[[["易于理解","easyToUnderstand","thumb-up"],["解决了我的问题","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["很难理解","hardToUnderstand","thumb-down"],["信息或示例代码不正确","incorrectInformationOrSampleCode","thumb-down"],["没有我需要的信息/示例","missingTheInformationSamplesINeed","thumb-down"],["翻译问题","translationIssue","thumb-down"],["其他","otherDown","thumb-down"]],["最后更新时间 (UTC):2025-09-04。"],[[["\u003cp\u003eThis page guides developers through setting up a project to use the Speech-to-Text service, which involves project creation, API enablement, client library installation, and credential authentication.\u003c/p\u003e\n"],["\u003cp\u003eDevelopers must create a project using the GDC console or the gdcloud CLI, to organize Speech-to-Text resources and you need your project ID for API calls.\u003c/p\u003e\n"],["\u003cp\u003eTo utilize speech recognition features, users need the AI Speech Developer role, granted by the Project IAM Admin.\u003c/p\u003e\n"],["\u003cp\u003eUsing Python client libraries is recommended for making API calls to Speech-to-Text and you need to ensure the correct version is installed.\u003c/p\u003e\n"],["\u003cp\u003eEnvironment variables, such as service account keys, can be defined in Python scripts to facilitate API interactions and the usage of those variables.\u003c/p\u003e\n"]]],[],null,["# Set up a speech recognition project\n\nThis page helps developers set up a project to use the Speech-to-Text service.\nThis process includes creating a project, enabling the Speech-to-Text API,\ninstalling client libraries, defining environment variables, and authenticating\nyour credentials. If you are new to Vertex AI, [learn more about speech recognition features](/distributed-cloud/hosted/docs/latest/gdch/application/ao-user/vertex-ai-stt).\n\nYou set up a speech recognition project using the GDC console and\ngdcloud CLI as follows:\n\n- **GDC console**: Enable the Speech-to-Text API and view the service status and endpoint.\n- **The gdcloud CLI**: Configure service accounts to interact with the Speech-to-Text API, install client libraries, and authenticate API requests.\n\nCreate a project\n----------------\n\nCreating a speech recognition project within your Distributed Cloud\n[resource hierarchy](/distributed-cloud/hosted/docs/latest/gdch/resources/resource-hierarchy)\norganizes your Speech-to-Text resources, which include collaborators,\nenabled APIs, monitoring tools, billing information, authentication credentials,\nand access controls.\n\nTo create your project, see [Set up a project for Vertex AI](/distributed-cloud/hosted/docs/latest/gdch/application/ao-user/vertex-ai-set-up-project).\nYou need your project ID when making API calls.\n| **Tip:** Improve security, resource management, and cost tracking by isolating your experimental, testing, and production workloads in separate Distributed Cloud projects.\n\nRequest developer permissions\n-----------------------------\n\nYou must have the AI Speech Developer role in your project to\naccess speech recognition features and generate an API token for request\nauthentication and authorization.\n\nAsk your Project IAM Admin to grant the AI Speech Developer\n(`ai-speech-developer`) role to your user or service account\nwithin your project namespace. For information about this role, see\n[Prepare IAM permissions](/distributed-cloud/hosted/docs/latest/gdch/application/ao-user/vertex-ai-ao-permissions).\n\nEnable the Speech-to-Text API\n-----------------------------\n\nYou must [enable the Speech-to-Text pre-trained API](/distributed-cloud/hosted/docs/latest/gdch/application/ao-user/vertex-ai-enable-pre-trained-apis)\nfor your project. If enabled, you can [view the service status and endpoint for the Speech-to-Text pre-trained API](/distributed-cloud/hosted/docs/latest/gdch/application/ao-user/vertex-ai-api-status).\n\nInstall client libraries\n------------------------\n\nClient libraries are available for the Python programming language. We recommend\nusing these client libraries to make calls to the Speech-to-Text API\nbecause they make it easier to access APIs.\n\n[Install the Speech-to-Text client library](/distributed-cloud/hosted/docs/latest/gdch/application/ao-user/vertex-ai-install-libraries)\nand follow these steps to ensure you have the correct version:\n\n1. Check if the Speech-to-Text client library is installed and obtain\n the version number:\n\n pip freeze | grep speech\n\n If the client library is already installed, you obtain an output similar\n to the following example: \n\n google-cloud-speech==2.15.0\n\n The version number you obtain must match the client library at the\n following endpoint: \n\n https://\u003cvar translate=\"no\"\u003eGDC_URL\u003c/var\u003e/.well-known/static/client-libraries\n\n Replace \u003cvar translate=\"no\"\u003eGDC_URL\u003c/var\u003e with the\n URL of your organization in GDC.\n2. If the version numbers don't match, uninstall the client library:\n\n pip uninstall google-cloud-speech\n\n3. If you uninstalled the Speech-to-Text client library, you must\n [reinstall it](/distributed-cloud/hosted/docs/latest/gdch/application/ao-user/vertex-ai-install-libraries)\n by specifying the filename corresponding to your operating system.\n\nSet your environment variables\n------------------------------\n\nAfter installing the Speech-to-Text client library, you can interact\nwith the API from a Python script.\n\nIf you [set up a service account](/distributed-cloud/hosted/docs/latest/gdch/application/ao-user/vertex-ai-set-up-project#set-up-service)\nin your project to make authorized API calls programmatically, you can define\nenvironment variables in the Python script to access values such as the service\naccount keys when running.\n\nFollow these steps to set required environment variables on a Python script:\n\n1. [Create a JupyterLab notebook](/distributed-cloud/hosted/docs/latest/gdch/application/ao-user/vertex-ai-workbench#create-notebook)\n to interact with the Speech-to-Text pre-trained API.\n\n2. Create a Python script on the JupyterLab notebook.\n\n3. Add the following code to the Python script:\n\n import os\n\n os.environ[\"GOOGLE_APPLICATION_CREDENTIALS\"] = \"\u003cvar translate=\"no\"\u003eAPPLICATION_DEFAULT_CREDENTIALS_FILENAME\u003c/var\u003e\"\n\n Replace \u003cvar translate=\"no\"\u003eAPPLICATION_DEFAULT_CREDENTIALS_FILENAME\u003c/var\u003e with\n the name of the JSON file that contains [the service account keys you created](/distributed-cloud/hosted/docs/latest/gdch/application/ao-user/vertex-ai-set-up-project#set-up-service)\n in the project, such as `my-service-key.json`.\n4. Save the Python script with a name, such as `speech.py`.\n\n5. Run the Python script to set the environment variables:\n\n python \u003cvar translate=\"no\"\u003e\u003cspan class=\"devsite-syntax-n\"\u003eSCRIPT_NAME\u003c/span\u003e\u003c/var\u003e\n\n Replace \u003cvar translate=\"no\"\u003eSCRIPT_NAME\u003c/var\u003e with the name you gave to your\n Python script, such as `speech.py`.\n\n| **Note:** Keep the script open when using the environment variables from Python or getting an authentication token.\n\nSet up authentication\n---------------------\n\nBefore you can start using the Speech-to-Text API, you must authenticate\nyour client credentials and request account access to your project resources.\nFor more information, see [Authenticate API requests](/distributed-cloud/hosted/docs/latest/gdch/application/ao-user/vertex-ai-api-auth)."]]