Description #

Audio format conversion processor that converts various audio formats to MP3

Key features #

• Supports converting multiple audio formats to MP3
• Customizable audio quality and encoding parameters
• Supports fine control of audio sample rate and bitrate
• Automatically selects the first audio track
• Supports local files, HTTP/HTTPS URLs, and TOS/S3 storage

Format support #

• Input: WAV, FLAC, AAC, M4A, OGG, WMA, APE, and other mainstream audio formats
• Output: MP3 (.mp3)
• Audio codec: LAME MP3 encoder
• Sample rate: 8kHz–96kHz
• Bitrate: 32kbps–320kbps

Operator parameters #

Input #

Output #

An array containing the conversion result paths. Returns the output path on success, returns None on failure.

Parameters #

If a parameter does not have a default value, it is required.

Examples #

The following code demonstrates how to use Daft (for distributed scenarios) to run the operator for converting audio to MP3 format.

from __future__ import annotations

import os

import daft
from daft import col
from daft.las.functions.audio import AudioConvertToMp3
from daft.las.functions.udf import las_udf

if __name__ == "__main__":
    # The converted audio will be saved to the specified TOS path. Therefore, you need to set environment variables to ensure write permissions to TOS, including: ACCESS_KEY, SECRET_KEY, TOS_ENDPOINT, TOS_REGION, TOS_TEST_DIR
    TOS_TEST_DIR_URL = os.getenv("TOS_TEST_DIR_URL", "las-cn-beijing-public-online.tos-cn-beijing.volces.com")
    TOS_TEST_DIR = os.getenv("TOS_TEST_DIR", "tos_bucket")

    if os.getenv("DAFT_RUNNER", "native") == "ray":
        import logging

        import ray

        def configure_logging():
            logging.basicConfig(
                level=logging.INFO,
                format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
                datefmt="%Y-%m-%d %H:%M:%S",
            )
            logging.getLogger("tracing.span").setLevel(logging.WARNING)
            logging.getLogger("daft_io.stats").setLevel(logging.WARNING)
            logging.getLogger("DaftStatisticsManager").setLevel(logging.WARNING)
            logging.getLogger("DaftFlotillaScheduler").setLevel(logging.WARNING)
            logging.getLogger("DaftFlotillaDispatcher").setLevel(logging.WARNING)

        ray.init(dashboard_host="0.0.0.0", runtime_env={"worker_process_setup_hook": configure_logging})
        daft.set_runner_ray()

    daft.set_execution_config(actor_udf_ready_timeout=600)
    daft.set_execution_config(min_cpu_per_task=0)

    samples = {
        "input_path": [f"https://{TOS_TEST_DIR_URL}/public/archive/audio_convert_to_mp3/sample.wav"],
        "output_path": [f"tos://{TOS_TEST_DIR}/audio_convert_to_mp3/sample_converted.mp3"],
    }
    ds = daft.from_pydict(samples)

    # Using Daft to convert audio to MP3 format
    constructor_kwargs = {
        "bitrate": "192k",
        "sample_rate": 44100,
        "audio_map": "auto",
        "quality": 2,
        "extra_params": [],
    }

    ds = ds.with_column(
        "convert_result",
        las_udf(
            AudioConvertToMp3,
            construct_args=constructor_kwargs,
            num_cpus=1,
            concurrency=1,
            batch_size=1,
        )(col("input_path"), col("output_path")),
    )

    ds.show()
    # ╭────────────────────────────────┬────────────────────────────────┬────────────────────────────────╮
    # │ input_path                     ┆ output_path                    ┆ convert_result                 │
    # │ ---                            ┆ ---                            ┆ ---                            │
    # │ String                         ┆ String                         ┆ String                         │
    # ╞════════════════════════════════╪════════════════════════════════╪════════════════════════════════╡
    # │ https://las-public-data-qa.to… ┆ tos://tos_bucket/audio_conver… ┆ tos://tos_bucket/audio_conver… │
    # ╰────────────────────────────────┴────────────────────────────────┴────────────────────────────────╯