b931e66dfe5fa41fc867ed5c6abf9e665dc0
+  metadata.gz: 8d9f0cca3c16aa53e8bdf28e34e527ae80dc58bdda8b34228dffa5a30901673af2188e883a355ec568febb532b18fee3698c4c7f76bdc19587d3673cdadebdb4
+  data.tar.gz: 66b66c117736e412d2d8df1b48069513e467b2cd847c208b447a9ed8f6c1d6e107769de3d2c1140915f797ea10d60d173b629783254dcb3ec4c25461bcb07ab6

data/lib/VERSION

@@ -1 +1 @@
-3.0.1115
+3.0.1123

data/lib/v20190722/client.rb

@@ -1774,6 +1774,54 @@ module TencentCloud
           raise TencentCloud::Common::TencentCloudSDKException.new(nil, e.inspect)
         end
 
+        # 语音合成接口
+
+        # @param request: Request instance for TextToSpeech.
+        # @type request: :class:`Tencentcloud::trtc::V20190722::TextToSpeechRequest`
+        # @rtype: :class:`Tencentcloud::trtc::V20190722::TextToSpeechResponse`
+        def TextToSpeech(request)
+          body = send_request('TextToSpeech', request.serialize)
+          response = JSON.parse(body)
+          if response['Response'].key?('Error') == false
+            model = TextToSpeechResponse.new
+            model.deserialize(response['Response'])
+            model
+          else
+            code = response['Response']['Error']['Code']
+            message = response['Response']['Error']['Message']
+            reqid = response['Response']['RequestId']
+            raise TencentCloud::Common::TencentCloudSDKException.new(code, message, reqid)
+          end
+        rescue TencentCloud::Common::TencentCloudSDKException => e
+          raise e
+        rescue StandardError => e
+          raise TencentCloud::Common::TencentCloudSDKException.new(nil, e.inspect)
+        end
+
+        # SSE流式文本转语音
+
+        # @param request: Request instance for TextToSpeechSSE.
+        # @type request: :class:`Tencentcloud::trtc::V20190722::TextToSpeechSSERequest`
+        # @rtype: :class:`Tencentcloud::trtc::V20190722::TextToSpeechSSEResponse`
+        def TextToSpeechSSE(request)
+          body = send_request('TextToSpeechSSE', request.serialize)
+          response = JSON.parse(body)
+          if response['Response'].key?('Error') == false
+            model = TextToSpeechSSEResponse.new
+            model.deserialize(response['Response'])
+            model
+          else
+            code = response['Response']['Error']['Code']
+            message = response['Response']['Error']['Message']
+            reqid = response['Response']['RequestId']
+            raise TencentCloud::Common::TencentCloudSDKException.new(code, message, reqid)
+          end
+        rescue TencentCloud::Common::TencentCloudSDKException => e
+          raise e
+        rescue StandardError => e
+          raise TencentCloud::Common::TencentCloudSDKException.new(nil, e.inspect)
+        end
+
         # 更新AIConversation参数
 
         # @param request: Request instance for UpdateAIConversation.
@@ -1872,6 +1920,30 @@ module TencentCloud
           raise TencentCloud::Common::TencentCloudSDKException.new(nil, e.inspect)
         end
 
+        # 声音克隆
+
+        # @param request: Request instance for VoiceClone.
+        # @type request: :class:`Tencentcloud::trtc::V20190722::VoiceCloneRequest`
+        # @rtype: :class:`Tencentcloud::trtc::V20190722::VoiceCloneResponse`
+        def VoiceClone(request)
+          body = send_request('VoiceClone', request.serialize)
+          response = JSON.parse(body)
+          if response['Response'].key?('Error') == false
+            model = VoiceCloneResponse.new
+            model.deserialize(response['Response'])
+            model
+          else
+            code = response['Response']['Error']['Code']
+            message = response['Response']['Error']['Message']
+            reqid = response['Response']['RequestId']
+            raise TencentCloud::Common::TencentCloudSDKException.new(code, message, reqid)
+          end
+        rescue TencentCloud::Common::TencentCloudSDKException => e
+          raise e
+        rescue StandardError => e
+          raise TencentCloud::Common::TencentCloudSDKException.new(nil, e.inspect)
+        end
+
 
