[[["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):2025-08-18。"],[],[],null,["# Cloud Speech-to-Text On-Prem\n\n| **Private feature** \n| This product is a private feature. The documentation is publicly available but you must [contact Google](https://cloud.google.com/contact) for full access.\n\nOverview\n--------\n\nCloud Speech-to-Text On-Prem enables easy integration of Google speech recognition\ntechnologies into your on-premises solution. The Speech-To-Text (STT) On-Prem solution gives you\nfull control over your infrastructure and protected speech data in order to\nmeet data residency and compliance requirements. This best-in-class machine\nlearning technology gives you access to the next-generation speech recognition\nmodels that are more accurate, smaller in size, and require fewer computing\nresources to run than existing solutions.\n\nSpeech-to-Text On-Prem is a\n[Google Cloud Marketplace](https://cloud.google.com/marketplace/) application\nand can be deployed as a container to any GKE cluster. This gives you\nflexibility and greater control in deployment, whether you decide to deploy on\nGoogle Cloud with GKE or on-premises with Anthos. This lets you to take\nadvantage of the simplicity, agility, and cost-effectiveness of Google's\ncontainer hosting and management across hybrid environments.\n\nReference architecture\n----------------------\n\nDeployment and installation\n---------------------------\n\n1. See the Speech-to-Text On-Prem [pricing page](/speech-to-text/priv/pricing) for an outline of how cost is calculated.\n2. [Contact your seller](https://cloud.google.com/contact) to get access to the solution.\n3. Deploy the application to your cluster.\n4. Configure your chosen client library to access your deployment.\n5. Start transcribing your audio files."]]