retell-sdk 4.56.0 → 4.58.0

package/src/resources/call.ts

@@ -216,7 +216,7 @@ export interface PhoneCallResponse {
   data_storage_setting?: 'everything' | 'everything_except_pii' | 'basic_attributes_only' | null;
 
   /**
-   * The reason for the disconnection of the call. Read details desciption about
+   * The reason for the disconnection of the call. Read detailed description about
    * reasons listed here at
    * [Disconnection Reason Doc](/reliability/debug-call-disconnect#understanding-disconnection-reasons).
    */
@@ -377,6 +377,15 @@ export interface PhoneCallResponse {
     | PhoneCallResponse.ToolCallResultUtterance
     | PhoneCallResponse.DtmfUtterance
   >;
+
+  /**
+   * The destination number or identifier where the call was transferred to. Only
+   * populated when the disconnection reason was `call_transfer`. Can be a phone
+   * number or a SIP URI. SIP URIs are prefixed with "sip:" and may include a
+   * ";transport=..." portion (if transport is known) where the transport type can be
+   * "tls", "tcp", "udp", or "auto".
+   */
+  transfer_destination?: string | null;
 }
 
 export namespace PhoneCallResponse {
@@ -1122,7 +1131,7 @@ export interface WebCallResponse {
   data_storage_setting?: 'everything' | 'everything_except_pii' | 'basic_attributes_only' | null;
 
   /**
-   * The reason for the disconnection of the call. Read details desciption about
+   * The reason for the disconnection of the call. Read detailed description about
    * reasons listed here at
    * [Disconnection Reason Doc](/reliability/debug-call-disconnect#understanding-disconnection-reasons).
    */
@@ -1277,6 +1286,15 @@ export interface WebCallResponse {
     | WebCallResponse.ToolCallResultUtterance
     | WebCallResponse.DtmfUtterance
   >;
+
+  /**
+   * The destination number or identifier where the call was transferred to. Only
+   * populated when the disconnection reason was `call_transfer`. Can be a phone
+   * number or a SIP URI. SIP URIs are prefixed with "sip:" and may include a
+   * ";transport=..." portion (if transport is known) where the transport type can be
+   * "tls", "tcp", "udp", or "auto".
+   */
+  transfer_destination?: string | null;
 }
 
 export namespace WebCallResponse {
@@ -2135,6 +2153,12 @@ export interface CallCreatePhoneCallParams {
    */
   to_number: string;
 
+  /**
+   * Override configuration for agent, retell LLM, or conversation flow settings for
+   * a specific call.
+   */
+  agent_override?: CallCreatePhoneCallParams.AgentOverride;
+
   /**
    * Add optional custom SIP headers to the call.
    */
@@ -2176,6 +2200,826 @@ export interface CallCreatePhoneCallParams {
   retell_llm_dynamic_variables?: { [key: string]: unknown };
 }
 
