Generate Audio

This action generates file for the specified input text with an AI model.

Action Settings

Setting Description
Model Enum, required. The Model's resource name. This serves as an ID for the Model to use.
Voice Enum, required. The voice to use for generating the audio.
Temperature Double, optional. Controls the randomness of the output. The default value varies by Model. Values can range from [0.0, 2.0]
TopP Double, optional. The maximum cumulative probability of tokens to consider when sampling.
TopK Int, optional. The maximum number of tokens to consider when sampling.
Seed Int, optional. Seed used in decoding. If not set, the request uses a randomly generated seed.
MaxOutputTokens Int32, optional. The maximum number of tokens to include in a response candidate.

Action Parameters

Parameter Description
Prompt String, required. The user-provided text to be processed by the Model.

Result

The result contains the following fields: Audio_ResponseId, Audio_BinaryContent, Audio_FinishReason, Audio_TotalTokenCount.