You're looking at a specific version of this model. Jump to the model overview.
nghimestudio /vieneu-tts:7f9fe07b
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
|
Vietnamese (or bilingual) text to synthesize. Supports optional emotion tags: [cười], [thở dài], [hắng giọng].
|
|
| voice |
None
|
Hải Đăng
|
Built-in preset voice. Ignored when ref_audio is provided.
|
| ref_audio |
string
|
Optional 3–8s reference clip for instant voice cloning. When set, overrides the preset voice.
|
|
| denoise |
boolean
|
True
|
Denoise / trim the reference clip before cloning.
|
| temperature |
number
|
0.8
Min: 0.1 Max: 1.5 |
Sampling temperature.
|
| top_k |
integer
|
25
Min: 1 Max: 100 |
Top-k sampling.
|
| top_p |
number
|
0.95
Min: 0.1 Max: 1 |
Top-p (nucleus) sampling.
|
| repetition_penalty |
number
|
1.2
Min: 1 Max: 2 |
Repetition penalty.
|
| max_chars |
integer
|
256
Min: 32 Max: 512 |
Max characters per synthesis chunk.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'format': 'uri', 'title': 'Output', 'type': 'string'}