Transcribe speech to text by using the API

Before you begin

Before you can send a request to the Speech-to-Text API, you must have completed the following actions. See the before you begin page for details.

• Enable Speech-to-Text on a GCP project.
  1. Make sure billing is enabled for Speech-to-Text.

• Install the Google Cloud CLI. After installation, initialize the Google Cloud CLI by running the following command:

  gcloud init

  If you're using an external identity provider (IdP), you must first sign in to the gcloud CLI with your federated identity.

• (Optional) Create a new Google Cloud Storage bucket to store your audio data.

Make an audio transcription request

Now you can use Speech-to-Text to transcribe an audio file to text. Use the following code sample to send a recognize REST request to the Speech-to-Text API.

1. Create a JSON request file with the following text, and save it as a sync-request.json plain text file:

   {
     "config": {
         "encoding":"FLAC",
         "sampleRateHertz": 16000,
         "languageCode": "en-US",
         "enableWordTimeOffsets": false
     },
     "audio": {
         "uri":"gs://cloud-samples-tests/speech/brooklyn.flac"
     }
   }
     

   This JSON snippet indicates that the audio file has a FLAC encoding format, a sample rate of 16000 Hz, and that the audio file is stored on Google Cloud Storage at the given URI. The audio file is publicly accessible, so you don't need authentication credentials to access the file.

2. Use curl to make a speech:recognize request, passing it the filename of the JSON request you set up in step 1:

   The sample curl command uses the gcloud auth print-access-token command to get an authentication token.

   curl -s -H "Content-Type: application/json" \
       -H "Authorization: Bearer "$(gcloud auth print-access-token) \
       https://speech.googleapis.com/v1/speech:recognize \
       -d @sync-request.json
     

   Note that to pass a filename to curl you use the -d option (for "data") and precede the filename with an @ sign. This file should be in the same directory in which you execute the curl command.

   You should see a response similar to the following:

   {
     "results": [
       {
         "alternatives": [
           {
             "transcript": "how old is the Brooklyn Bridge",
             "confidence": 0.98267895
           }
         ]
       }
     ]
   }
     

Congratulations! You've sent your first request to Speech-to-Text.

If you receive an error or an empty response from Speech-to-Text, take a look at the troubleshooting and error mitigation steps.