Recognizers

The Cloud Speech-to-Text API V2 supports a Google Cloud resource called recognizers. Recognizers represent stored and reusable recognition configuration. You can use them to logically group together transcriptions or traffic for your application.

Before you begin

Sign in to your Google Cloud account. If you're new to Google Cloud, create an account to evaluate how our products perform in real-world scenarios. New customers also get $300 in free credits to run, test, and deploy workloads.

Set up a Google Cloud console project.

Set up a project

Click to:

• Create or select a project.
• Enable the Speech-to-Text API for that project.

You can view and manage these resources at any time in the Google Cloud console.

Install the Google Cloud CLI.

Note: If you installed the gcloud CLI previously, make sure you have the latest version by running gcloud components update.

To initialize the gcloud CLI, run the following command:

gcloud init

Set up a Google Cloud console project.

Set up a project

Click to:

• Create or select a project.
• Enable the Speech-to-Text API for that project.

You can view and manage these resources at any time in the Google Cloud console.

Install the Google Cloud CLI.

Note: If you installed the gcloud CLI previously, make sure you have the latest version by running gcloud components update.

To initialize the gcloud CLI, run the following command:

gcloud init

Client libraries can use Application Default Credentials to easily authenticate with Google APIs and send requests to those APIs. With Application Default Credentials, you can test your application locally and deploy it without changing the underlying code. For more information, see Authenticate for using client libraries.

1. If you're using a local shell, then create local authentication credentials for your user account:

   gcloud auth application-default login

   You don't need to do this if you're using Cloud Shell.

   If an authentication error is returned, and you are using an external identity provider (IdP), confirm that you have signed in to the gcloud CLI with your federated identity.

Also ensure you have installed the client library.

Understand recognizers

Recognizers are configurable, reusable recognition configurations. Creating recognizers with frequently used recognition configuration helps to simplify and reduce the size of recognition requests.

The core element of a recognizer is its default configuration. This is the configuration for every recognition request that this recognizer performs. You can override this default per request. Keep the default configuration for features you need across requests for a given recognizer, while overriding specific features for specific requests.

Reuse recognizers as often as possible. Creating one for each request dramatically increases the latency of your application and consumes your resource quotas. Create them infrequently during integration and setup, then reuse them for recognition requests.

Create recognizers

Here is an example of creating a recognizer that can be used to send recognition requests:

Python

import os

from google.cloud.speech_v2 import SpeechClient
from google.cloud.speech_v2.types import cloud_speech

PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT")


def create_recognizer(recognizer_id: str) -> cloud_speech.Recognizer:
    """Сreates a recognizer with an unique ID and default recognition configuration.
    Args:
        recognizer_id (str): The unique identifier for the recognizer to be created.
    Returns:
        cloud_speech.Recognizer: The created recognizer object with configuration.
    """
    # Instantiates a client
    client = SpeechClient()

    request = cloud_speech.CreateRecognizerRequest(
        parent=f"projects/{PROJECT_ID}/locations/global",
        recognizer_id=recognizer_id,
        recognizer=cloud_speech.Recognizer(
            default_recognition_config=cloud_speech.RecognitionConfig(
                language_codes=["en-US"], model="long"
            ),
        ),
    )
    # Sends the request to create a recognizer and waits for the operation to complete
    operation = client.create_recognizer(request=request)
    recognizer = operation.result()

    print("Created Recognizer:", recognizer.name)
    return recognizer

Use an existing recognizer to send requests

Here is an example of sending multiple recognition requests using the same recognizer:

Python

import os

from google.cloud.speech_v2 import SpeechClient
from google.cloud.speech_v2.types import cloud_speech

PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT")


def transcribe_reuse_recognizer(
    audio_file: str,
    recognizer_id: str,
) -> cloud_speech.RecognizeResponse:
    """Transcribe an audio file using an existing recognizer.
    Args:
        audio_file (str): Path to the local audio file to be transcribed.
            Example: "resources/audio.wav"
        recognizer_id (str): The ID of the existing recognizer to be used for transcription.
    Returns:
        cloud_speech.RecognizeResponse: The response containing the transcription results.
    """
    # Instantiates a client
    client = SpeechClient()

