> ## Documentation Index > Fetch the complete documentation index at: https://documentation.dumgum.com/llms.txt > Use this file to discover all available pages before exploring further. # Generate (asynchronous) > Enqueue a conversation to be processed asynchronously ## OpenAPI ````yaml POST /cs/v1/content_creation/conversations/enqueue openapi: 3.1.0 info: title: DumGum version: '2.0' servers: - url: https://api.dumgum.com security: - bearerAuth: [] paths: /cs/v1/content_creation/conversations/enqueue: post: tags: - content-creation summary: Generate (asynchronous) description: Enqueue a conversation to be processed asynchronously operationId: content-creation-conversations-enqueue requestBody: content: application/json: schema: $ref: '#/components/schemas/ContentCreationConversationEnqueueRequest' required: true responses: '204': description: No Content components: schemas: ContentCreationConversationEnqueueRequest: type: object description: Represents a request to enqueue a conversation properties: userProfileId: type: string description: >- A user profile ID; this will represent the profile that will receive the generated reply. personaProfileId: type: string description: >- A persona profile ID; this will represent the profile that our operator will impersonate. language: type: string description: The language used to generate the reply. enum: - EN - EN_GB - FR - FR_BE - RO - NL - ES - DE - DE_CH - DE_AT - IT - ES_LATAM - BG - HE - JA - NL_BE - EN_AU - PT_PT - PT_BR - SV_SE - DA_DK - FI_FI - PL_PL - LT_LT - NB_NO - NN_NO - SL_SI - HU - HU_HU - CS_CZ - EL_GR - EL_GR_LATIN - EL_GR_GREEK - HR_HR - TR_TR - EN_IE - AF_ZA - ZU_ZA - LV_LV - SK_SK - GA_IE - SR_RS - ET_EE - EN_CA - FR_CA - RU_RU - UA_UA additionalLanguages: type: array description: >- A list of additional languages that can be used to generate the reply. Currently, we support only one additional language. items: type: string enum: - EN - EN_GB - FR - FR_BE - RO - NL - ES - DE - DE_CH - DE_AT - IT - ES_LATAM - BG - HE - JA - NL_BE - EN_AU - PT_PT - PT_BR - SV_SE - DA_DK - FI_FI - PL_PL - LT_LT - NB_NO - NN_NO - SL_SI - HU - HU_HU - CS_CZ - EL_GR - EL_GR_LATIN - EL_GR_GREEK - HR_HR - TR_TR - EN_IE - AF_ZA - ZU_ZA - LV_LV - SK_SK - GA_IE - SR_RS - ET_EE - EN_CA - FR_CA - RU_RU - UA_UA maxItems: 1 minItems: 0 userProfileVersion: type: - string - 'null' description: >- Specify the current user profile version. If it differs from the stored version, it will trigger a profile data refresh. personaProfileVersion: type: - string - 'null' description: >- Specify the current persona profile version. If it differs from the stored version, it will trigger a profile data refresh. tags: type: - object - 'null' additionalProperties: type: string description: >- A map of tags to associate with the generated answer. You can use any key-value pair to store additional information along with your request. You can use this to store arbitrary metadata, for events tracking or statistics. testMode: type: - boolean - 'null' description: >- Specify whether the conversation should be processed in test mode. In test mode, you will receive a dummy answer, which is useful for testing purposes. > **You will not be charged** when using test mode. replyParameters: $ref: >- #/components/schemas/ContentCreationQueueConversationReplyParameterSet type: - object - 'null' description: >- A set of parameters that allow you to customize the reply you receive from us, enabling greater flexibility and control over the response format, content, and behavior. required: - language - personaProfileId - userProfileId ContentCreationQueueConversationReplyParameterSet: type: object properties: chatModel: type: - string - 'null' default: chat-2-smart description: > Allows you to set the AI chat model to use for generating the reply. If not specified, the default model will be used. The default model is `dating-smart-1`. **🚨🚨🚨 IMPORTANT NOTE: the default model is subject to change at any time, if you want to stick with a specific model make sure to provide it explicitly.** enum: - chat-2-smart - chat-2-pro bufferSeconds: type: integer format: int32 default: '5' description: >- Allows you to set the AI buffer time (in seconds). This delay enables the AI to wait before generating a response, allowing it to accumulate more messages. If not specified, defaults to `5` seconds. maximum: 180 minimum: 0 maxProcessingTimeSeconds: type: integer format: int32 default: '300' description: > Allows you to set the maximum processing time (in seconds) for a reply. If this time limit is exceeded, the conversation will be dropped, and you will receive an `conversation.dropped` webhook event. If not specified, defaults to `300` seconds. > **WARNING: This value may occasionally be exceeded by several seconds due to various factors.