+export namespace CallCreatePhoneCallParams {
+  /**
+   * Override configuration for agent, retell LLM, or conversation flow settings for
+   * a specific call.
+   */
+  export interface AgentOverride {
+    /**
+     * Override agent configuration settings. Any properties specified here will
+     * override the base agent configuration for this call.
+     */
+    agent?: AgentOverride.Agent;
+
+    /**
+     * Override conversation flow configuration settings. Only applicable when using
+     * conversation flow as the response engine. Supported attributes - model_choice,
+     * model_temperature, knowledge_base_ids, kb_config, start_speaker,
+     * begin_after_user_silence_ms.
+     */
+    conversation_flow?: AgentOverride.ConversationFlow;
+
+    /**
+     * Override Retell LLM configuration settings. Only applicable when using Retell
+     * LLM as the response engine. Supported attributes - model, s2s_model,
+     * model_temperature, knowledge_base_ids, kb_config, start_speaker,
+     * begin_after_user_silence_ms, begin_message.
+     */
+    retell_llm?: AgentOverride.RetellLlm;
+  }
+
+  export namespace AgentOverride {
+    /**
+     * Override agent configuration settings. Any properties specified here will
+     * override the base agent configuration for this call.
+     */
+    export interface Agent {
+      /**
+       * The name of the agent. Only used for your own reference.
+       */
+      agent_name?: string | null;
+
+      /**
+       * If set to true, DTMF input will be accepted and processed. If false, any DTMF
+       * input will be ignored. Default to true.
+       */
+      allow_user_dtmf?: boolean;
+
+      /**
+       * If set, will add ambient environment sound to the call to make experience more
+       * realistic. Currently supports the following options:
+       *
+       * - `coffee-shop`: Coffee shop ambience with people chatting in background.
+       *   [Listen to Ambience](https://retell-utils-public.s3.us-west-2.amazonaws.com/coffee-shop.wav)
+       *
+       * - `convention-hall`: Convention hall ambience, with some echo and people
+       *   chatting in background.
+       *   [Listen to Ambience](https://retell-utils-public.s3.us-west-2.amazonaws.com/convention-hall.wav)
+       *
+       * - `summer-outdoor`: Summer outdoor ambience with cicada chirping.
+       *   [Listen to Ambience](https://retell-utils-public.s3.us-west-2.amazonaws.com/summer-outdoor.wav)
+       *
+       * - `mountain-outdoor`: Mountain outdoor ambience with birds singing.
+       *   [Listen to Ambience](https://retell-utils-public.s3.us-west-2.amazonaws.com/mountain-outdoor.wav)
+       *
+       * - `static-noise`: Constant static noise.
+       *   [Listen to Ambience](https://retell-utils-public.s3.us-west-2.amazonaws.com/static-noise.wav)
+       *
+       * - `call-center`: Call center work noise.
+       *   [Listen to Ambience](https://retell-utils-public.s3.us-west-2.amazonaws.com/call-center.wav)
+       *
+       * Set to `null` to remove ambient sound from this agent.
+       */
+      ambient_sound?:
+        | 'coffee-shop'
+        | 'convention-hall'
+        | 'summer-outdoor'
+        | 'mountain-outdoor'
+        | 'static-noise'
+        | 'call-center'
+        | null;
+
+      /**
+       * If set, will control the volume of the ambient sound. Value ranging from [0,2].
+       * Lower value means quieter ambient sound, while higher value means louder ambient
+       * sound. If unset, default value 1 will apply.
+       */
+      ambient_sound_volume?: number;
+
+      /**
+       * Only applicable when enable_backchannel is true. Controls how often the agent
+       * would backchannel when a backchannel is possible. Value ranging from [0,1].
+       * Lower value means less frequent backchannel, while higher value means more
+       * frequent backchannel. If unset, default value 0.8 will apply.
+       */
+      backchannel_frequency?: number;
+
+      /**
+       * Only applicable when enable_backchannel is true. A list of words that the agent
+       * would use as backchannel. If not set, default backchannel words will apply.
+       * Check out
+       * [backchannel default words](/agent/interaction-configuration#backchannel) for
+       * more details. Note that certain voices do not work too well with certain words,
+       * so it's recommended to experiment before adding any words.
+       */
+      backchannel_words?: Array<string> | null;
+
+      /**
+       * If set, will delay the first message by the specified amount of milliseconds, so
+       * that it gives user more time to prepare to take the call. Valid range is [0,
+       * 5000]. If not set or set to 0, agent will speak immediately. Only applicable
+       * when agent speaks first.
+       */
+      begin_message_delay_ms?: number;
+
+      /**
+       * Provide a customized list of keywords to bias the transcriber model, so that
+       * these words are more likely to get transcribed. Commonly used for names, brands,
+       * street, etc.
+       */
+      boosted_keywords?: Array<string> | null;
+
+      /**
+       * Granular setting to manage how Retell stores sensitive data (transcripts,
+       * recordings, logs, etc.). This replaces the deprecated
+       * `opt_out_sensitive_data_storage` field.
+       *
+       * - `everything`: Store all data including transcripts, recordings, and logs.
+       * - `everything_except_pii`: Store data without PII when PII is detected.
+       * - `basic_attributes_only`: Store only basic attributes; no
+       *   transcripts/recordings/logs. If not set, default value of "everything" will
+       *   apply.
+       */
+      data_storage_setting?: 'everything' | 'everything_except_pii' | 'basic_attributes_only';
+
+      /**
+       * If set, determines what denoising mode to use. Default to noise-cancellation.
+       */
+      denoising_mode?: 'noise-cancellation' | 'noise-and-background-speech-cancellation';
+
+      /**
+       * Controls whether the agent would backchannel (agent interjects the speaker with
+       * phrases like "yeah", "uh-huh" to signify interest and engagement). Backchannel
+       * when enabled tends to show up more in longer user utterances. If not set, agent
+       * will not backchannel.
+       */
+      enable_backchannel?: boolean;
+
+      /**
+       * If users stay silent for a period after agent speech, end the call. The minimum
+       * value allowed is 10,000 ms (10 s). By default, this is set to 600000 (10 min).
+       */
+      end_call_after_silence_ms?: number;
+
+      /**
+       * When TTS provider for the selected voice is experiencing outages, we would use
+       * fallback voices listed here for the agent. Voice id and the fallback voice ids
+       * must be from different TTS providers. The system would go through the list in
+       * order, if the first one in the list is also having outage, it would use the next
