TTS mode: voice cloning requires a prompt audio file to mimic the voice; voice creation generates speech with specified gender/pitch/speed parameters. (TTS模式：声音克隆需要提供语音样本来模仿声音；声音创建使用指定的性别/音高/语速参数生成语音)

Default

"voice_creation"

Text for TTS generation - REQUIRED in both modes (要转换为语音的文本 - 两种模式下都必需)

[Voice Creation] Voice pitch level - REQUIRED in voice creation mode (声音创建模式：声音音高 - 声音创建模式下必需)

Default

"moderate"

[Voice Creation] Speaking speed - REQUIRED in voice creation mode (声音创建模式：说话速度 - 声音创建模式下必需)

Default

"moderate"

Top-k sampling parameter - Limits the token selection to top k options (Top-k采样参数 - 将令牌选择限制为前k个选项)

Default

50

Top-p sampling parameter - Nucleus sampling probability threshold (Top-p采样参数 - 核采样概率阈值)

Default

0.95

[Voice Creation] Voice gender - REQUIRED in voice creation mode (声音创建模式：声音性别 - 声音创建模式下必需)

Default

"female"

[Voice Cloning] Transcript of prompt audio - Optional but improves quality (声音克隆模式：提示音频的文本转录 - 可选，但提供可提高质量)

Sampling temperature (0.0-1.0) - Controls randomness in generation (采样温度 - 控制生成的随机性)

Default

0.8

[Voice Cloning] Path to the prompt audio file - REQUIRED in voice cloning mode (声音克隆模式：提示音频文件路径 - 声音克隆模式下必需)