Parses the specified JSON string into a parse tree @param reader JSON text @return a parse tree of {@link JsonElement}s corresponding to the specifie

Pre-warm the HTTP connection to reduce latency for first API call. Uses a lightweight list request to establish connection pool.

查询指定热词表 @param vocabularyId 需要查询的热词表 @return 热词表对象 @throws NoApiKeyException 如果apikey为空 @throws InputRequiredException 如果必须参数为空

查询指定音色 @param voiceId 需要查询的音色 @return Voice 音色对象，包含状态信息和用于克隆的音频文件url @throws NoApiKeyException 如果apikey为空 @throws InputRequiredException 如果必须参数为空

Reset SDK, should be called before reuse SDK object.

Reset SDK, should be called before reuse SDK object.

Retrieve the run step. @param threadId The thread id. @param runId The run id. @param stepId the run step id. @return The `RunStep` object. @throws A

Send one frame audio @param audioFrame One frame of binary audio The correct order of calls is: first call, then repeatedly sendAudioFrame, and f

Send one frame audio @param audioFrame One frame of binary audio The correct order of calls is: first call, then repeatedly sendAudioFrame, and f

Send one frame audio @param audioFrame One frame of binary audio The correct order of calls is: first call, then repeatedly sendAudioFrame, and f

Send tool call result back to server using createItem

Set text in corpus to improve model recognition accuracy.

Stop Speech Translation and Recognition real-time via call and sendAudioFrame API. The correct order of calls is: first call, then repeatedly sendAudi

Stop Speech Translation and Recognition real-time via call and sendAudioFrame API. The correct order of calls is: first call, then repeatedly sendAudi

Stop Speech Translation and Recognition real-time via call and sendAudioFrame API. The correct order of calls is: first call, then repeatedly sendAudi

Call the server to get the result by stream. @param param The input param of class `ImageGenerationParam`. @return A `Flowable` of the output structu

Stream call with CIP (Content Integrity Protection) parameters sample @throws NoApiKeyException Can not find api key @throws InputRequiredExcept

Demonstrates streaming call with callback - receives audio chunks as they arrive.

Streaming input mode: You can call the stream_call function multiple times to send text. A session will be created on the first call. The session ends

Demonstrates synchronous call with SSE - blocks until synthesis is complete and returns audio data.

Note: This method currently now only supports wan2.2-t2i-flash and wan2.2-t2i-plus. Using other models will result in an error，More raw image models m

Demonstrates synchronous call without SSE - returns audio URL instead of audio data. This is a simpler and faster way to get the synthesized audio.