You're looking at a specific version of this model. Jump to the model overview.
suminhthanh /vixtts:ac720f52
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
|
Xin chào các bạn
|
Text to synthesize
|
| speaker |
string
|
Original speaker audio (wav, mp3, m4a, ogg, or flv). Duration should be at least 6 seconds.
|
|
| language |
string
(enum)
|
vi
Options: vi, en, es, fr, de, it, pt, pl, tr, ru, nl, cs, ar, zh, hu, ko, hi |
Output language for the synthesised speech
|
| cleanup_voice |
boolean
|
False
|
Whether to apply denoising to the speaker audio (microphone recordings)
|
| use_deepfilter |
boolean
|
False
|
Whether to use deepfilter
|
| normalize_text |
boolean
|
False
|
Whether to normalize the text
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'properties': {'path': {'format': 'uri', 'title': 'Path', 'type': 'string'}},
'required': ['path'],
'title': 'Output',
'type': 'object'}