       end
     end

data/lib/v20190722/models.rb

@@ -271,6 +271,22 @@ module TencentCloud
         end
       end
 
+      # TTS音频输出的格式
+      class AudioFormat < TencentCloud::Common::AbstractModel
+        # @param Format: 生成的音频格式，默认pcm，目前支持的格式列表：[pcm]。
+        # @type Format: String
+
+        attr_accessor :Format
+
+        def initialize(format=nil)
+          @Format = format
+        end
+
+        def deserialize(params)
+          @Format = params['Format']
+        end
+      end
+
       # 录制音频转码参数。
       class AudioParams < TencentCloud::Common::AbstractModel
         # @param SampleRate: 音频采样率枚举值:(注意1 代表48000HZ, 2 代表44100HZ, 3 代表16000HZ)
@@ -1308,6 +1324,7 @@ module TencentCloud
         # aCapEnergy：音频采集能量；
         # aPlayEnergy：音频播放能量；
         # rtt：SDK到云端的往返延时；单位: ms
+        # bigvRecFps: 云端送达帧率；
         # @type DataType: Array
         # @param PageNumber: 当前页数，默认为0，
         # 注意：PageNumber和PageSize 其中一个不填均默认返回6条数据。
@@ -5446,7 +5463,7 @@ module TencentCloud
         # @param STTConfig: 语音识别配置。
         # @type STTConfig: :class:`Tencentcloud::Trtc.v20190722.models.STTConfig`
         # @param LLMConfig: LLM配置。需符合openai规范，为JSON字符串，示例如下：
-        # <pre> { <br> &emsp;  "LLMType": "大模型类型",  // String 必填，如："openai" <br> &emsp;  "Model": "您的模型名称", // String 必填，指定使用的模型<br>    "APIKey": "您的LLM API密钥", // String 必填 <br> &emsp;  "APIUrl": "https://api.xxx.com/chat/completions", // String 必填，LLM API访问的URL<br> &emsp;  "Streaming": true // Boolean 非必填，指定是否使用流式传输<br> &emsp;} </pre>
+        # <pre> { <br> &emsp;  "LLMType": "大模型类型",  // String 必填，如："openai" <br> &emsp;  "Model": "您的模型名称", // String 必填，指定使用的模型<br>    "APIKey": "您的LLM API密钥", // String 必填 <br> &emsp;  "APIUrl": "https://api.xxx.com/chat/completions", // String 必填，LLM API访问的URL<br> &emsp;  "History": 10, // Integer 选填，设置 LLM 的上下文轮次，默认值为0，最大值50<br> &emsp;  "HistoryMode": 1, // Integer 选填，1表示LLM上下文中的内容会和播放音频做同步，没有播放的音频对应的文本不会出现在上下文中。0表示不会做同步，默认值为0<br> &emsp;  "Streaming": true // Boolean 非必填，指定是否使用流式传输<br> &emsp;} </pre>
         # @type LLMConfig: String
         # @param TTSConfig: TTS配置，为JSON字符串，腾讯云TTS示例如下： <pre>{ <br> &emsp; "AppId": 您的应用ID, // Integer 必填<br> &emsp; "TTSType": "TTS类型", // String TTS类型, 固定为"tencent"<br> &emsp; "SecretId": "您的密钥ID", // String 必填<br> &emsp; "SecretKey":  "您的密钥Key", // String 必填<br> &emsp; "VoiceType": 101001, // Integer  必填，音色 ID，包括标准音色与精品音色，精品音色拟真度更高，价格不同于标准音色，请参见<a href="https://cloud.tencent.com/document/product/1073/34112">语音合成计费概述</a>。完整的音色 ID 列表请参见<a href="https://cloud.tencent.com/document/product/1073/92668#55924b56-1a73-4663-a7a1-a8dd82d6e823">语音合成音色列表</a>。<br> &emsp; "Speed": 1.25, // Integer 非必填，语速，范围：[-2，6]，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  6: 代表2.5倍  如果需要更细化的语速，可以保留小数点后 2 位，例如0.5/1.25/2.81等。 参数值与实际语速转换，可参考 <a href="https://sdk-1300466766.cos.ap-shanghai.myqcloud.com/sample/speed_sample.tar.gz">语速转换</a><br> &emsp; "Volume": 5, // Integer 非必填，音量大小，范围：[0，10]，分别对应11个等级的音量，默认值为0，代表正常音量。<br> &emsp; "EmotionCategory":  "angry", // String 非必填 控制合成音频的情感，仅支持多情感音色使用。取值: neutral(中性)、sad(悲伤)、happy(高兴)、angry(生气)、fear(恐惧)、news(新闻)、story(故事)、radio(广播)、poetry(诗歌)、call(客服)、sajiao(撒娇)、disgusted(厌恶)、amaze(震惊)、peaceful(平静)、exciting(兴奋)、aojiao(傲娇)、jieshuo(解说)。<br> &emsp; "EmotionIntensity":  150 // Integer 非必填 控制合成音频情感程度，取值范围为 [50,200]，默认为 100；只有 EmotionCategory 不为空时生效。<br> &emsp; }</pre>
         # @type TTSConfig: String
@@ -6497,6 +6514,118 @@ module TencentCloud
         end
       end
 
