Introducing LiteRT: Google's high-performance runtime for on-device AI, formerly known as TensorFlow Lite. Learn more

tflite_support.task.audio.AudioRecord

A class to record audio in a streaming basis.

tflite_support.task.audio.AudioRecord(
    channels: int, sampling_rate: int, buffer_size: int
) -> None

Args
`channels`	Number of input channels.
`sampling_rate`	Sampling rate in Hertz.
`buffer_size`	Size of the ring buffer in number of samples.

Raises
`ValueError`	if any of the arguments is non-positive.
`ImportError`	if failed to import `sounddevice`.
`OSError`	if failed to load `PortAudio`.

Attributes

buffer_size

channels

sampling_rate

read(
    size: int
) -> np.ndarray

Reads the latest audio data captured in the buffer.

Args
`size`	Number of samples to read from the buffer.

Returns
A NumPy array containing the audio data.

Raises
`ValueError`	Raised if `size` is larger than the buffer size.

start_recording() -> None

Starts the audio recording.

stop() -> None

Stops the audio recording.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2024-05-08 UTC.