Enum VoiceType
Namespace: Glitch9.AIDevKit
Assembly: Glitch9.AIDevKit.dll
Syntax
public enum VoiceType
Fields
| Name | Description |
|---|---|
| Neural | Deep learning-based neural synthesis. Produces more natural, human-like speech. Used by Microsoft Azure TTS (Neural tier), Amazon Polly (Neural tier), ElevenLabs, and OpenAI TTS. |
| Standard | Rule-based concatenative synthesis. Lower computational cost but less natural prosody. Used by Microsoft Azure TTS (Standard tier) and Amazon Polly (Standard tier). |
| WaveNet | Google DeepMind's WaveNet-based synthesis model, exclusive to Google Cloud TTS. Functionally equivalent to Neural TTS but identified separately to preserve provider-specific voice metadata. |