SmartAudioTTSAdapter

Overview

Converts the Text property of the associated Wisej.NET Audio control into natural, lifelike speech using advanced text-to-speech technology.

You can use the SmartAudioTTSAdapter (Text-To-Speech) to convert plain text into audio files. These audio files can then be played back using the associated Audio control in your application. This integration allows you to add dynamic voice output capabilities to your Wisej.NET applications.

Configuration

[Extends(typeof(Audio), allowMultiple: true)]
[WorksWith(typeof(OpenAIEndpointTTS))]
[WorksWith(typeof(LocalAIEndpointTTS))]

Properties

In addition to the properties inherited from the SmartAdapter, the SmartAudioTTSAdapter exposes the following additional properties.

Voice

Specifies the voice to use for speech synthesis. Available voices include: Alloy (default), Echo, Fable, Onyx, Nova, and Shimmer. However, the selection of voices depends on the specific text-to-speech (TTS) model being used. Refer to the documentation for your chosen TTS provider to determine which voices are supported.

AudioFormat

Specifies the audio format for the generated speech output. The default format is "mp3". Other supported formats include "opus", "aac", "flac", and "pcm". However, the availability of each audio format depends on the specific text-to-speech (TTS) model being used. Please consult the documentation for your selected TTS provider to confirm which audio formats are supported.

Speed

Gets or sets the playback speed of the generated audio. The value should be between 0.5 and 4.0, although the acceptable range may vary depending on the specific text-to-speech (TTS) model in use. Please refer to the documentation for your selected TTS provider to confirm supported speed values.

AudioFilesPath

The AudioFilesPath property specifies the directory where audio files are stored. By default, this property is set to "~AI\AudioFiles". Wisej.AI uses this path to save audio content generated by the text-to-speech (TTS) model.