Michele LaurelliBlog

TTS (Text-to-Speech)

TTS (Text-to-Speech): Speech synthesis from text, with control over voice, prosody and pronunciation. The model produces acoustic representations and a vocoder or decoder generates audio. Intelligibility, naturalness and authorization to use a voice are distinct requirements. Examples include Article narration, Voice assistant, Synthetic audiobooks.

In italiano: TTS (Text-to-Speech)Legge II · Probabilità, softmax e modelli generativi

The model produces acoustic representations and a vocoder or decoder generates audio. Intelligibility, naturalness and authorization to use a voice are distinct requirements.

Examples

  • Article narration
  • Voice assistant
  • Synthetic audiobooks