Skip to main content

AudioChunk

One chunk of a streamed synthesis: mono Float32 samples at sample_rate, in order; the chunks concatenate to the utterance.

index (property)​

The chunk's position in the stream, 0-based.

is_last (property)​

True on the stream's last chunk.

sample_rate (property)​

(self) -> int

samples (property)​

The chunk's samples, a Float32 [S] tensor.

__init__​

__init__(self, /, *args, **kwargs)

Initialize self. See help(type(self)) for accurate signature.