+       * one. Set to null to remove voice fallback for the agent.
+       */
+      fallback_voice_ids?: Array<string> | null;
+
+      /**
+       * Controls how sensitive the agent is to user interruptions. Value ranging from
+       * [0,1]. Lower value means it will take longer / more words for user to interrupt
+       * agent, while higher value means it's easier for user to interrupt agent. If
+       * unset, default value 1 will apply. When this is set to 0, agent would never be
+       * interrupted.
+       */
+      interruption_sensitivity?: number;
+
+      /**
+       * Specifies what language (and dialect) the speech recognition will operate in.
+       * For instance, selecting `en-GB` optimizes speech recognition for British
+       * English. If unset, will use default value `en-US`. Select `multi` for
+       * multilingual support, currently this supports Spanish and English.
+       */
+      language?:
+        | 'en-US'
+        | 'en-IN'
+        | 'en-GB'
+        | 'en-AU'
+        | 'en-NZ'
+        | 'de-DE'
+        | 'es-ES'
+        | 'es-419'
+        | 'hi-IN'
+        | 'fr-FR'
+        | 'fr-CA'
+        | 'ja-JP'
+        | 'pt-PT'
+        | 'pt-BR'
+        | 'zh-CN'
+        | 'ru-RU'
+        | 'it-IT'
+        | 'ko-KR'
+        | 'nl-NL'
+        | 'nl-BE'
+        | 'pl-PL'
+        | 'tr-TR'
+        | 'th-TH'
+        | 'vi-VN'
+        | 'ro-RO'
+        | 'bg-BG'
+        | 'ca-ES'
+        | 'da-DK'
+        | 'fi-FI'
+        | 'el-GR'
+        | 'hu-HU'
+        | 'id-ID'
+        | 'no-NO'
+        | 'sk-SK'
+        | 'sv-SE'
+        | 'multi';
+
+      /**
+       * Maximum allowed length for the call, will force end the call if reached. The
+       * minimum value allowed is 60,000 ms (1 min), and maximum value allowed is
+       * 7,200,000 (2 hours). By default, this is set to 3,600,000 (1 hour).
+       */
+      max_call_duration_ms?: number;
+
+      /**
+       * If set to true, will normalize the some part of text (number, currency, date,
+       * etc) to spoken to its spoken form for more consistent speech synthesis
+       * (sometimes the voice synthesize system itself might read these wrong with the
+       * raw text). For example, it will convert "Call my number 2137112342 on Jul 5th,
+       * 2024 for the $24.12 payment" to "Call my number two one three seven one one two
+       * three four two on july fifth, twenty twenty four for the twenty four dollars
+       * twelve cents payment" before starting audio generation.
+       */
+      normalize_for_speech?: boolean;
+
+      /**
+       * Whether this agent opts in for signed URLs for public logs and recordings. When
+       * enabled, the generated URLs will include security signatures that restrict
+       * access and automatically expire after 24 hours.
+       */
+      opt_in_signed_url?: boolean;
+
+      /**
+       * Configuration for PII scrubbing from transcripts and recordings.
+       */
+      pii_config?: Agent.PiiConfig;
+
+      /**
+       * Post call analysis data to extract from the call. This data will augment the
+       * pre-defined variables extracted in the call analysis. This will be available
+       * after the call ends.
+       */
+      post_call_analysis_data?: Array<
+        | Agent.StringAnalysisData
+        | Agent.EnumAnalysisData
+        | Agent.BooleanAnalysisData
+        | Agent.NumberAnalysisData
+      > | null;
+
+      /**
+       * The model to use for post call analysis. Default to gpt-4o-mini.
+       */
+      post_call_analysis_model?:
+        | 'gpt-4o'
+        | 'gpt-4o-mini'
+        | 'gpt-4.1'
+        | 'gpt-4.1-mini'
+        | 'gpt-4.1-nano'
+        | 'gpt-5'
+        | 'gpt-5-mini'
+        | 'gpt-5-nano'
+        | 'claude-4.5-sonnet'
+        | 'claude-4.0-sonnet'
+        | 'claude-3.7-sonnet'
+        | 'claude-3.5-haiku'
+        | 'gemini-2.0-flash'
+        | 'gemini-2.0-flash-lite'
+        | 'gemini-2.5-flash'
+        | 'gemini-2.5-flash-lite';
+
+      /**
+       * A list of words / phrases and their pronunciation to be used to guide the audio
+       * synthesize for consistent pronunciation. Currently only supported for English &
+       * 11labs voices. Set to null to remove pronunciation dictionary from this agent.
+       */
+      pronunciation_dictionary?: Array<Agent.PronunciationDictionary> | null;
+
+      /**
+       * If set, controls how many times agent would remind user when user is
+       * unresponsive. Must be a non negative integer. If unset, default value of 1 will
+       * apply (remind once). Set to 0 to disable agent from reminding.
+       */
+      reminder_max_count?: number;
+
+      /**
+       * If set (in milliseconds), will trigger a reminder to the agent to speak if the
+       * user has been silent for the specified duration after some agent speech. Must be
+       * a positive number. If unset, default value of 10000 ms (10 s) will apply.
+       */
+      reminder_trigger_ms?: number;
+
+      /**
+       * The Response Engine to attach to the agent. It is used to generate responses for
+       * the agent. You need to create a Response Engine first before attaching it to an
+       * agent.
+       */
+      response_engine?:
+        | Agent.ResponseEngineRetellLm
+        | Agent.ResponseEngineCustomLm
+        | Agent.ResponseEngineConversationFlow;
+
+      /**
+       * Controls how responsive is the agent. Value ranging from [0,1]. Lower value
+       * means less responsive agent (wait more, respond slower), while higher value
+       * means faster exchanges (respond when it can). If unset, default value 1 will
+       * apply.
+       */
+      responsiveness?: number;
+
+      /**
+       * If set, the phone ringing will last for the specified amount of milliseconds.
+       * This applies for both outbound call ringtime, and call transfer ringtime.
+       * Default to 30000 (30 s). Valid range is [5000, 90000].
+       */
+      ring_duration_ms?: number;
+
+      /**
+       * If set, determines whether speech to text should focus on latency or accuracy.
+       * Default to fast mode.
+       */
+      stt_mode?: 'fast' | 'accurate';
+
+      user_dtmf_options?: Agent.UserDtmfOptions | null;
+
+      /**
+       * If set, determines the vocabulary set to use for transcription. This setting
+       * only applies for English agents, for non English agent, this setting is a no-op.
+       * Default to general.
+       */
+      vocab_specialization?: 'general' | 'medical';
+
+      /**
+       * Unique voice id used for the agent. Find list of available voices and their
+       * preview in Dashboard.
+       */
+      voice_id?: string;
+
+      /**
+       * Optionally set the voice model used for the selected voice. Currently only
+       * elevenlab voices have voice model selections. Set to null to remove voice model
