Transcribe long audio files into text

This page demonstrates how to transcribe long audio files (longer than one minute) to text using the Speech-to-Text API and asynchronous speech recognition.

About asynchronous speech recognition

Batch speech recognition starts a long-running audio processing operation. Use asynchronous speech recognition to transcribe audio that is longer than 60 seconds. For shorter audio, synchronous speech recognition is faster and simpler. The upper limit for asynchronous speech recognition is 480 minutes (8 hours).

Batch speech recognition is only able to transcribe audio stored in Cloud Storage. The transcription output can be either provided inline in the response (for single-file batch recognition requests) or written to Cloud Storage.

The batch recognition request returns an Operation that contains information about the ongoing recognition processing of your request. You can poll the operation to know when the operation is complete and transcripts are available.

Before you begin

1. 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.

2. In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

   Note: If you don't plan to keep the resources that you create in this procedure, create a project instead of selecting an existing project. After you finish these steps, you can delete the project, removing all resources associated with the project.

   Go to project selector

3. Make sure that billing is enabled for your Google Cloud project.

4. Enable the Speech-to-Text APIs.

   Enable the APIs

5. Make sure that you have the following role or roles on the project: Cloud Speech Administrator

   Check for the roles

   1. In the Google Cloud console, go to the IAM page.

      Go to IAM
   2. Select the project.

   3. In the Principal column, find all rows that identify you or a group that you're included in. To learn which groups you're included in, contact your administrator.

   4. For all rows that specify or include you, check the Role colunn to see whether the list of roles includes the required roles.

   Grant the roles

   1. In the Google Cloud console, go to the IAM page.

      Go to IAM
   2. Select the project.
   3. Click Grant access.

   4. In the New principals field, enter your user identifier. This is typically the email address for a Google Account.

   5. In the Select a role list, select a role.
   6. To grant additional roles, click Add another role and add each additional role.
   7. Click Save.
6. Install the Google Cloud CLI.

7. To initialize the gcloud CLI, run the following command:

   gcloud init

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

8. In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

   Note: If you don't plan to keep the resources that you create in this procedure, create a project instead of selecting an existing project. After you finish these steps, you can delete the project, removing all resources associated with the project.

   Go to project selector

9. Make sure that billing is enabled for your Google Cloud project.

10. Enable the Speech-to-Text APIs.

    Enable the APIs

11. Make sure that you have the following role or roles on the project: Cloud Speech Administrator

    Check for the roles

    1. In the Google Cloud console, go to the IAM page.

       Go to IAM
    2. Select the project.

    3. In the Principal column, find all rows that identify you or a group that you're included in. To learn which groups you're included in, contact your administrator.

    4. For all rows that specify or include you, check the Role colunn to see whether the list of roles includes the required roles.

    Grant the roles

    1. In the Google Cloud console, go to the IAM page.

       Go to IAM
    2. Select the project.
    3. Click Grant access.

    4. In the New principals field, enter your user identifier. This is typically the email address for a Google Account.

    5. In the Select a role list, select a role.
    6. To grant additional roles, click Add another role and add each additional role.
    7. Click Save.
12. Install the Google Cloud CLI.

13. To initialize the gcloud CLI, run the following command:

    gcloud init

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

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.

14. 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.

Also ensure you have installed the client library.

Enable access to Cloud Storage

Speech-to-Text uses a service account to access your files in Cloud Storage. By default, the service account has access to Cloud Storage files in the same project.

The service account email address is the following:

[e-mail]

In order to transcribe Cloud Storage files in another project, you can give this service account the Speech-to-Text Service Agent role in the other project:

gcloud projects add-iam-policy-binding PROJECT_ID \
    --member=serviceAccount:[e-mail] \
    --role=roles/speech.serviceAgent

More information about project IAM policy is available at Manage access to projects, folders, and organizations.

You can also give the service account more granular access by giving it permission to a specific Cloud Storage bucket:

gcloud storage buckets add-iam-policy-binding gs://BUCKET_NAME \
    --member=serviceAccount:[e-mail] \
    --role=roles/storage.admin

More information about managing access to Cloud Storage is available at Create and Manage access control lists in the Cloud Storage documentation.