    # Reads a file as bytes
    with open(audio_file, "rb") as f:
        audio_content = f.read()

    request = cloud_speech.RecognizeRequest(
        recognizer=f"projects/{PROJECT_ID}/locations/global/recognizers/{recognizer_id}",
        content=audio_content,
    )

    # Transcribes the audio into text
    response = client.recognize(request=request)

    for result in response.results:
        print(f"Transcript: {result.alternatives[0].transcript}")

    return response

Enable features in a recognizer

Recognizers can be used to enable various features in recognition, such as automatic punctuation or profanity filtering.

Here is an example of enabling automatic punctuation in a recognizer, which enables automatic punctuation in the recognition request using this recognizer:

Note: Samples throughout the documentation repeatedly illustrate creating recognizers. However, you should create them infrequently and reuse them often.

Python

from google.cloud.speech_v2 import SpeechClient
from google.cloud.speech_v2.types import cloud_speech

from google.api_core.exceptions import NotFound

# Instantiates a client
client = SpeechClient()

# TODO(developer): Update and un-comment below line
# PROJECT_ID = "your-project-id"
# recognizer_id = "id-recognizer"
recognizer_name = (
    f"projects/{PROJECT_ID}/locations/global/recognizers/{recognizer_id}"
)
try:
    # Use an existing recognizer
    recognizer = client.get_recognizer(name=recognizer_name)
    print("Using existing Recognizer:", recognizer.name)
except NotFound:
    # Create a new recognizer
    request = cloud_speech.CreateRecognizerRequest(
        parent=f"projects/{PROJECT_ID}/locations/global",
        recognizer_id=recognizer_id,
        recognizer=cloud_speech.Recognizer(
            default_recognition_config=cloud_speech.RecognitionConfig(
                auto_decoding_config=cloud_speech.AutoDetectDecodingConfig(),
                language_codes=["en-US"],
                model="latest_long",
                features=cloud_speech.RecognitionFeatures(
                    enable_automatic_punctuation=True,
                ),
            ),
        ),
    )
    operation = client.create_recognizer(request=request)
    recognizer = operation.result()
    print("Created Recognizer:", recognizer.name)

# Reads a file as bytes
with open(audio_file, "rb") as f:
    audio_content = f.read()

request = cloud_speech.RecognizeRequest(
    recognizer=f"projects/{PROJECT_ID}/locations/global/recognizers/{recognizer_id}",
    content=audio_content,
)

# Transcribes the audio into text
response = client.recognize(request=request)

for result in response.results:
    print(f"Transcript: {result.alternatives[0].transcript}")

Override recognizer features in recognition requests

Here is an example of enabling multiple features in a recognizer, but disabling automatic punctuation for this recognition request:

Python

import os

from google.cloud.speech_v2 import SpeechClient
from google.cloud.speech_v2.types import cloud_speech
from google.protobuf.field_mask_pb2 import FieldMask

PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT")


def transcribe_override_recognizer(
    audio_file: str,
    recognizer_id: str,
) -> cloud_speech.RecognizeResponse:
    """Transcribe an audio file using an existing recognizer with overridden settings for the recognition request.
    Args:
        audio_file (str): Path to the local audio file to be transcribed.
            Example: "resources/audio.wav"
        recognizer_id (str): The unique ID of the recognizer to be used for transcription.
    Returns:
        cloud_speech.RecognizeResponse: The response containing the transcription results.
    """
    # Instantiates a client
    client = SpeechClient()

    request = cloud_speech.CreateRecognizerRequest(
        parent=f"projects/{PROJECT_ID}/locations/global",
        recognizer_id=recognizer_id,
        recognizer=cloud_speech.Recognizer(
            default_recognition_config=cloud_speech.RecognitionConfig(
                auto_decoding_config=cloud_speech.AutoDetectDecodingConfig(),
                language_codes=["en-US"],
                model="latest_long",
                features=cloud_speech.RecognitionFeatures(
                    enable_automatic_punctuation=True,
                    enable_word_time_offsets=True,
                ),
            ),
        ),
    )

    operation = client.create_recognizer(request=request)
    recognizer = operation.result()

    print("Created Recognizer:", recognizer.name)