+       * selection, and default ones will apply. Check out the dashboard for details on
+       * each voice model.
+       */
+      voice_model?:
+        | 'eleven_turbo_v2'
+        | 'eleven_flash_v2'
+        | 'eleven_turbo_v2_5'
+        | 'eleven_flash_v2_5'
+        | 'eleven_multilingual_v2'
+        | 'tts-1'
+        | 'gpt-4o-mini-tts'
+        | null;
+
+      /**
+       * Controls speed of voice. Value ranging from [0.5,2]. Lower value means slower
+       * speech, while higher value means faster speech rate. If unset, default value 1
+       * will apply.
+       */
+      voice_speed?: number;
+
+      /**
+       * Controls how stable the voice is. Value ranging from [0,2]. Lower value means
+       * more stable, and higher value means more variant speech generation. Currently
+       * this setting only applies to `11labs` voices. If unset, default value 1 will
+       * apply.
+       */
+      voice_temperature?: number;
+
+      /**
+       * If this option is set, the call will try to detect voicemail in the first 3
+       * minutes of the call. Actions defined (hangup, or leave a message) will be
+       * applied when the voicemail is detected. Set this to null to disable voicemail
+       * detection.
+       */
+      voicemail_option?: Agent.VoicemailOption | null;
+
+      /**
+       * If set, will control the volume of the agent. Value ranging from [0,2]. Lower
+       * value means quieter agent speech, while higher value means louder agent speech.
+       * If unset, default value 1 will apply.
+       */
+      volume?: number;
+
+      /**
+       * The timeout for the webhook in milliseconds. If not set, default value of 10000
+       * will apply.
+       */
+      webhook_timeout_ms?: number;
+
+      /**
+       * The webhook for agent to listen to call events. See what events it would get at
+       * [webhook doc](/features/webhook). If set, will binds webhook events for this
+       * agent to the specified url, and will ignore the account level webhook for this
+       * agent. Set to `null` to remove webhook url from this agent.
+       */
+      webhook_url?: string | null;
+    }
+
+    export namespace Agent {
+      /**
+       * Configuration for PII scrubbing from transcripts and recordings.
+       */
+      export interface PiiConfig {
+        /**
+         * List of PII categories to scrub from transcripts and recordings.
+         */
+        categories: Array<
+          | 'person_name'
+          | 'address'
+          | 'email'
+          | 'phone_number'
+          | 'ssn'
+          | 'passport'
+          | 'driver_license'
+          | 'credit_card'
+          | 'bank_account'
+          | 'password'
+          | 'pin'
+          | 'medical_id'
+          | 'date_of_birth'
+        >;
+
+        /**
+         * The processing mode for PII scrubbing. Currently only post-call is supported.
+         */
+        mode: 'post_call';
+      }
+
+      export interface StringAnalysisData {
+        /**
+         * Description of the variable.
+         */
+        description: string;
+
+        /**
+         * Name of the variable.
+         */
+        name: string;
+
+        /**
+         * Type of the variable to extract.
+         */
+        type: 'string';
+
+        /**
+         * Examples of the variable value to teach model the style and syntax.
+         */
+        examples?: Array<string>;
+      }
+
+      export interface EnumAnalysisData {
+        /**
+         * The possible values of the variable, must be non empty array.
+         */
+        choices: Array<string>;
+
+        /**
+         * Description of the variable.
+         */
+        description: string;
+
+        /**
+         * Name of the variable.
+         */
+        name: string;
+
+        /**
+         * Type of the variable to extract.
+         */
+        type: 'enum';
+      }
+
+      export interface BooleanAnalysisData {
+        /**
+         * Description of the variable.
+         */
+        description: string;
+
+        /**
+         * Name of the variable.
+         */
+        name: string;
+
+        /**
+         * Type of the variable to extract.
+         */
+        type: 'boolean';
+      }
+
+      export interface NumberAnalysisData {
+        /**
+         * Description of the variable.
+         */
+        description: string;
+
+        /**
+         * Name of the variable.
+         */
+        name: string;
+
+        /**
+         * Type of the variable to extract.
+         */
+        type: 'number';
+      }
+
+      export interface PronunciationDictionary {
+        /**
+         * The phonetic alphabet to be used for pronunciation.
+         */
+        alphabet: 'ipa' | 'cmu';
+
+        /**
+         * Pronunciation of the word in the format of a IPA / CMU pronunciation.
+         */
+        phoneme: string;
+
+        /**
+         * The string of word / phrase to be annotated with pronunciation.
+         */
+        word: string;
+      }
+
+      export interface ResponseEngineRetellLm {
+        /**
+         * id of the Retell LLM Response Engine.
+         */
+        llm_id: string;
+
+        /**
+         * type of the Response Engine.
+         */
+        type: 'retell-llm';
+
+        /**
+         * Version of the Retell LLM Response Engine.
+         */
+        version?: number | null;
+      }
+
+      export interface ResponseEngineCustomLm {
+        /**
+         * LLM websocket url of the custom LLM.
+         */
+        llm_websocket_url: string;
+
+        /**
+         * type of the Response Engine.
+         */
+        type: 'custom-llm';
+      }
+
+      export interface ResponseEngineConversationFlow {
+        /**
+         * ID of the Conversation Flow Response Engine.
+         */
+        conversation_flow_id: string;
+
+        /**
+         * type of the Response Engine.
+         */
+        type: 'conversation-flow';
+
+        /**
+         * Version of the Conversation Flow Response Engine.
+         */
+        version?: number | null;
+      }
+
+      export interface UserDtmfOptions {
+        /**
+         * The maximum number of digits allowed in the user's DTMF (Dual-Tone
+         * Multi-Frequency) input per turn. Once this limit is reached, the input is
+         * considered complete and a response will be generated immediately.
+         */
+        digit_limit?: number | null;
+
+        /**
+         * A single key that signals the end of DTMF input. Acceptable values include any
+         * digit (0–9), the pound/hash symbol (#), or the asterisk (\*).
+         */
+        termination_key?: string | null;
+
+        /**
+         * The time (in milliseconds) to wait for user DTMF input before timing out. The
+         * timer resets with each digit received.
+         */
+        timeout_ms?: number;
+      }
+
+      /**
+       * If this option is set, the call will try to detect voicemail in the first 3