Perform batch recognition with inline results

Here is an example of performing batch speech recognition on an audio file in Cloud Storage and reading the transcription results inline from the response:

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_batch_gcs_input_inline_output_v2(
    audio_uri: str,
) -> cloud_speech.BatchRecognizeResults:
    """Transcribes audio from a Google Cloud Storage URI using the Google Cloud Speech-to-Text API.
        The transcription results are returned inline in the response.
    Args:
        audio_uri (str): The Google Cloud Storage URI of the input audio file.
            E.g., gs://[BUCKET]/[FILE]
    Returns:
        cloud_speech.BatchRecognizeResults: The response containing the transcription results.
    """
    # Instantiates a client
    client = SpeechClient()

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

    file_metadata = cloud_speech.BatchRecognizeFileMetadata(uri=audio_uri)

    request = cloud_speech.BatchRecognizeRequest(
        recognizer=f"projects/{PROJECT_ID}/locations/global/recognizers/_",
        config=config,
        files=[file_metadata],
        recognition_output_config=cloud_speech.RecognitionOutputConfig(
            inline_response_config=cloud_speech.InlineOutputConfig(),
        ),
    )

    # Transcribes the audio into text
    operation = client.batch_recognize(request=request)

    print("Waiting for operation to complete...")
    response = operation.result(timeout=120)

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

    return response.results[audio_uri].transcript

Perform batch recognition and write results to Cloud Storage

Here is an example of performing batch speech recognition on an audio file in Cloud Storage and reading the transcription results from the output file in Cloud Storage. Note that the file written to Cloud Storage is a BatchRecognizeResults message in JSON format:

Python

import os

import re

from google.cloud import storage
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_batch_gcs_input_gcs_output_v2(
    audio_uri: str,
    gcs_output_path: str,
) -> cloud_speech.BatchRecognizeResults:
    """Transcribes audio from a Google Cloud Storage URI using the Google Cloud Speech-to-Text API.
    The transcription results are stored in another Google Cloud Storage bucket.
    Args:
        audio_uri (str): The Google Cloud Storage URI of the input audio file.
            E.g., gs://[BUCKET]/[FILE]
        gcs_output_path (str): The Google Cloud Storage bucket URI where the output transcript will be stored.
            E.g., gs://[BUCKET]
    Returns:
        cloud_speech.BatchRecognizeResults: The response containing the URI of the transcription results.
    """
    # Instantiates a client
    client = SpeechClient()

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

    file_metadata = cloud_speech.BatchRecognizeFileMetadata(uri=audio_uri)

    request = cloud_speech.BatchRecognizeRequest(
        recognizer=f"projects/{PROJECT_ID}/locations/global/recognizers/_",
        config=config,
        files=[file_metadata],
        recognition_output_config=cloud_speech.RecognitionOutputConfig(
            gcs_output_config=cloud_speech.GcsOutputConfig(
                uri=gcs_output_path,
            ),
        ),
    )

    # Transcribes the audio into text
    operation = client.batch_recognize(request=request)

    print("Waiting for operation to complete...")
    response = operation.result(timeout=120)

    file_results = response.results[audio_uri]

    print(f"Operation finished. Fetching results from {file_results.uri}...")
    output_bucket, output_object = re.match(
        r"gs://([^/]+)/(.*)", file_results.uri
    ).group(1, 2)

    # Instantiates a Cloud Storage client
    storage_client = storage.Client()

    # Fetch results from Cloud Storage
    bucket = storage_client.bucket(output_bucket)
    blob = bucket.blob(output_object)
    results_bytes = blob.download_as_bytes()
    batch_recognize_results = cloud_speech.BatchRecognizeResults.from_json(
        results_bytes, ignore_unknown_fields=True
    )

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

    return batch_recognize_results

Perform batch recognition on multiple files

Here is an example of performing batch speech recognition on multiple audio files in Cloud Storage and reading the transcription results from the output files in Cloud Storage:

