Pre-Recorded Audio Transcription

The Deepgram Pre-Recorded Clients allows you to request transcripts for pre-recorded audio. To request a transcript for a pre-recorded particular audio file, you’ll use one of the following functions depending on your audio source:

• transcribe_file
• transcribe_url

Pre-recorded Transcription Parameters

You can pass a Buffer or URL to a file to transcribe. Here’s how to construct each:

Sending a URL

1
source = {'url': URL_TO_AUDIO_FILE}

Sending a Buffer

Open a file and send the buffer returned.

1
with open(PATH_TO_FILE, 'rb') as audio:
2
  source = {'buffer': audio}

Pre-recorded Transcription Options

Additional transcription options can be provided for pre-recorded transcriptions. They are provided as an object as the second parameter of the transcription.prerecorded function. Each of these parameters maps to a feature in the Deepgram API. Reference the features documentation to learn the appropriate features for your request.

Pre-recorded Transcription Example Request

With the source you chose above, call the transcription function and provide any additional options as an object.

1
try:
2
    # STEP 1 Create a Deepgram client using the DEEPGRAM_API_KEY from environment variables
3
    deepgram = DeepgramClient()
4
5
    # STEP 2 Call the transcribe_url method on the prerecorded class
6
    options = PrerecordedOptions(
7
        model="nova-3",
8
        smart_format=True,
9
        summarize="v2",
10
    )
11
    url_response = deepgram.listen.rest.v("1").transcribe_url(
12
        AUDIO_URL, options
13
    )
14
    print(url_response)
15
16
except Exception as e:
17
    print(f"Exception: {e}")

Increasing the Timeout for Processing Larger Files

You might need to increase the default HTTP Timeout setting for larger files. The example increases the time to 300 seconds (or 5 mins).

1
# this will increase the timeout to 300 seconds or 5 minutes
2
response = deepgram.listen.rest.v("1").transcribe_file(
3
  payload, options, timeout=httpx.Timeout(300.0, connect=10.0)
4
)

Where To Find Additional Examples

The SDK repository has a good collection of live audio transcription examples. The README contains links to them. Each example below attempts to provide different options for transcribing an audio source.

Some Examples

• Threaded Client using an Audio File - examples/speech-to-text/rest/file
• Threaded Client from a URL - examples/speech-to-text/rest/url

If the Async Client suits your use case better:

• Async Client from a URL - examples/speech-to-text/rest/async_url