** maximum: 86400 minimum: 300 enableSexualTextContent: type: boolean default: null description: |- Allows our chat models to generate sexual text content. If not specified, defaults to `true`. fixedResponseLength: type: boolean default: false description: >- Force our chat model to strictly respect `aiSentenceLength` and `aiMessageLength` parameters. If not specified, defaults to `false`. sentenceLength: type: - string - 'null' default: null description: >- Allow you to specify the length of the sentences composing the response. enum: - SHORT - REGULAR - LONG messageLength: type: - string - 'null' default: null description: Allow you to specify the length of the response enum: - SHORT - REGULAR - LONG - VERY_LONG personaPersonality: type: - string - 'null' default: null description: Allow you to override the personality given to the persona enum: - SUPPORTIVE - TEASING - CONFIDENT - GEEKY - POETIC - HIGH_ENERGY - INTELLECTUAL - ROMANTIC - SARCASTIC - POSSESSIVE - NATURAL - APPRECIATIVE - PASSIONATE generatePersonality: type: - boolean - 'null' default: null description: >- Automatically generate the personality of the persona profile (SoulEngine). This will incurs an additional cost to the reply. shareablePictures: type: array description: > A list of shareable picture objects that the persona is allowed to send when the user requests an image. Picture sharing is only supported on specific chat models: | Chat Model | Picture Sharing Support | |------------------|-------------------------| | `chat-2-pro` | βœ… Enabled | | `chat-2-smart` | βœ… Enabled | | `dating-pro-1` | ❌ Not Supported | | `dating-smart-1` | ❌ Not Supported | items: $ref: '#/components/schemas/ShareablePicture' shareableVideos: type: array description: > A list of shareable video objects that the persona is allowed to send when the user requests a video. A reply carries at most one medium: either a picture or a video, never both. Video sharing is only supported on specific chat models: | Chat Model | Video Sharing Support | |------------------|-----------------------| | `chat-2-pro` | βœ… Enabled | | `chat-2-smart` | βœ… Enabled | | `dating-pro-1` | ❌ Not Supported | | `dating-smart-1` | ❌ Not Supported | items: $ref: '#/components/schemas/ShareableVideo' emojis: type: string description: > Allows our operator/chat models to add emojis to the reply. | Emoji Frequency | Description | |----------------|-------------| | `FREQUENT` | 50% at least 1 and maybe 1 more emoji if appropriate / 50% 1 if appropriate | | `SOMETIMES` | 75% 1 if appropriate / 25% no emoji | | `RARELY` | 75% no emoji / 25% 1 if appropriate | | `NEVER` | 100% no emoji | enum: - FREQUENT - SOMETIMES - RARELY - NEVER fluencyDegradation: type: - string - 'null' default: null description: >- Allows our chat model to degrade the text content generation quality to improve human-like response. Defaults to `NONE` or `LOW` randomly (50/50). enum: - LOW - MEDIUM - HIGH - NONE multipleMessagesPerReply: type: - boolean - 'null' default: false description: >- Allows our AI to split a long response into multiple shorter messages. If not specified, defaults to `false`. This provides a more natural conversation flow by breaking down lengthy responses. Note that every message sent has its own `answer.created` event. multipleMessagesPerReplyFrequency: type: - string - 'null' default: null description: >- Changes the chances of replying with several messages. Ignored unless multiple messages per reply are enabled β€” either with `multipleMessagesPerReply` on this request, or in your project settings. enum: - VERY_FREQUENT - FREQUENT - OCCASIONAL - RARE questionFrequency: type: number format: double description: >- Define the frequency of questions in the conversation. This can be used to control the pace and engagement of the conversation. The frequency control is best effort, and it may not always be perfectly accurate due to the nature of AI-generated responses. Example: `0.5` will result in 50% of the messages being questions. maximum: 1 minimum: 0 replyTypingDelay: type: string default: INSTANT description: >- Introduces a delay between the answer.processing and answer.created events to simulate human-like typing behavior. This can enhance user experience by making responses feel more natural. See the [Notify Your End Users](/best-practices/notify-your-end-users) use case for implementation example. enum: - INSTANT - FAST - NORMAL icebreakerType: type: - string - 'null' default: null deprecated: true description: > **Deprecated β€” use `engageType` instead.