类的使用
io.agentscope.core.message.AudioBlock

使用AudioBlock的程序包

程序包	说明
io.agentscope.core.formatter.dashscope
io.agentscope.core.formatter.gemini
io.agentscope.core.hook
io.agentscope.core.message
io.agentscope.core.model.tts

io.agentscope.core.formatter.dashscope中AudioBlock的使用

参数类型为AudioBlock的io.agentscope.core.formatter.dashscope中的方法

修饰符和类型	方法	说明
DashScopeContentPart	DashScopeMediaConverter.convertAudioBlockToContentPart(AudioBlock audioBlock)	Convert AudioBlock to DashScopeContentPart.
String	DashScopeMediaConverter.convertAudioBlockToUrl(AudioBlock audioBlock)	Convert AudioBlock to URL string for DashScope API.

io.agentscope.core.formatter.gemini中AudioBlock的使用

参数类型为AudioBlock的io.agentscope.core.formatter.gemini中的方法

修饰符和类型	方法	说明
com.google.genai.types.Part	GeminiMediaConverter.convertToInlineDataPart(AudioBlock block)	Convert AudioBlock to Gemini Part with inline data.

io.agentscope.core.hook中AudioBlock的使用

返回变量类型为AudioBlock的类型的io.agentscope.core.hook中的方法

修饰符和类型	方法	说明
reactor.core.publisher.Flux<AudioBlock>	TTSHook.getAudioStream()	Gets the reactive audio stream.

类型变量类型为AudioBlock的io.agentscope.core.hook中的方法参数

修饰符和类型	方法	说明
TTSHook.Builder	TTSHook.Builder.audioCallback(Consumer<AudioBlock> audioCallback)	Sets a callback for receiving audio blocks.

io.agentscope.core.message中AudioBlock的使用

返回AudioBlock的io.agentscope.core.message中的方法

修饰符和类型	方法	说明
AudioBlock	AudioBlock.Builder.build()	Builds a new AudioBlock with the configured source.

io.agentscope.core.model.tts中AudioBlock的使用

返回AudioBlock的io.agentscope.core.model.tts中的方法

修饰符和类型	方法	说明
AudioBlock	TTSResponse.toAudioBlock()	Converts this response to an AudioBlock for use in Msg.

返回变量类型为AudioBlock的类型的io.agentscope.core.model.tts中的方法

修饰符和类型	方法	说明
reactor.core.publisher.Flux<AudioBlock>	DashScopeRealtimeTTSModel.finish()	Finishes the streaming session and retrieves remaining audio.
reactor.core.publisher.Flux<AudioBlock>	RealtimeTTSModel.finish()	Signals end of input and flushes remaining audio.
reactor.core.publisher.Flux<AudioBlock>	DashScopeRealtimeTTSModel.getAudioStream()	Gets the audio stream for listening to all audio chunks.
reactor.core.publisher.Flux<AudioBlock>	RealtimeTTSModel.getAudioStream()	Gets the audio stream for receiving synthesized audio.
reactor.core.publisher.Flux<AudioBlock>	DashScopeRealtimeTTSModel.push(String text)	Pushes a text chunk for synthesis.
reactor.core.publisher.Flux<AudioBlock>	RealtimeTTSModel.push(String text)	Pushes text incrementally to the TTS service.
reactor.core.publisher.Flux<AudioBlock>	DashScopeRealtimeTTSModel.synthesizeStream(String text)	Synthesizes complete text to audio using streaming.
reactor.core.publisher.Flux<AudioBlock>	RealtimeTTSModel.synthesizeStream(String text)	Synthesizes text using streaming and returns audio blocks.

参数类型为AudioBlock的io.agentscope.core.model.tts中的方法

修饰符和类型	方法	说明
void	AudioPlayer.play(AudioBlock audioBlock)	Plays an AudioBlock.