You're looking at a specific version of this model. Jump to the model overview.
lucataco /higgs-audio-v2:f5945a34
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
|
The sun rises in the east and sets in the west
|
Text to convert to speech
|
| temperature |
number
|
0.3
Min: 0.1 Max: 1 |
Controls randomness in generation. Lower values are more deterministic.
|
| top_p |
number
|
0.95
Min: 0.1 Max: 1 |
Nucleus sampling parameter. Controls diversity of generated audio.
|
| top_k |
integer
|
50
Min: 1 Max: 100 |
Top-k sampling parameter. Limits vocabulary to top k tokens.
|
| max_new_tokens |
integer
|
1024
Min: 256 Max: 2048 |
Maximum number of audio tokens to generate
|
| scene_description |
string
|
Audio is recorded from a quiet room.
|
Scene description for audio context
|
| system_message |
string
|
|
Custom system message (optional)
|
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'}