Modeisteğe bağlı
TTS mode: 'custom_voice' uses preset speakers, 'voice_clone' clones from reference audio, 'voice_design' creates voice from description
Languageisteğe bağlı
Language of the text (use 'auto' for automatic detection)
Speakeristeğe bağlı
Preset speaker voice (only for 'custom_voice' mode)
Voice Descriptionisteğe bağlı
Natural language description of desired voice (only for 'voice_design' mode). Example: 'A warm, friendly female voice with a slight British accent'
Reference Audioisteğe bağlı
Reference audio file for voice cloning (only for 'voice_clone' mode)
Reference Textisteğe bağlı
Transcript of the reference audio (recommended for 'voice_clone' mode)
Style Instructionisteğe bağlı
Optional style/emotion instruction (e.g., 'speak slowly and calmly', 'excited tone')
