[[["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 ES supports rich response messages, allowing you to enhance user interactions with elements beyond plain text, such as images, audio, and interactive buttons.\u003c/p\u003e\n"],["\u003cp\u003eYou can define default responses that apply across all platforms, or customize responses for specific platforms to tailor the user experience.\u003c/p\u003e\n"],["\u003cp\u003eVarious response types are available, including Text, Image, Card, Quick Reply, Synthesize Speech, Play Audio, Transfer Call, and Custom Payload, each with its own specific formatting requirements and limitations.\u003c/p\u003e\n"],["\u003cp\u003eWhen adding responses, parameter references and events can be utilized to provide dynamic content based on user input or runtime triggers.\u003c/p\u003e\n"],["\u003cp\u003eEach response message type has platform-specific limitations on the maximum number of entries, characters, and supported integrations, such as the Dialogflow phone gateway or Google Assistant.\u003c/p\u003e\n"]]],[],null,["# Rich response messages\n\nMany of the\n[integration](/dialogflow/docs/integrations)\nplatforms support platform-specific *rich response messages*.\nThese messages can be used to provide the end-user\nwith more than just text responses.\nThere are a variety of response types to choose from.\nFor example, you can show images, play audio, or provide buttons.\nEach platform supports a subset of the available response types.\n\nWhere to find this data\n-----------------------\n\nWhen building an agent,\nit is most common to use the\nDialogflow ES console ([visit documentation](/dialogflow/docs/console), [open console](https://dialogflow.cloud.google.com)).\nThe instructions below focus on using the console.\nTo access intent response data:\n\n1. Go to the [Dialogflow ES console](https://dialogflow.cloud.google.com).\n2. Select an agent.\n3. Select **Intents** in the left sidebar menu.\n4. Select an intent.\n5. Scroll down to the **Responses** section.\n\nIf you are building an agent using the API instead of the console, see the\n[Intents reference](/dialogflow/docs/reference/common-types#intents).\nThe API field names are similar to the console field names.\nThe instructions below highlight any important differences between the console and the API.\n\nAdd rich response messages\n--------------------------\n\nThe **Responses** section has tabs for each platform,\nincluding a *default* platform.\nYou can define responses for the default platform,\nwhich can be used on all platforms.\n\nYou can define responses for platform-specific tabs,\nwhich only work on the corresponding platforms.\nYou can also opt to use the default responses for a specific platform,\nso you do not need to create duplicate text responses for all platforms.\n\nTo add rich response messages:\n\n1. Select the tab for your desired platform. If the desired platform tab is not shown, click the add *add* button and select it.\n2. Click the **Add Responses** button. A dropdown shows the response types supported by the platform.\n3. Choose the response type. These are described below.\n4. Enter fields for the selected response type.\n5. Add more platform tabs and responses as needed. You can add up to 10 ordered messages in each tab.\n6. Click **Save**.\n\nYou can use\n[parameter references](/dialogflow/docs/intents-actions-parameters#values)\nin your responses to reference parameters provided by the\nend-user or\n[events](/dialogflow/docs/events-overview#param)\nat runtime.\n\nText responses\n--------------\n\nBy default, **Text** responses send a text response to the end-user.\n\nIf text-to-speech is\n[enabled for an agent](/dialogflow/docs/agents-settings#speech)\nor\n[requested by detect intent requests](/dialogflow/docs/how/detect-intent-tts),\nthe supplied text is used to synthesize speech and play the audio.\nIn this case,\nsupplied text can optionally use the\n[Speech Synthesis Markup Language (SSML)](https://cloud.google.com/text-to-speech/docs/ssml).\n\nThe fields are:\n\n- List of text or SSML entries\n\nWhen entering a response,\npress **Shift** + **Enter** to input a newline\nor just **Enter** to input another text response.\n\nThe following limitations apply:\n\n- Max of 300 text entries per text response\n\nImage responses\n---------------\n\n**Image** responses send an image to the end-user.\nThey contain the following fields:\n\n- Publicly accessible URL for the image\n\nCard responses\n--------------\n\n**Card** responses send an image, a card title, a card subtitle,\nand interactive buttons to the end-user.