** Still honored for backward compatibility (and accepted on `NUDGE`/`REVIVE` as well, like `engageType`). Specifies the type of icebreaker message to use when starting a conversation. | Type | Description | |------------------|--------------------------------------------------------------------------------| | `AUTO` | Automatically selects appropriate ice-breaker type | | `NO_PHOTO` | Message about user having no photos | | `MISSING_DETAIL` | Message about incomplete profile details | | `MUCH_YOUNGER` | Message addressing significant age difference (user younger) | | `MUCH_OLDER` | Message addressing significant age difference (user older) | | `NEARBY` | Message highlighting close proximity | | `GENERIC` | General conversation starter | | `USER_ONLINE` | Message acknowledging user is currently online | | `USER_OFFLINE` | Message for offline users | | `JUST_JOINED` | Welcome message for new users | | `EROTIC` | The persona will initiate the conversation with a strongly erotic message | | `PHOTO_COMMENT` | The Persona will engage the conversation by commenting the User main picture | | `HAPPY_BIRTHDAY` | Wish the User a happy birthday (valid on `ICEBREAKER`, `NUDGE`, and `REVIVE`) | Icebreaker-only types (`NO_PHOTO`, `MISSING_DETAIL`, `MUCH_YOUNGER`, `MUCH_OLDER`, `NEARBY`, `GENERIC`, `USER_ONLINE`, `USER_OFFLINE`, `JUST_JOINED`, `PHOTO_COMMENT`) require `engage` = `AUTO` or `ICEBREAKER`; if sent for an engage mode they are not valid for, they fall back to `AUTO`. If `PHOTO_COMMENT` is used while the user doesn't have a main picture, the type will default to `AUTO`. enum: - AUTO - NO_PHOTO - MISSING_DETAIL - MUCH_YOUNGER - MUCH_OLDER - NEARBY - GENERIC - USER_ONLINE - USER_OFFLINE - JUST_JOINED - PHOTO_COMMENT - EROTIC - HAPPY_BIRTHDAY engageType: type: - string - 'null' default: null description: > Specifies the angle for an engagement message. Applies across engage modes (ICEBREAKER, NUDGE, REVIVE) per each type's applicability. If a type is sent for an engage mode it is not valid for, it falls back to AUTO. Replaces the deprecated icebreakerType. Two silent fallbacks to AUTO to be aware of: when `engage` is not set the type is validated against `ICEBREAKER`, and `PHOTO_COMMENT` falls back to AUTO when the user profile has no main picture. enum: - AUTO - NO_PHOTO - MISSING_DETAIL - MUCH_YOUNGER - MUCH_OLDER - NEARBY - GENERIC - USER_ONLINE - USER_OFFLINE - JUST_JOINED - PHOTO_COMMENT - EROTIC - HAPPY_BIRTHDAY meetingPolicy: type: - string - 'null' default: null description: > Controls how the Persona handles in-person meeting requests from the user. | Value | Description | |-------|-------------| | `DEFAULT_MODE` | (default when null) Warm refusal using a plausible personal excuse. Uses the stored long-term memory excuse if one is already present. | | `DEFERRED_MEETING` | Expresses genuine desire to meet first, then softly refuses with a personal excuse, and ends on a hopeful note. | | `RAINCHECK` | Declines with a specific, time-bound excuse and explicitly signals that meeting will happen later. Re-engages by showing interest in the user. | | `CHAT_ONLY` | Firm but warm redirect back to the conversation. No implied future possibility of meeting. No personal-life excuses. | | `EAGER_TO_MEET` | Always accepts meeting requests with immediate enthusiasm, treating the meeting as real and imminent. Pure fantasy β€” never refuses, defers, or breaks the illusion. Excluded from the IRL_MEETING_ACCEPTANCE guardrail. | enum: - DEFAULT_MODE - DEFERRED_MEETING - RAINCHECK - CHAT_ONLY - EAGER_TO_MEET engage: type: - string - 'null' default: null description: > Manages engagement messages in conversations. By default, engagement messages are disabled. Set to `AUTO` for context-based engagement type selection. Note: Using specific values instead of `AUTO` will force that engagement type regardless of context. | Value | Description | |--------------|----------------------------------------------------------------------------------------------------------------------------------------------------------| | `AUTO` | Selects