[[["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。"],[[["\u003cp\u003eDialogflow voice agents utilize Speech-to-Text for speech recognition, which is included in Dialogflow's pricing.\u003c/p\u003e\n"],["\u003cp\u003eWhile Dialogflow automatically selects a speech recognition model, users can manually specify a model suited to their domain and language requirements.\u003c/p\u003e\n"],["\u003cp\u003eThe best-performing models generally include \u003ccode\u003etelephony_short\u003c/code\u003e, \u003ccode\u003etelephony\u003c/code\u003e, \u003ccode\u003ephone_call\u003c/code\u003e, \u003ccode\u003elatest_short\u003c/code\u003e, and \u003ccode\u003ecommand_and_search\u003c/code\u003e, each designed for specific use cases like telephony or non-telephony Dialogflow.\u003c/p\u003e\n"],["\u003cp\u003eUsers can specify a speech recognition model for an agent, flow, or page through the model selection setting or when using the \u003ccode\u003eSessions.detectIntent\u003c/code\u003e or \u003ccode\u003eSessions.streamingDetectIntent\u003c/code\u003e methods, overriding default settings.\u003c/p\u003e\n"],["\u003cp\u003eSpecifying the model with a conversation profile will apply it to Agent Assist and the associated virtual agent for all speech recognition activities.\u003c/p\u003e\n"]]],[],null,["# Speech models\n\nDialogflow voice agents use\n[Speech-to-Text](/speech-to-text/docs)\nfor speech recognition,\nwhich is included in\n[Dialogflow pricing](/dialogflow/pricing).\nDialogflow automatically selects a speech recognition model for you,\nbut you can optionally specify the model.\n\nAvailable models\n----------------\n\nAll available models are listed at\n[Speech-to-Text models](/speech-to-text/docs/transcription-model).\nSelect a model that is best suited to your domain and\n[supports your agent language and speech features](/speech-to-text/docs/speech-to-text-supported-languages).\n\nIf a model is not explicitly [specified](#specify),\nthen Dialogflow auto-selects a model based on\nthe audio configuration in API requests and agent settings.\n\nThe following models typically have the best performance:\n\n- telephony_short (best for telephony Dialogflow)\n- telephony (best for Agent Assist) (also good for telephony Dialogflow when [advanced timeout-based end of speech sensitivity](/dialogflow/cx/docs/concept/agent#advanced-end-of-speech-sensitivity) is enabled)\n- phone_call (good for Agent Assist and telephony Dialogflow)\n- latest_short (best for non-telephony Dialogflow)\n- command_and_search (best for languages where other models are not available)\n\nSpecify a model\n---------------\n\nYou can supply the model for an agent, flow, or page with the [model selection setting](/dialogflow/cx/docs/concept/agent#stt-model-selection).\n\n\u003cbr /\u003e\n\nYou can also supply the model when calling the\n`Sessions.detectIntent` or `Sessions.streamingDetectIntent` methods;\n\n\nGo to the Session API reference \n**Select a protocol and version for the Session reference:**\n\nClose\nor when configuring the [`ConversationProfile`](/dialogflow/es/docs/reference/rpc/google.cloud.dialogflow.v2#google.cloud.dialogflow.v2.ConversationProfile) for [Agent Assist](/agent-assist/docs). Specifying the model in a detect intent or conversation profile API call will override any model selections applied to the agent, flow, or page, unless you enable the [**Override request-level speech\nmodel**](/dialogflow/cx/docs/concept/agent#stt-model-selection) setting. **Note:** If you specify the model with a conversation profile, Agent Assist and the associated virtual agent use this model for all speech recognition."]]