Actions10
AudioQuery取得
AI-generatedSummary
Retrieve AudioQuery data for given text and speaker ID to obtain detailed phoneme and accent information used in speech synthesis.
Inputs
- text (required) — The text to be pronounced.
- speakerId (required) — The speaker's style ID, which can be confirmed by retrieving the speaker list.
Output shape
a single JSON object containing the AudioQuery data, original text, and speakerId
The AudioQuery JSON includes phoneme timing, accent, and prosody details necessary for subsequent speech synthesis operations.
Examples
Example 1: Obtain phoneme and accent details for the text 'こんにちは' with speaker style ID 888753760
Pass text='こんにちは' and speakerId=888753760 as parameters, then use the resulting AudioQuery JSON for fine-tuned speech synthesis.