best engagement type based on context | | `ICEBREAKER` | Sends an icebreaker message when starting a new conversation. You can specify the `engageType` parameter (the canonical field) to force a specific type; `icebreakerType` is still accepted for backward compatibility. | | `NUDGE` | Sends re-engagement message after inactivity | | `REVIVE` | Sends messages to reactivate dormant conversations | Takes precedence over `action`: when an engagement message is produced, an `action` sent on the same request (such as `PAUSE_CONVERSATION` or `USER_PHOTO_REACTION`) is ignored. Send them on separate requests. enum: - AUTO - ICEBREAKER - NUDGE - REVIVE fictionalDisclosure: type: boolean description: >- When enabled and the AI Suspicion guardrail is triggered, the persona will disclose that it is a fictitious profile instead of denying it. Requires the AI Suspicion guardrail to be on (`guardrails.aiSuspicion`, enabled by default) β€” with it off, this has no effect. disableSafetyFeatures: type: boolean description: >- Allows you to disable the Core Guardian security features for our chat models. You will be responsible for ensuring the content is safe for all users. guardrails: $ref: '#/components/schemas/GuardrailOptionSet' description: >- Selects which Core Guardian guardrails run for this request. **This object replaces your project's Core Guardian settings β€” it is not merged with them.** Any guardrail you leave out falls back to the platform default, not to what you configured in the dashboard, so send the complete set whenever you use this parameter. Ignored when `disableSafetyFeatures` is `true`, which turns every guardrail off. preventAggressiveTone: type: boolean description: >- If set to true, the AI will avoid using an aggressive or confrontational tone, even when the user is being rude, insulting, or hostile. It will remain calm, polite, and non-reactive in all situations, and will not retaliate or escalate the conversation. serviceLoyalty: type: boolean description: > If set to true, the Persona will never validate or agree with complaints about the platform, service, or pricing. Instead, the Persona will deflect warmly in character and occasionally express genuine appreciation for being on the platform. This prevents the Persona from reinforcing negative sentiment that could lead users to disengage. personaProfileOverrides: $ref: '#/components/schemas/PersonaProfileOverrideSet' description: >- Allows you to override a subset of persona profile attributes for the current request vision: $ref: '#/components/schemas/VisionOptionSet' description: > Enable vision features that allow the AI to interpret, analyze, and understand images. Vision capability by model: | Model | Vision Support | |-------------------|----------------| | `chat-2-pro` | βœ… Enabled | | `chat-2-smart` | βœ… Enabled | | `dating-pro-1` | ❌ Not Supported | | `dating-smart-1` | ❌ Not Supported | pictureSharingMode: type: string description: >- Controls how willingly the persona shares photos. NORMAL (default): only shares when explicitly asked. EAGER: shares naturally when the conversation calls for it. enum: - NORMAL - EAGER forcePictureSharing: type: string nullable: true description: >- Force the persona to share a picture in this reply (chat-2 models only). The value "true" (case-insensitive, surrounding whitespace ignored) forces a send and auto-picks from shareablePictures. Any other value is treated as a picture URL to force (one of shareablePictures, or an arbitrary URL analyzed on the fly). Omit or null for no forcing β€” the persona decides naturally. If the forced picture fails moderation it is silently dropped to a text-only reply. forceVideoSharing: type: string description: >- Force the persona to share a video in this reply. The value "true" (case-insensitive, surrounding whitespace ignored) β†’ force and auto-pick from shareableVideos. Any other value is treated as a video URL to force (in shareableVideos, or arbitrary β€” analyzed on the fly). Null β†’ no forcing; the persona decides naturally. A reply carries at most one medium: when `forcePictureSharing` also resolves, the picture wins. chat-2 only. action: $ref: '#/components/schemas/ChatModelAction' description: > Available actions: | Action | Description | |-------------|-------------| | `PAUSE_CONVERSATION` | This feature requests the Persona to send a message indicating that they are temporarily pausing the conversation