+      # TextToSpeech请求参数结构体
+      class TextToSpeechRequest < TencentCloud::Common::AbstractModel
+        # @param Text: 需要转语音的文字内容，长度范围：[1, 255]
+        # @type Text: String
+        # @param Voice: 文本转语音的声音配置
+        # @type Voice: :class:`Tencentcloud::Trtc.v20190722.models.Voice`
+        # @param SdkAppId: TRTC的SdkAppId
+        # @type SdkAppId: Integer
+        # @param AudioFormat: 文本转语音的输出音频的格式
+        # @type AudioFormat: :class:`Tencentcloud::Trtc.v20190722.models.AudioFormat`
+        # @param APIKey: TTS的API密钥
+        # @type APIKey: String
+
+        attr_accessor :Text, :Voice, :SdkAppId, :AudioFormat, :APIKey
+
+        def initialize(text=nil, voice=nil, sdkappid=nil, audioformat=nil, apikey=nil)
+          @Text = text
+          @Voice = voice
+          @SdkAppId = sdkappid
+          @AudioFormat = audioformat
+          @APIKey = apikey
+        end
+
+        def deserialize(params)
+          @Text = params['Text']
+          unless params['Voice'].nil?
+            @Voice = Voice.new
+            @Voice.deserialize(params['Voice'])
+          end
+          @SdkAppId = params['SdkAppId']
+          unless params['AudioFormat'].nil?
+            @AudioFormat = AudioFormat.new
+            @AudioFormat.deserialize(params['AudioFormat'])
+          end
+          @APIKey = params['APIKey']
+        end
+      end
+
+      # TextToSpeech返回参数结构体
+      class TextToSpeechResponse < TencentCloud::Common::AbstractModel
+        # @param Audio: Base64编码的音频数据
+        # @type Audio: String
+        # @param RequestId: 唯一请求 ID，由服务端生成，每次请求都会返回（若请求因其他原因未能抵达服务端，则该次请求不会获得 RequestId）。定位问题时需要提供该次请求的 RequestId。
+        # @type RequestId: String
+
+        attr_accessor :Audio, :RequestId
+
+        def initialize(audio=nil, requestid=nil)
+          @Audio = audio
+          @RequestId = requestid
+        end
+
+        def deserialize(params)
+          @Audio = params['Audio']
+          @RequestId = params['RequestId']
+        end
+      end
+
+      # TextToSpeechSSE请求参数结构体
+      class TextToSpeechSSERequest < TencentCloud::Common::AbstractModel
+        # @param Text: 需要转语音的文字内容，长度范围：[1, 255]
+        # @type Text: String
+        # @param Voice: 文本转语音的声音配置
+        # @type Voice: :class:`Tencentcloud::Trtc.v20190722.models.Voice`
+        # @param SdkAppId: TRTC的SdkAppId
+        # @type SdkAppId: Integer
+        # @param AudioFormat: 文本转语音的输出音频的格式
+        # @type AudioFormat: :class:`Tencentcloud::Trtc.v20190722.models.AudioFormat`
+        # @param APIKey: TTS的API密钥
+        # @type APIKey: String
+
+        attr_accessor :Text, :Voice, :SdkAppId, :AudioFormat, :APIKey
+
+        def initialize(text=nil, voice=nil, sdkappid=nil, audioformat=nil, apikey=nil)
+          @Text = text
+          @Voice = voice
+          @SdkAppId = sdkappid
+          @AudioFormat = audioformat
+          @APIKey = apikey
+        end
+
+        def deserialize(params)
+          @Text = params['Text']
+          unless params['Voice'].nil?
+            @Voice = Voice.new
+            @Voice.deserialize(params['Voice'])
+          end
+          @SdkAppId = params['SdkAppId']
+          unless params['AudioFormat'].nil?
+            @AudioFormat = AudioFormat.new
+            @AudioFormat.deserialize(params['AudioFormat'])
+          end
+          @APIKey = params['APIKey']
+        end
+      end
+
+      # TextToSpeechSSE返回参数结构体
+      class TextToSpeechSSEResponse < TencentCloud::Common::AbstractModel
+        # @param RequestId: 唯一请求 ID，由服务端生成，每次请求都会返回（若请求因其他原因未能抵达服务端，则该次请求不会获得 RequestId）。定位问题时需要提供该次请求的 RequestId。本接口为流式响应接口，当请求成功时，RequestId 会被放在 HTTP 响应的 Header "X-TC-RequestId" 中。
+        # @type RequestId: String
+
+        attr_accessor :RequestId
+
+        def initialize(requestid=nil)
+          @RequestId = requestid
+        end
+
+        def deserialize(params)
+          @RequestId = params['RequestId']
+        end
+      end
+
       # 返回的质量数据，时间:值
       class TimeValue < TencentCloud::Common::AbstractModel
         # @param Time: 时间，unix时间戳（1590065877s)
@@ -7045,6 +7174,74 @@ module TencentCloud
         end
       end
 