+       * minutes of the call. Actions defined (hangup, or leave a message) will be
+       * applied when the voicemail is detected. Set this to null to disable voicemail
+       * detection.
+       */
+      export interface VoicemailOption {
+        action:
+          | VoicemailOption.VoicemailActionPrompt
+          | VoicemailOption.VoicemailActionStaticText
+          | VoicemailOption.VoicemailActionHangup;
+      }
+
+      export namespace VoicemailOption {
+        export interface VoicemailActionPrompt {
+          /**
+           * The prompt used to generate the text to be spoken when the call is detected to
+           * be in voicemail.
+           */
+          text: string;
+
+          type: 'prompt';
+        }
+
+        export interface VoicemailActionStaticText {
+          /**
+           * The text to be spoken when the call is detected to be in voicemail.
+           */
+          text: string;
+
+          type: 'static_text';
+        }
+
+        export interface VoicemailActionHangup {
+          type: 'hangup';
+        }
+      }
+    }
+
+    /**
+     * Override conversation flow configuration settings. Only applicable when using
+     * conversation flow as the response engine. Supported attributes - model_choice,
+     * model_temperature, knowledge_base_ids, kb_config, start_speaker,
+     * begin_after_user_silence_ms.
+     */
+    export interface ConversationFlow {
+      /**
+       * If set, the AI will begin the conversation after waiting for the user for the
+       * duration (in milliseconds) specified by this attribute. This only applies if the
+       * agent is configured to wait for the user to speak first. If not set, the agent
+       * will wait indefinitely for the user to speak.
+       */
+      begin_after_user_silence_ms?: number | null;
+
+      /**
+       * Knowledge base configuration for RAG retrieval.
+       */
+      kb_config?: ConversationFlow.KBConfig;
+
+      /**
+       * Knowledge base IDs for RAG (Retrieval-Augmented Generation).
+       */
+      knowledge_base_ids?: Array<string> | null;
+
+      /**
+       * The model choice for the conversation flow.
+       */
+      model_choice?: ConversationFlow.ModelChoice;
+
+      /**
+       * Controls the randomness of the model's responses. Lower values make responses
+       * more deterministic.
+       */
+      model_temperature?: number | null;
+
+      /**
+       * Who starts the conversation - user or agent.
+       */
+      start_speaker?: 'user' | 'agent';
+    }
+
+    export namespace ConversationFlow {
+      /**
+       * Knowledge base configuration for RAG retrieval.
+       */
+      export interface KBConfig {
+        /**
+         * Similarity threshold for filtering search results
+         */
+        filter_score?: number;
+
+        /**
+         * Max number of knowledge base chunks to retrieve
+         */
+        top_k?: number;
+      }
+
+      /**
+       * The model choice for the conversation flow.
+       */
+      export interface ModelChoice {
+        /**
+         * The LLM model to use
+         */
+        model:
+          | 'gpt-5'
+          | 'gpt-5-mini'
+          | 'gpt-5-nano'
+          | 'gpt-4o'
+          | 'gpt-4o-mini'
+          | 'gpt-4.1'
+          | 'gpt-4.1-mini'
+          | 'gpt-4.1-nano'
+          | 'claude-3.7-sonnet'
+          | 'claude-3.5-haiku'
+          | 'gemini-2.0-flash'
+          | 'gemini-2.0-flash-lite'
+          | 'gemini-2.5-flash'
+          | 'gemini-2.5-flash-lite';
+
+        /**
+         * Type of model choice
+         */
+        type: 'cascading';
+
+        /**
+         * Whether to use high priority pool with more dedicated resource, default false
+         */
+        high_priority?: boolean;
+      }
+    }
+
+    /**
+     * Override Retell LLM configuration settings. Only applicable when using Retell
+     * LLM as the response engine. Supported attributes - model, s2s_model,
+     * model_temperature, knowledge_base_ids, kb_config, start_speaker,
+     * begin_after_user_silence_ms, begin_message.
+     */
+    export interface RetellLlm {
+      /**
+       * If set, the AI will begin the conversation after waiting for the user for the
+       * duration (in milliseconds) specified by this attribute. This only applies if the
+       * agent is configured to wait for the user to speak first. If not set, the agent
+       * will wait indefinitely for the user to speak.
+       */
+      begin_after_user_silence_ms?: number | null;
+
+      /**
+       * First utterance said by the agent in the call. If not set, LLM will dynamically
+       * generate a message. If set to "", agent will wait for user to speak first.
+       */
+      begin_message?: string | null;
+
+      /**
+       * Knowledge base configuration for RAG retrieval.
+       */
+      kb_config?: RetellLlm.KBConfig | null;
+
+      /**
+       * A list of knowledge base ids to use for this resource.
+       */
+      knowledge_base_ids?: Array<string> | null;
+
+      /**
+       * Select the underlying text LLM. If not set, would default to gpt-4.1.
+       */
+      model?:
+        | 'gpt-5'
+        | 'gpt-5-mini'
+        | 'gpt-5-nano'
+        | 'gpt-4o'
+        | 'gpt-4o-mini'
+        | 'gpt-4.1'
+        | 'gpt-4.1-mini'
+        | 'gpt-4.1-nano'
+        | 'claude-3.7-sonnet'
+        | 'claude-3.5-haiku'
+        | 'gemini-2.0-flash'
+        | 'gemini-2.0-flash-lite'
+        | 'gemini-2.5-flash'
+        | 'gemini-2.5-flash-lite'
+        | null;
+
+      /**
+       * If set, will control the randomness of the response. Value ranging from [0,1].
+       * Lower value means more deterministic, while higher value means more random. If
+       * unset, default value 0 will apply. Note that for tool calling, a lower value is
+       * recommended.
+       */
+      model_temperature?: number;
+
+      /**
+       * Select the underlying speech to speech model. Can only set this or model, not
+       * both.
+       */
+      s2s_model?: 'gpt-4o-realtime' | 'gpt-4o-mini-realtime' | 'gpt-realtime' | null;
+
+      /**
+       * The speaker who starts the conversation. Required. Must be either 'user' or
+       * 'agent'.
+       */
+      start_speaker?: 'user' | 'agent';
+    }
+
+    export namespace RetellLlm {
+      /**
+       * Knowledge base configuration for RAG retrieval.
+       */
+      export interface KBConfig {
+        /**
+         * Similarity threshold for filtering search results
+         */
+        filter_score?: number;
+
+        /**
+         * Max number of knowledge base chunks to retrieve
+         */
+        top_k?: number;
+      }
+    }
+  }
+}
+
 export interface CallCreateWebCallParams {
   /**
    * Unique id of agent used for the call. Your agent would contain the LLM Websocket
@@ -2183,6 +3027,12 @@ export interface CallCreateWebCallParams {
    */
   agent_id: string;
 