without specifying a timeline for resuming. This is useful if you disconnect your Personas or limit your Users' messages. Optionally, you can specify a pause duration to be respected on DumGum. During this period, our platform will not respond to any new User messages in the affected conversation. | | `USER_PHOTO_REACTION` | Requests the Persona to send a message reacting to one of the User's photos. Provide a `userPhotoReaction` object with a `source` (`PROFILE_PICTURE` or `URL`). When `source` is `URL`, a `url` pointing to the photo is required; for `PROFILE_PICTURE` the User's profile picture is used and `url` is optional. | postProcessing: $ref: '#/components/schemas/PostProcessingOptionSet' description: >- Allow you to customize the post-processing of the generated content. This can be used to replace specific characters or remove certain elements from the generated text. ShareablePicture: type: object properties: id: type: string description: >- Your identifier for this picture. Keep it stable across requests: we use it to remember which pictures have already been shared in the conversation, so a changing id makes the persona offer the same picture again. maxLength: 128 minLength: 1 url: type: string description: >- URL we fetch the picture from. Maximum 512 characters. HTTPS is strongly recommended. maxLength: 512 minLength: 1 caption: type: string description: >- A custom caption of the picture, this can be used to override the default caption generated by our AI. maxLength: 100 minLength: 1 required: - id - url ShareableVideo: type: object properties: id: type: string description: >- Your identifier for this video. Keep it stable across requests: we use it to remember which videos have already been shared in the conversation, so a changing id makes the persona offer the same video again. maxLength: 128 minLength: 1 url: type: string description: >- URL we fetch the video from. Maximum 512 characters. HTTPS is strongly recommended. maxLength: 512 minLength: 1 caption: type: string description: >- A custom caption of the video, this can be used to override the default caption generated by our AI. maxLength: 100 minLength: 1 required: - id - url GuardrailOptionSet: type: object properties: maliciousContent: type: boolean default: false description: Enable/Disable Malicious Content guardrail maliciousContentOptionSet: $ref: '#/components/schemas/GuardrailOptions' description: >- Overrides `answer` and `banDurations` for the Malicious Content guardrail. Only applies when `maliciousContent` is `true`. aiSuspicion: type: boolean default: true description: Enable/Disable AI Suspicion guardrail aiSuspicionOptionSet: $ref: '#/components/schemas/GuardrailOptions' description: >- Overrides `answer` and `banDurations` for the AI Suspicion guardrail. Only applies when `aiSuspicion` is `true`. underageDetection: type: boolean default: true description: Enable/Disable Underage Detection guardrail underageDetectionOptionSet: $ref: '#/components/schemas/GuardrailOptions' description: >- Overrides `answer` and `banDurations` for the Underage Detection guardrail. Only applies when `underageDetection` is `true`. unknownLanguage: type: boolean default: true description: Enable/Disable Unknown Language guardrail unknownLanguageOptionSet: $ref: '#/components/schemas/GuardrailOptions' description: >- Overrides `answer` and `banDurations` for the Unknown Language guardrail. Only applies when `unknownLanguage` is `true`. messageRepetition: type: boolean default: true description: Enable/Disable Message Repetition guardrail messageRepetitionOptionSet: $ref: '#/components/schemas/GuardrailOptions' description: >- Overrides `answer` and `banDurations` for the Message Repetition guardrail. Only applies when `messageRepetition` is `true`. prohibitedIllegalContent: type: boolean default: false deprecated: true description: >- [Deprecated: Is not used and will be removed in the future] Enables Prohibited Illegal Content guardrail prohibitedIllegalContentOptionSet: $ref: '#/components/schemas/GuardrailOptions' deprecated: true description: This guardrail is deprecated and will be removed in the future. dangerousDrugUse: type: boolean default: false deprecated: true description: >- [Deprecated: Is not used and will be removed in the future] Enables Dangerous Drug Use guardrail dangerousDrugUseOptionSet: $ref: '#/components/schemas/GuardrailOptions' deprecated: true description: This guardrail is deprecated and will