Google Speech to Text API not working for audio files longer than one minute

Question

I am trying to convert an audio file with the following attributes using Google Speech to Text API

1) Raw File 2) Sample Rate: 16000 3) Bit Rate: 16 4) Audio Type: mono

I am using the following Python Code to get the text file

service_request = service.speech().asyncrecognize(
        body={
            'config': {
                'encoding': 'LINEAR16',  # raw 16-bit signed LE samples
                'sampleRate': 16000,  # 16 khz
                'languageCode': 'en-US',  # a BCP-47 language tag
            },
            'audio': {
                'uri':'gs://xxxxxxxxx/english.raw'
                }
            })
    response = service_request.execute()
    print(json.dumps(response))

This logic works well, but for some reason the transcription only returns one minute worth of recording and ignores the rest.

Why is this happening, can someone help me out?

MattDMo MattDMo · Accepted Answer · 2017-01-14T22:10:57

It's difficult to tell from your code, but you must be submitting a Synchronous Request. According to the docs, length is limited to ~60 seconds. Asynchronous Requests accept up to approximately 80 minutes. Read through the APIs and Reference docs to learn how to properly structure your requests for the API you are using.

Google Speech to Text API not working for audio files longer than one minute

2 Answers