Python

import os
import re
from typing import List

from google.cloud import storage
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_batch_multiple_files_v2(
    audio_uris: List[str],
    gcs_output_path: str,
) -> cloud_speech.BatchRecognizeResponse:
    """Transcribes audio from multiple Google Cloud Storage URIs using the Google Cloud Speech-to-Text API.
    The transcription results are stored in another Google Cloud Storage bucket.
    Args:
        audio_uris (List[str]): The list of Google Cloud Storage URIs of the input audio files.
            E.g., ["gs://[BUCKET]/[FILE]", "gs://[BUCKET]/[FILE]"]
        gcs_output_path (str): The Google Cloud Storage bucket URI where the output transcript will be stored.
            E.g., gs://[BUCKET]
    Returns:
        cloud_speech.BatchRecognizeResponse: The response containing the URIs of the transcription results.
    """
    # Instantiates a client
    client = SpeechClient()

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

    files = [cloud_speech.BatchRecognizeFileMetadata(uri=uri) for uri in audio_uris]

    request = cloud_speech.BatchRecognizeRequest(
        recognizer=f"projects/{PROJECT_ID}/locations/global/recognizers/_",
        config=config,
        files=files,
        recognition_output_config=cloud_speech.RecognitionOutputConfig(
            gcs_output_config=cloud_speech.GcsOutputConfig(
                uri=gcs_output_path,
            ),
        ),
    )

    # Transcribes the audio into text
    operation = client.batch_recognize(request=request)

    print("Waiting for operation to complete...")
    response = operation.result(timeout=120)

    print("Operation finished. Fetching results from:")
    for uri in audio_uris:
        file_results = response.results[uri]
        print(f"  {file_results.uri}...")
        output_bucket, output_object = re.match(
            r"gs://([^/]+)/(.*)", file_results.uri
        ).group(1, 2)

        # Instantiates a Cloud Storage client
        storage_client = storage.Client()

        # Fetch results from Cloud Storage
        bucket = storage_client.bucket(output_bucket)
        blob = bucket.blob(output_object)
        results_bytes = blob.download_as_bytes()
        batch_recognize_results = cloud_speech.BatchRecognizeResults.from_json(
            results_bytes, ignore_unknown_fields=True
        )

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

    return response

Enable dynamic batching on batch recognition

Dynamic batching enables lower cost transcription for higher latency. This feature is only available for batch recognition.

Here is an example of performing batch recognition on an audio file in Cloud Storage with dynamic batching enabled:

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_batch_dynamic_batching_v2(
    audio_uri: str,
) -> cloud_speech.BatchRecognizeResults:
    """Transcribes audio from a Google Cloud Storage URI using dynamic batching.
    Args:
        audio_uri (str): The Cloud Storage URI of the input audio.
        E.g., gs://[BUCKET]/[FILE]
    Returns:
        cloud_speech.BatchRecognizeResults: The response containing the transcription results.
    """
    # Instantiates a client
    client = SpeechClient()

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

    file_metadata = cloud_speech.BatchRecognizeFileMetadata(uri=audio_uri)

    request = cloud_speech.BatchRecognizeRequest(
        recognizer=f"projects/{PROJECT_ID}/locations/global/recognizers/_",
        config=config,
        files=[file_metadata],
        recognition_output_config=cloud_speech.RecognitionOutputConfig(
            inline_response_config=cloud_speech.InlineOutputConfig(),
        ),
        processing_strategy=cloud_speech.BatchRecognizeRequest.ProcessingStrategy.DYNAMIC_BATCHING,
    )

    # Transcribes the audio into text
    operation = client.batch_recognize(request=request)

    print("Waiting for operation to complete...")
    response = operation.result(timeout=120)

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

    return response.results[audio_uri].transcript

Override recognition features per file

Batch recognition by default uses the same recognition configuration for each file in the batch recognition request. If different files require different configuration or features, configuration can be overridden per file using the config field in the [BatchRecognizeFileMetadata][batch-file-metadata-grpc] message. See the recognizers documentation for an example overriding recognition features.

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

• See the reference documentation for batch recognition.
• Learn how to transcribe streaming audio.
• Practice transcribing short audio files.
• Transcribe audio files using Chirp.
• For best performance, accuracy, and other tips, see the best practices documentation.