For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).

Python class

AudioProviderOptions

AudioProviderOptions

class max.pipelines.request.provider_options.AudioProviderOptions(*, lyrics=None, audio_duration=None, steps=None, guidance_scale=None, audio_format='wav')

source

Bases: BaseModel

Options specific to audio generation pipelines.

Audio does not share the pixel modalities’ base: it has no width, height, or negative prompt, and the text it takes beyond the prompt is lyrics rather than a second caption.

Parameters:

• lyrics (str | None)
• audio_duration (float | None)
• steps (int | None)
• guidance_scale (float | None)
• audio_format (str)

audio_duration

audio_duration: float | None

source

audio_format

audio_format: str

source

guidance_scale

guidance_scale: float | None

source

lyrics

lyrics: str | None

source

model_config

model_config: ClassVar[ConfigDict] = {'extra': 'forbid', 'frozen': True}

source

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

steps

steps: int | None

source