Actions10
音声合成（AudioQueryから）
AI-generatedSummary
Synthesize speech audio from provided AudioQuery JSON data by specifying a speaker style ID, producing a WAV audio binary output accessible under a named binary property.
Inputs
- speakerId (required) — Speaker style ID to use for synthesis, as available from the speaker list
- audioQueryJson (required) — JSON data from a prior AudioQuery retrieval, representing the detailed phoneme and prosody parameters for synthesis
- binaryPropertyName — Name of the binary property in which the synthesized audio WAV file is output (default is 'data')
Output shape
Single item with JSON containing success status and speakerId, and a binary property containing the synthesized WAV audio data
The output binary property name can be customized via 'binaryPropertyName' parameter, and the audio data is in WAV format encoded for playback or saving.
Examples
Example 1: Generate speech audio from an existing AudioQuery JSON for a selected speaker style
Provide the speakerId corresponding to the desired voice style, supply the AudioQuery JSON data obtained from a previous request, and optionally set the output binary property name to access the resulting audio in downstream nodes