We propose PromptTTS++, a prompt-based text-to-speech (TTS) synthesis system that allows control over speaker identity using natural language descriptions. To control speaker identity within the ...

GitHub is where people build software. More than 150 million people use GitHub to discover, fork, and contribute to over 420 million projects.

Scaling Zero-shot Text-to-speech (TTS) to large-scale datasets has been demonstrated as an effective method for improving the diversity and naturalness of synthesized speech. At the high level, ...