DiffSinger is a voice synthesizer using artificial intelligence to produce the voice from scratch, mimics the qualities of the voice provider completely
Voicebank counting expressions and recorded time:
【Standard • Nightcore • Calm • Growl • Falsetto • Cute • Screamo • Female • Solid • Mature • Nasal • Whisper • Adult • Punk • Nexus】
This Voicebank can sing in different languages, being Spanish the native one, but the other languages are:
Spanish, English, French, Japanese, Korean, Russian, Thai, Italian, German