+  /**
+   * Override configuration for agent, retell LLM, or conversation flow settings for
+   * a specific call.
+   */
+  agent_override?: CallCreateWebCallParams.AgentOverride;
+
   /**
    * The version of the agent to use for the call.
    */
@@ -2203,45 +3053,1691 @@ export interface CallCreateWebCallParams {
   retell_llm_dynamic_variables?: { [key: string]: unknown };
 }
 
-export interface CallRegisterPhoneCallParams {
+export namespace CallCreateWebCallParams {
   /**
-   * The agent to use for the call.
+   * Override configuration for agent, retell LLM, or conversation flow settings for
+   * a specific call.
    */
-  agent_id: string;
+  export interface AgentOverride {
+    /**
+     * Override agent configuration settings. Any properties specified here will
+     * override the base agent configuration for this call.
+     */
+    agent?: AgentOverride.Agent;
 
-  /**
-   * The version of the agent to use for the call.
-   */
-  agent_version?: number;
+    /**
+     * Override conversation flow configuration settings. Only applicable when using
+     * conversation flow as the response engine. Supported attributes - model_choice,
+     * model_temperature, knowledge_base_ids, kb_config, start_speaker,
+     * begin_after_user_silence_ms.
+     */
+    conversation_flow?: AgentOverride.ConversationFlow;
 
