You're looking at a specific version of this model. Jump to the model overview.
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| text |
string
|
[S1]你好[S2]你好
|
对话文本，格式：[S1]说话者1的内容[S2]说话者2的内容[S1]... / Dialogue text, format: [S1]Speaker 1 content[S2]Speaker 2 content[S1]...
|
| reference_audio_speaker1 |
string
|
说话者1的参考音频文件（可选，用于声音克隆）/ Reference audio file for speaker 1 (optional, for voice cloning)
|
|
| reference_text_speaker1 |
string
|
|
说话者1的参考文本（与参考音频对应）/ Reference text for speaker 1 (corresponding to reference audio)
|
| reference_audio_speaker2 |
string
|
说话者2的参考音频文件（可选，用于声音克隆）/ Reference audio file for speaker 2 (optional, for voice cloning)
|
|
| reference_text_speaker2 |
string
|
|
说话者2的参考文本（与参考音频对应）/ Reference text for speaker 2 (corresponding to reference audio)
|
| use_normalize |
boolean
|
False
|
是否使用文本规范化（推荐开启，改善数字、标点符号等的处理）/ Whether to use text normalization (recommended for better handling of numbers, punctuation, etc.)
|
| seed |
integer
|
42
|
随机种子，用于结果重现 / Random seed for reproducibility
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'format': 'uri', 'title': 'Output', 'type': 'string'}