be removed in the future. PersonaProfileOverrideSet: type: object properties: sexualDrive: type: string description: > This parameter adjusts the Persona’s sexual appetite and likelihood to engage in sexting. | Value | Description | |-------------|--------------------------------------------------------------------------------------------| | `NONE` | The Persona will never send sexually explicit replies. | | `LOW` | The Persona will rarely initiate or respond to sexual topics, even if prompted. | | `NORMAL` | The Persona may engage in sexting if the conversation naturally leads there. | | `HIGH` | The Persona will respond positively and proactively to sexual cues from the User faster. | | `VERY_HIGH` | The Persona will initiate or escalate sexting as soon as the User shows any sexual intent. | enum: - VERY_HIGH - HIGH - NORMAL - LOW - NONE VisionOptionSet: type: object properties: userProfilePictureAnalysis: type: boolean default: false description: Enable user profile's picture analysis. personaProfilePictureAnalysis: type: boolean default: false description: Enable persona profile's picture analysis. sharedPicturesAnalysis: type: boolean default: false description: >- Enable user's shared pictures analysis. The pictures are analysed on their own, but comparing them against the user's profile picture (so the persona can tell whether it is the same person) also requires `userProfilePictureAnalysis`. sharedVideosAnalysis: type: boolean default: false description: Enable user's shared videos analysis. shareablePicturesAnalysis: type: boolean description: >- Enable persona's shareable pictures analysis, this will allows our chat model to understand each image it is sharing. shareableVideosAnalysis: type: boolean default: false description: >- Enable persona's shareable videos analysis, this will allows our chat model to understand each video it is sharing. Videos carrying a caption are never analyzed. ChatModelAction: type: object properties: type: type: string description: The type of the action. enum: - PAUSE_CONVERSATION - USER_PHOTO_REACTION pauseConversation: $ref: '#/components/schemas/PauseConversation' description: Optional pause conversation parameters. userPhotoReaction: $ref: '#/components/schemas/UserPhotoReaction' required: - type PostProcessingOptionSet: type: object properties: greekRewrite: type: boolean default: false description: >- Used for Greek answer generations. Replace ";" by "?" and accentuated characters by their non-accentuated equivalents. russianRewrite: type: boolean default: false description: >- Used for Russian answer generations. Remove quotation marks the model places around individual slang words or short informal expressions, while leaving genuine quoted sentences intact. GuardrailOptions: type: object properties: answer: type: boolean description: >- Whether the persona still sends a final message when this guardrail bans the user. Defaults to `true`. banDurations: type: array description: >- Escalating ban durations for this guardrail, **in seconds** β€” up to 5 values. The first applies to the user's first offence, the next to the following one; the last value repeats for every further offence. Defaults to `[7200, 43200, 86400, 172800, 3153600000]` (2h, 12h, 24h, 48h, permanent), or `[3153600000]` for the Underage guardrail. A permanent ban is the sentinel `3153600000` (about a century). The dashboard takes these durations in hours and converts them for you. items: type: integer format: int64 maxItems: 5 minItems: 0 PauseConversation: type: object properties: duration: type: integer format: int32 description: >- Optional duration of the pause in seconds (maximum 12 hours). By default, the conversation will not be paused on DumGum side. maximum: 43200 minimum: 1 UserPhotoReaction: type: object properties: source: type: string description: The source of the photo. enum: - PROFILE_PICTURE - URL url: type: - string - 'null' default: null description: The URL of the photo. Required when `source` is set to `URL`. caption: type: - string - 'null' default: null description: >- Optional caption describing the photo. When set (non-blank), it is used as the photo description instead of the automatic vision analysis. required: - source securitySchemes: bearerAuth: type: http description: >- Bearer authentication header of the form `Bearer `, where `` is an access key. Example: `Authorization: Bearer sk-proj-XXXXXXXXX` scheme: bearer bearerFormat: JWT | Access Key ````