-  /**
-   * Direction of the phone call. Stored for tracking purpose.
-   */
-  direction?: 'inbound' | 'outbound';
+    /**
+     * Override Retell LLM configuration settings. Only applicable when using Retell
+     * LLM as the response engine. Supported attributes - model, s2s_model,
+     * model_temperature, knowledge_base_ids, kb_config, start_speaker,
+     * begin_after_user_silence_ms, begin_message.
+     */
+    retell_llm?: AgentOverride.RetellLlm;
+  }
 
-  /**
-   * The number you own in E.164 format. Stored for tracking purpose.
-   */
-  from_number?: string;
+  export namespace AgentOverride {
+    /**
+     * Override agent configuration settings. Any properties specified here will
+     * override the base agent configuration for this call.
+     */
+    export interface Agent {
+      /**
+       * The name of the agent. Only used for your own reference.
+       */
+      agent_name?: string | null;
 
-  /**
-   * An arbitrary object for storage purpose only. You can put anything here like
-   * your internal customer id associated with the call. Not used for processing. You
-   * can later get this field from the call object.
-   */
-  metadata?: unknown;
+      /**
+       * If set to true, DTMF input will be accepted and processed. If false, any DTMF
+       * input will be ignored. Default to true.
+       */
+      allow_user_dtmf?: boolean;
 
-  /**
-   * Add optional dynamic variables in key value pairs of string that injects into
-   * your Response Engine prompt and tool description. Only applicable for Response
-   * Engine.
-   */
-  retell_llm_dynamic_variables?: { [key: string]: unknown };
+      /**
+       * If set, will add ambient environment sound to the call to make experience more
+       * realistic. Currently supports the following options:
+       *
+       * - `coffee-shop`: Coffee shop ambience with people chatting in background.
+       *   [Listen to Ambience](https://retell-utils-public.s3.us-west-2.amazonaws.com/coffee-shop.wav)
+       *
+       * - `convention-hall`: Convention hall ambience, with some echo and people
+       *   chatting in background.
+       *   [Listen to Ambience](https://retell-utils-public.s3.us-west-2.amazonaws.com/convention-hall.wav)
+       *
+       * - `summer-outdoor`: Summer outdoor ambience with cicada chirping.
+       *   [Listen to Ambience](https://retell-utils-public.s3.us-west-2.amazonaws.com/summer-outdoor.wav)
+       *
+       * - `mountain-outdoor`: Mountain outdoor ambience with birds singing.
+       *   [Listen to Ambience](https://retell-utils-public.s3.us-west-2.amazonaws.com/mountain-outdoor.wav)
+       *
+       * - `static-noise`: Constant static noise.
+       *   [Listen to Ambience](https://retell-utils-public.s3.us-west-2.amazonaws.com/static-noise.wav)
+       *
+       * - `call-center`: Call center work noise.
+       *   [Listen to Ambience](https://retell-utils-public.s3.us-west-2.amazonaws.com/call-center.wav)
+       *
+       * Set to `null` to remove ambient sound from this agent.
+       */
+      ambient_sound?:
+        | 'coffee-shop'
+        | 'convention-hall'
+        | 'summer-outdoor'
+        | 'mountain-outdoor'
+        | 'static-noise'
+        | 'call-center'
+        | null;
 