+      # TTS的声音参数
+      class Voice < TencentCloud::Common::AbstractModel
+        # @param VoiceId: TTS的声音的ID
+        # @type VoiceId: String
+
+        attr_accessor :VoiceId
+
+        def initialize(voiceid=nil)
+          @VoiceId = voiceid
+        end
+
+        def deserialize(params)
+          @VoiceId = params['VoiceId']
+        end
+      end
+
+      # VoiceClone请求参数结构体
+      class VoiceCloneRequest < TencentCloud::Common::AbstractModel
+        # @param SdkAppId: TRTC的SdkAppId
+        # @type SdkAppId: Integer
+        # @param APIKey: TTS的API密钥
+        # @type APIKey: String
+        # @param VoiceName: 声音克隆的名称, 只允许使用数字、字母、下划线，不能超过36位
+        # @type VoiceName: String
+        # @param PromptAudio: 声音克隆的参考音频，必须为16k单声道的wav的base64字符串， 长度在5秒～12秒之间
+        # @type PromptAudio: String
+        # @param PromptText: 声音克隆的参考文本，为参考音频对应的文字。
+        # @type PromptText: String
+
+        attr_accessor :SdkAppId, :APIKey, :VoiceName, :PromptAudio, :PromptText
+
+        def initialize(sdkappid=nil, apikey=nil, voicename=nil, promptaudio=nil, prompttext=nil)
+          @SdkAppId = sdkappid
+          @APIKey = apikey
+          @VoiceName = voicename
+          @PromptAudio = promptaudio
+          @PromptText = prompttext
+        end
+
+        def deserialize(params)
+          @SdkAppId = params['SdkAppId']
+          @APIKey = params['APIKey']
+          @VoiceName = params['VoiceName']
+          @PromptAudio = params['PromptAudio']
+          @PromptText = params['PromptText']
+        end
+      end
+
+      # VoiceClone返回参数结构体
+      class VoiceCloneResponse < TencentCloud::Common::AbstractModel
+        # @param VoiceId: 克隆出的音色ID，可以用此id进行语音合成
+        # @type VoiceId: String
+        # @param RequestId: 唯一请求 ID，由服务端生成，每次请求都会返回（若请求因其他原因未能抵达服务端，则该次请求不会获得 RequestId）。定位问题时需要提供该次请求的 RequestId。
+        # @type RequestId: String
+
+        attr_accessor :VoiceId, :RequestId
+
+        def initialize(voiceid=nil, requestid=nil)
+          @VoiceId = voiceid
+          @RequestId = requestid
+        end
+
+        def deserialize(params)
+          @VoiceId = params['VoiceId']
+          @RequestId = params['RequestId']
+        end
+      end
+
       # 声纹配置参数
       class VoicePrint < TencentCloud::Common::AbstractModel
         # @param Mode: 默认为0，表示不启用声纹。1表示启用声纹，此时需要填写voiceprint id。

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: tencentcloud-sdk-trtc
 version: !ruby/object:Gem::Version
-  version: 3.0.1115
+  version: 3.0.1123
 platform: ruby
 authors:
 - Tencent Cloud
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2025-08-01 00:00:00.000000000 Z
+date: 2025-08-14 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: tencentcloud-sdk-common