You're looking at a specific version of this model. Jump to the model overview.
kamaravichow /maya-2-indic-audio:eebab570
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
|
Text to speak. Output is synthetic speech.
|
|
| language |
None
|
en
|
Language of the input text.
|
| voice |
None
|
Ahana
|
Built-in synthetic voice.
|
| normalize |
boolean
|
True
|
Normalize numbers, dates, currencies and abbreviations.
|
| max_seconds |
number
|
30
Min: 0.08 Max: 120 |
Maximum output duration. Speech may be cut off at this limit.
|
| seed |
integer
|
20261024
Max: 2147483647 |
Random seed for a single sequential request.
|
| temperature |
number
|
0.9
Min: 0.05 Max: 2 |
Codebook-0 sampling temperature.
|
| top_k |
integer
|
64
Min: 1 Max: 2049 |
Codebook-0 top-k sampling cutoff.
|
| top_p |
number
|
1
Min: 0.000001 Max: 1 |
Codebook-0 nucleus sampling cutoff.
|
| repetition_penalty |
number
|
0.8
Max: 5 |
Codebook-0 presence penalty over the last 12 frames.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'format': 'uri', 'title': 'Output', 'type': 'string'}