    # Reads a file as bytes
    with open(audio_file, "rb") as f:
        audio_content = f.read()

    request = cloud_speech.RecognizeRequest(
        recognizer=f"projects/{PROJECT_ID}/locations/global/recognizers/{recognizer_id}",
        config=cloud_speech.RecognitionConfig(
            features=cloud_speech.RecognitionFeatures(
                enable_word_time_offsets=False,
            ),
        ),
        config_mask=FieldMask(paths=["features.enable_word_time_offsets"]),
        content=audio_content,
    )

    # Transcribes the audio into text
    response = client.recognize(request=request)

    for result in response.results:
        print(f"Transcript: {result.alternatives[0].transcript}")

    return response

Send requests without recognizers

Recognizers are optional in recognition requests. To make a request without a recognizer, use the recognizer resource ID _ in the location you are making a request. Here is an example:

Python

import os

from google.cloud.speech_v2 import SpeechClient
from google.cloud.speech_v2.types import cloud_speech

PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT")


def quickstart_v2(audio_file: str) -> cloud_speech.RecognizeResponse:
    """Transcribe an audio file.
    Args:
        audio_file (str): Path to the local audio file to be transcribed.
    Returns:
        cloud_speech.RecognizeResponse: The response from the recognize request, containing
        the transcription results
    """
    # Reads a file as bytes
    with open(audio_file, "rb") as f:
        audio_content = f.read()

    # Instantiates a client
    client = SpeechClient()

    config = cloud_speech.RecognitionConfig(
        auto_decoding_config=cloud_speech.AutoDetectDecodingConfig(),
        language_codes=["en-US"],
        model="long",
    )

    request = cloud_speech.RecognizeRequest(
        recognizer=f"projects/{PROJECT_ID}/locations/global/recognizers/_",
        config=config,
        content=audio_content,
    )

    # Transcribes the audio into text
    response = client.recognize(request=request)

    for result in response.results:
        print(f"Transcript: {result.alternatives[0].transcript}")

    return response

Clean up

To avoid incurring charges to your Google Cloud account for the resources used on this page, follow these steps.

1. Optional: Revoke the authentication credentials that you created, and delete the local credential file.

   gcloud auth application-default revoke

2. Optional: Revoke credentials from the gcloud CLI.

   gcloud auth revoke

Console

Caution: Deleting a project has the following effects:

• Everything in the project is deleted. If you used an existing project for the tasks in this document, when you delete it, you also delete any other work you've done in the project.
• Custom project IDs are lost. When you created this project, you might have created a custom project ID that you want to use in the future. To preserve the URLs that use the project ID, such as an appspot.com URL, delete selected resources inside the project instead of deleting the whole project.

If you plan to explore multiple architectures, tutorials, or quickstarts, reusing projects can help you avoid exceeding project quota limits.

In the Google Cloud console, go to the Manage resources page.

Go to Manage resources

In the project list, select the project that you want to delete, and then click Delete.

In the dialog, type the project ID, and then click Shut down to delete the project.

gcloud

Caution: Deleting a project has the following effects:

• Everything in the project is deleted. If you used an existing project for the tasks in this document, when you delete it, you also delete any other work you've done in the project.
• Custom project IDs are lost. When you created this project, you might have created a custom project ID that you want to use in the future. To preserve the URLs that use the project ID, such as an appspot.com URL, delete selected resources inside the project instead of deleting the whole project.

If you plan to explore multiple architectures, tutorials, or quickstarts, reusing projects can help you avoid exceeding project quota limits.

Delete a Google Cloud project:

gcloud projects delete PROJECT_ID

What's next

• Learn how to transcribe short audio files.
• Learn how to transcribe streaming audio.
• Learn how to transcribe long audio files.
• For best performance, accuracy, and other tips, see the best practices documentation.