AI Converter

API Tools

• API Tool provides some API for features: Sync Text, Normalize Audio Mp3

1. Sync Text for Audio API Documentation

Endpoint

URL: https://aitools.monkeyenglish.net/segement

Method: POST

Parameters

Returns

Example Request

curl -X 'POST' \
  'https://aitools.monkeyenglish.net/segement' \
  -H 'accept: application/json' \
  -H 'Content-Type: multipart/form-data' \
  -F 'audio=@L2U6 - Chant 4 - Mr. Billy.mp3;type=audio/mpeg' \
  -F 'karaoke_format=false' \
  -F 'text='

2. API normalize mp3 file

Endpoint: https://aitools.monkeyenglish.net/normalize-audio`

Method: POST

Parameters

Returns

Example Request

curl -X 'POST' \
  'https://aitools.monkeyenglish.net/normalize-audio' \
  -H 'accept: application/json' \
  -H 'Content-Type: multipart/form-data' \
  -F 'file=@L2U6 - Chant 4 - Mr. Billy.mp3;type=audio/mpeg'

Score Audio from CSV

POST /score_audio
Description: Processes an uploaded CSV or Excel file and returns a CSV file with processed results.

Request
Content-Type: multipart/form-data
Parameters:
file (required): An uploaded file in CSV or Excel format. The file should contain the data to be processed.
name_column_text (required): The name of the column in the file that contains text data.
name_column_audio (required): The name of the column in the file that contains audio data.
name_column_output (required): The name of the column where the processed results will be written.

Convert Audio API

Base URL

The base URL for the API is: https://aitools.monkeyenglish.net/

Endpoints

1. Convert MP3 to WAV

Endpoint: POST /mp3-to-wav/

Description: Converts an MP3 file to a WAV file.

Request:

• file: The MP3 file to be converted. (required)

Response:

• Returns a WAV file with Content-Disposition header set to attachment; filename={original_filename}.wav.

2. Convert WAV to MP3

Endpoint: POST /wav-to-mp3/

Description: Converts a WAV file to an MP3 file.

Request:

• file: The WAV file to be converted. (required)

Response:

• Returns an MP3 file with Content-Disposition header set to attachment; filename={original_filename}.mp3.

3. Normalize MP3

Endpoint: POST /normalize-mp3/

Description: Normalizes the volume of an MP3 file.

Request:

• file: The MP3 file to be normalized. (required)

Response:

• Returns a normalized MP3 file with Content-Disposition header set to attachment; filename={original_filename}_normalized.mp3.

4. Normalize WAV

Endpoint: POST /normalize-wav/

Description: Normalizes the volume of a WAV file and optionally changes the sample rate and number of channels.

Request:

• file: The WAV file to be normalized. (required)
• sample_rate: The sample rate for the output file. (optional, default: 44100)
• channels: The number of channels for the output file. (optional, default: 2)

Response:

• Returns a normalized WAV file with Content-Disposition header set to attachment; filename={original_filename}_normalized.wav.

5. Convert WAV to Normalized MP3

Endpoint: POST /wav-normalize-mp3/

Description: Converts a WAV file to an MP3 file and normalizes the volume.

Request:

• file: The WAV file to be converted and normalized. (required)

Response:

• Returns a normalized MP3 file with Content-Disposition header set to attachment; filename={original_filename}_normalized.mp3.

6. Convert MP3 to Custom WAV

Endpoint: POST /mp3-custom-wav/

Description: Converts an MP3 file to a WAV file with custom sample rate and number of channels.

Request:

• file: The MP3 file to be converted. (required)
• sample_rate: The sample rate for the output file. (optional, default: 44100)
• channels: The number of channels for the output file. (optional, default: 2)

Response:

• Returns a WAV file with Content-Disposition header set to attachment; filename={original_filename}_normalized.wav.

CLI Tools

1. CLI Usage Document for _sync_lip_sync.py

Overview

The _sync_lip_sync.py script is designed to synchronize lip sync data from a source directory to a destination directory. This script is executed using Python 3 and takes two arguments: the source directory and the destination directory.

Prerequisites

• Ensure that Python 3 is installed on your system. You can download it from python.org.
• Make sure the _sync_lip_sync.py script is in your working directory or provide the full path to the script.
• Ensure you have the necessary permissions to read from the source directory and write to the destination directory.

Usage

To run the _sync_lip_sync.py script, open your terminal or command prompt and execute the following command:

python3 _sync_lip_sync.py <source_directory> <destination_directory>

2. CLI Tool for Scoring Audio

Overview

This CLI tool is designed to score audio files based on transcripts provided in a CSV file. It downloads audio files from URLs specified in the CSV, processes them, and outputs the results to a specified CSV file.

Usage

To use the CLI tool, run the following command in your terminal:

```bash
python3 _scoring_audio_competition.py arg1 arg2 arg3 arg4
```

Arguments

• arg1: Input filename (CSV)

  • The path to the input CSV file containing the transcripts and URLs.

• arg2: Column text

  • The name of the column in the CSV file that contains the transcripts.

• arg3: Column URL

  • The name of the column in the CSV file that contains the URLs of the audio files to be downloaded.

• arg4: Output filename (CSV)

  • The path to the output CSV file where the scoring results will be saved.

Detailed Instructions

1. Prepare Input CSV File

   • Create a CSV file with at least two columns: one for the transcripts and one for the URLs of the audio files.
   • Ensure the column names match the values you will provide for arg2 and arg3.

   Example:
   ```csv
   transcript,url
   "This is a sample transcript","http://example.com/audio1.mp3"
   "Another transcript","http://example.com/audio2.mp3"
   ```

2. Run the Tool

   • Open your terminal.
   • Navigate to the directory where _scoring_audio_competition.py is located.
   • Run the following command, replacing input.csv, transcript, url, and output.csv with your actual file and column names:

   ```bash
   python3 _scoring_audio_competition.py input.csv transcript url output.csv
   ```

3. Output

   • The tool will download the audio files from the URLs specified in the input CSV.
   • It will process the audio files and score them based on the provided transcripts.
   • The results will be saved in the output CSV file specified.

Example Command

Here is an example command based on the provided instructions:

```bash
python3 _scoring_audio_competition.py example_input.csv transcript url example_output.csv
```

In this example:

• example_input.csv is the input CSV file containing the transcripts and audio URLs.
• transcript is the name of the column containing the transcripts.
• url is the name of the column containing the audio URLs.
• example_output.csv is the output CSV file where the scoring results will be saved.

Notes

• Ensure you have all necessary dependencies installed before running the script.
• The input CSV file should be well-formatted to avoid any errors during processing.
• The output CSV file will contain the results of the scoring process, which can be used for further analysis.