Generate transcript

Textual can generate a transcript from an audio file. To do this, use the get_audio_transcript method.

To generate a transcript:

from tonic_textual.audio_api import TextualAudio

textual = TextualAudio()

transcription = textual.get_audio_transcript('path_to_file.mp3')

This generates a transcription_result.

It contains:

• The full text of the transcription.

• The detected language.

• A list of audio segments. Each segment is some portion of the transcription with start and end times in milliseconds.

It looks something like this:

{

    "text": "Thank you for calling First National Bank. My name is Steve. How may I assist you today? Hello, Steve. I have a problem with my credit card statement.",
    "segments": [
        {
            "start": 0,
            "end": 4300.0001,
            "id": 0,
            "text": " Thank you for calling First National Bank. My name is Steve. How may I assist you today?",
            "words": [
                {
                    "start": 0,
                    "end": 839.9999,
                    "word": "Thank"
                },
                {
                    "start": 839.9999,
                    "end": 899.9999,
                    "word": "you"
                },
                {
                    "start": 899.9999,
                    "end": 1120,
                    "word": "for"
                },
                {
                    "start": 1120,
                    "end": 1259.9999,
                    "word": "calling"
                },
                {
                    "start": 1259.9999,
                    "end": 1580,
                    "word": "First"
                },
                {
                    "start": 1580,
                    "end": 1879.9999,
                    "word": "National"
                },
                {
                    "start": 1879.9999,
                    "end": 2220,
                    "word": "Bank"
                },
                {
                    "start": 2440,
                    "end": 2559.9999,
                    "word": "My"
                },
                {
                    "start": 2559.9999,
                    "end": 2720,
                    "word": "name"
                },
                {
                    "start": 2720,
                    "end": 3259.9999,
                    "word": "is"
                },
                {
                    "start": 3259.9999,
                    "end": 3259.9999,
                    "word": "Steve"
                },
                {
                    "start": 3339.9999,
                    "end": 3460,
                    "word": "How"
                },
                {
                    "start": 3460,
                    "end": 3559.9999,
                    "word": "may"
                },
                {
                    "start": 3559.9999,
                    "end": 3859.9998,
                    "word": "I"
                },
                {
                    "start": 3859.9998,
                    "end": 3859.9998,
                    "word": "assist"
                },
                {
                    "start": 3859.9998,
                    "end": 4000,
                    "word": "you"
                },
                {
                    "start": 4000,
                    "end": 4300.0001,
                    "word": "today"
                }
            ]
        },
        {
            "start": 5280.0002,
            "end": 7780.0002,
            "id": 1,
            "text": " Hello, Steve. I have a problem with my credit card statement.",
            "words": [
                {
                    "start": 5280.0002,
                    "end": 5659.9998,
                    "word": "Hello"
                },
                {
                    "start": 5659.9998,
                    "end": 5900,
                    "word": "Steve"
                },
                {
                    "start": 5960,
                    "end": 6179.9998,
                    "word": "I"
                },
                {
                    "start": 6179.9998,
                    "end": 6300.0001,
                    "word": "have"
                },
                {
                    "start": 6300.0001,
                    "end": 6619.9998,
                    "word": "a"
                },
                {
                    "start": 6619.9998,
                    "end": 6619.9998,
                    "word": "problem"
                },
                {
                    "start": 6619.9998,
                    "end": 6820.0001,
                    "word": "with"
                },
                {
                    "start": 6820.0001,
                    "end": 7119.9998,
                    "word": "my"
                },
                {
                    "start": 7119.9998,
                    "end": 7199.9998,
                    "word": "credit"
                },
                {
                    "start": 7199.9998,
                    "end": 7480,
                    "word": "card"
                },
                {
                    "start": 7480,
                    "end": 7780.0002,
                    "word": "statement"
                }
            ]
        }
    ],
    "language": "english"
}

Additional remarks

When you use the Textual Cloud (https://textual.tonic.ai), file uploads are limited to 25MB or less.

Textual supports the following file types: m4a, mp3, webm, mpga, wav.

For file types such as m4a, make sure that your build of ffmpeg has the necessary libraries.