\nThe style of the card varies by platform.\n\nYou can configure buttons to send the end-user to a URL\nor to send pre-configured text to Dialogflow\nas though the end-user provided an expression.\n\nSome of the fields are optional, depending on the platform:\n\n- Publicly accessible URL for an image\n- Card title\n- Card subtitle\n- List of buttons with the following fields:\n - Button title\n - Text to send as end-user expression or URL to open\n\nThe following limitations apply:\n\n- Max of 10 cards per platform and per language for an intent.\n For example, if your agent supports\n English, French, platform X, and platform Y,\n an intent can have at most 40 cards:\n\n - 10 English cards for platform X\n - 10 English cards for platform Y\n - 10 French cards for platform X\n - 10 French cards for platform Y\n\nQuick reply responses\n---------------------\n\n**Quick Reply** responses send a button to the end-user.\nYou can configure buttons to send pre-configured text to Dialogflow\nas though the end-user provided an expression.\n\nThe fields are:\n\n- Button title\n- List of text entries to send as end-user expression\n\nThe following limitations apply:\n\n- Max of one quick reply response per platform and per language for an intent.\n For example, if your agent supports\n English, French, platform X, and platform Y,\n an intent can have at most 4 quick replies:\n\n - 1 English quick reply for platform X\n - 1 English quick reply for platform Y\n - 1 French quick reply for platform X\n - 1 French quick reply for platform Y\n- Max of 10 text entries per quick reply response.\n\n- Max of 20 characters per text entry.\n\nSynthesize speech responses\n---------------------------\n\n**Synthesize Speech** responses are used to\nsynthesize speech from text responses and play the audio.\nThe supplied text can optionally use the\n[Speech Synthesis Markup Language (SSML)](/text-to-speech/docs/ssml).\n\nThe fields are:\n\n- Text or SSML\n\nThe following limitations apply:\n\n- Only supported by the [Dialogflow phone gateway](/dialogflow/es/docs/integrations/phone-gateway) integration\n- Max of 20 synthesize speech responses per intent\n\nPlay audio responses\n--------------------\n\n**Play Audio** responses are used to play audio files.\nAudio files are supplied in a\n[Cloud Storage](/storage/docs)\nbucket.\n\nThe fields are:\n\n- Cloud Storage object URI in `gs://bucket-name/object-name` format.\n\nThe following limitations apply:\n\n- Only supported by the [Dialogflow phone gateway](/dialogflow/es/docs/integrations/phone-gateway) integration\n- Audio file specifications: a single channel (mono) of linear PCM audio (2 bytes / sample) at 8kHz\n- Max of 20 play audio responses per intent\n\nTransfer call responses\n-----------------------\n\n**Transfer Call** responses are used to\ntransfer the caller for a telephony integration.\n\nThe fields are:\n\n- The telephone number to transfer to.\n\nThe following limitations apply:\n\n- Only supported by the [Dialogflow phone gateway](/dialogflow/es/docs/integrations/phone-gateway)\n integration\n\n- Only US telephone numbers are supported\n\nCustom payload responses\n------------------------\n\nSome platforms support a custom payload response\nto handle non-standard, advanced responses.\nThese custom payloads are supplied in a JSON format\ndefined in the platform's documentation.\n\nYou can also send a custom payload to integrations that you develop.\nIt won't be processed by Dialogflow,\nso you need to handle it in your own business logic.\n\nYou can configure a custom payload for multiple platforms.\nTo configure this, use the default platform\nand a JSON format similar to the following: \n\n {\n \"facebook\": {\n \"attachment\": {\n \"type\": \"\",\n \"payload\": {}\n }\n },\n \"slack\": {\n \"text\": \"\",\n \"attachments\": []\n }\n }\n\n| **Note:** Custom payload JSON must be limited to 24 levels of depth.\n\nGoogle Assistant response types\n-------------------------------\n\nThe Google Assistant integration provides many response message types.\nFor more information, see the\n[Google Assistant responses reference](https://developers.google.com/assistant/conversational/responses).\n\nAdditional response types\n-------------------------\n\nOther message types are supported by various platforms.\nYou can see the complete list in the\n[response message REST reference](/dialogflow/docs/reference/rest/v2/projects.agent.intents#Message).\nSee the platform integration documentation for more information."]]