-  /**
-   * The number you want to call, in E.164 format. Stored for tracking purpose.
-   */
-  to_number?: string;
+      /**
+       * If set, will control the volume of the ambient sound. Value ranging from [0,2].
+       * Lower value means quieter ambient sound, while higher value means louder ambient
+       * sound. If unset, default value 1 will apply.
+       */
+      ambient_sound_volume?: number;
+
+      /**
+       * Only applicable when enable_backchannel is true. Controls how often the agent
+       * would backchannel when a backchannel is possible. Value ranging from [0,1].
+       * Lower value means less frequent backchannel, while higher value means more
+       * frequent backchannel. If unset, default value 0.8 will apply.
+       */
+      backchannel_frequency?: number;
+
+      /**
+       * Only applicable when enable_backchannel is true. A list of words that the agent
+       * would use as backchannel. If not set, default backchannel words will apply.
+       * Check out
+       * [backchannel default words](/agent/interaction-configuration#backchannel) for
+       * more details. Note that certain voices do not work too well with certain words,
+       * so it's recommended to experiment before adding any words.
+       */
+      backchannel_words?: Array<string> | null;
+
+      /**
+       * If set, will delay the first message by the specified amount of milliseconds, so
+       * that it gives user more time to prepare to take the call. Valid range is [0,
+       * 5000]. If not set or set to 0, agent will speak immediately. Only applicable
+       * when agent speaks first.
+       */
+      begin_message_delay_ms?: number;
+
+      /**
+       * Provide a customized list of keywords to bias the transcriber model, so that
+       * these words are more likely to get transcribed. Commonly used for names, brands,
+       * street, etc.
+       */
+      boosted_keywords?: Array<string> | null;
+
+      /**
+       * Granular setting to manage how Retell stores sensitive data (transcripts,
+       * recordings, logs, etc.). This replaces the deprecated
+       * `opt_out_sensitive_data_storage` field.
+       *
+       * - `everything`: Store all data including transcripts, recordings, and logs.
+       * - `everything_except_pii`: Store data without PII when PII is detected.
+       * - `basic_attributes_only`: Store only basic attributes; no
+       *   transcripts/recordings/logs. If not set, default value of "everything" will
+       *   apply.
+       */
+      data_storage_setting?: 'everything' | 'everything_except_pii' | 'basic_attributes_only';
+
+      /**
+       * If set, determines what denoising mode to use. Default to noise-cancellation.
+       */
+      denoising_mode?: 'noise-cancellation' | 'noise-and-background-speech-cancellation';
+
+      /**
+       * Controls whether the agent would backchannel (agent interjects the speaker with
+       * phrases like "yeah", "uh-huh" to signify interest and engagement). Backchannel
+       * when enabled tends to show up more in longer user utterances. If not set, agent
+       * will not backchannel.
+       */
+      enable_backchannel?: boolean;
+
+      /**
+       * If users stay silent for a period after agent speech, end the call. The minimum
+       * value allowed is 10,000 ms (10 s). By default, this is set to 600000 (10 min).
+       */
+      end_call_after_silence_ms?: number;
+
+      /**
+       * When TTS provider for the selected voice is experiencing outages, we would use
+       * fallback voices listed here for the agent. Voice id and the fallback voice ids
+       * must be from different TTS providers. The system would go through the list in
+       * order, if the first one in the list is also having outage, it would use the next
+       * one. Set to null to remove voice fallback for the agent.
+       */
+      fallback_voice_ids?: Array<string> | null;
+
+      /**
+       * Controls how sensitive the agent is to user interruptions. Value ranging from
+       * [0,1]. Lower value means it will take longer / more words for user to interrupt
+       * agent, while higher value means it's easier for user to interrupt agent. If
+       * unset, default value 1 will apply. When this is set to 0, agent would never be
+       * interrupted.
+       */
+      interruption_sensitivity?: number;
+
+      /**
+       * Specifies what language (and dialect) the speech recognition will operate in.
+       * For instance, selecting `en-GB` optimizes speech recognition for British
+       * English. If unset, will use default value `en-US`. Select `multi` for
+       * multilingual support, currently this supports Spanish and English.
+       */
+      language?:
+        | 'en-US'
+        | 'en-IN'
+        | 'en-GB'
+        | 'en-AU'
+        | 'en-NZ'
+        | 'de-DE'
+        | 'es-ES'
+        | 'es-419'
+        | 'hi-IN'
+        | 'fr-FR'
+        | 'fr-CA'
+        | 'ja-JP'
+        | 'pt-PT'
+        | 'pt-BR'
+        | 'zh-CN'
+        | 'ru-RU'
+        | 'it-IT'
+        | 'ko-KR'
+        | 'nl-NL'
+        | 'nl-BE'
+        | 'pl-PL'
+        | 'tr-TR'
+        | 'th-TH'
+        | 'vi-VN'
+        | 'ro-RO'
+        | 'bg-BG'
+        | 'ca-ES'
+        | 'da-DK'
+        | 'fi-FI'
+        | 'el-GR'
+        | 'hu-HU'
+        | 'id-ID'
+        | 'no-NO'
+        | 'sk-SK'
+        | 'sv-SE'
+        | 'multi';
+
+      /**
+       * Maximum allowed length for the call, will force end the call if reached. The
+       * minimum value allowed is 60,000 ms (1 min), and maximum value allowed is
+       * 7,200,000 (2 hours). By default, this is set to 3,600,000 (1 hour).
+       */
+      max_call_duration_ms?: number;
+
+      /**
+       * If set to true, will normalize the some part of text (number, currency, date,
+       * etc) to spoken to its spoken form for more consistent speech synthesis
+       * (sometimes the voice synthesize system itself might read these wrong with the
+       * raw text). For example, it will convert "Call my number 2137112342 on Jul 5th,
+       * 2024 for the $24.12 payment" to "Call my number two one three seven one one two
+       * three four two on july fifth, twenty twenty four for the twenty four dollars
+       * twelve cents payment" before starting audio generation.
+       */
+      normalize_for_speech?: boolean;
+
+      /**
+       * Whether this agent opts in for signed URLs for public logs and recordings. When
+       * enabled, the generated URLs will include security signatures that restrict
+       * access and automatically expire after 24 hours.
+       */
+      opt_in_signed_url?: boolean;
+
+      /**
+       * Configuration for PII scrubbing from transcripts and recordings.
+       */
+      pii_config?: Agent.PiiConfig;
+
+      /**
+       * Post call analysis data to extract from the call. This data will augment the
+       * pre-defined variables extracted in the call analysis. This will be available
+       * after the call ends.
+       */
+      post_call_analysis_data?: Array<
+        | Agent.StringAnalysisData
+        | Agent.EnumAnalysisData
+        | Agent.BooleanAnalysisData
+        | Agent.NumberAnalysisData
+      > | null;
+
+      /**
+       * The model to use for post call analysis. Default to gpt-4o-mini.
+       */
+      post_call_analysis_model?:
+        | 'gpt-4o'
+        | 'gpt-4o-mini'
+        | 'gpt-4.1'
+        | 'gpt-4.1-mini'
+        | 'gpt-4.1-nano'
+        | 'gpt-5'
+        | 'gpt-5-mini'
+        | 'gpt-5-nano'
+        | 'claude-4.5-sonnet'
+        | 'claude-4.0-sonnet'
+        | 'claude-3.7-sonnet'
+        | 'claude-3.5-haiku'
+        | 'gemini-2.0-flash'
+        | 'gemini-2.0-flash-lite'
+        | 'gemini-2.5-flash'
+        | 'gemini-2.5-flash-lite';
+
+      /**
+       * A list of words / phrases and their pronunciation to be used to guide the audio
+       * synthesize for consistent pronunciation. Currently only supported for English &
+       * 11labs voices. Set to null to remove pronunciation dictionary from this agent.
+       */
+      pronunciation_dictionary?: Array<Agent.PronunciationDictionary> | null;
+
+      /**
+       * If set, controls how many times agent would remind user when user is
+       * unresponsive. Must be a non negative integer. If unset, default value of 1 will
+       * apply (remind once). Set to 0 to disable agent from reminding.
+       */
+      reminder_max_count?: number;
+
+      /**
+       * If set (in milliseconds), will trigger a reminder to the agent to speak if the
+       * user has been silent for the specified duration after some agent speech. Must be
+       * a positive number. If unset, default value of 10000 ms (10 s) will apply.
+       */
+      reminder_trigger_ms?: number;
+
+      /**
+       * The Response Engine to attach to the agent. It is used to generate responses for
+       * the agent. You need to create a Response Engine first before attaching it to an
+       * agent.
+       */
+      response_engine?:
+        | Agent.ResponseEngineRetellLm
+        | Agent.ResponseEngineCustomLm
+        | Agent.ResponseEngineConversationFlow;
+
+      /**
+       * Controls how responsive is the agent. Value ranging from [0,1]. Lower value
+       * means less responsive agent (wait more, respond slower), while higher value
+       * means faster exchanges (respond when it can). If unset, default value 1 will
+       * apply.
+       */
+      responsiveness?: number;
+
+      /**
+       * If set, the phone ringing will last for the specified amount of milliseconds.
+       * This applies for both outbound call ringtime, and call transfer ringtime.
+       * Default to 30000 (30 s). Valid range is [5000, 90000].
+       */
+      ring_duration_ms?: number;
+
+      /**
+       * If set, determines whether speech to text should focus on latency or accuracy.
+       * Default to fast mode.
+       */
+      stt_mode?: 'fast' | 'accurate';
+
+      user_dtmf_options?: Agent.UserDtmfOptions | null;
+
+      /**
+       * If set, determines the vocabulary set to use for transcription. This setting
+       * only applies for English agents, for non English agent, this setting is a no-op.
+       * Default to general.
+       */
+      vocab_specialization?: 'general' | 'medical';
+
+      /**
+       * Unique voice id used for the agent. Find list of available voices and their
+       * preview in Dashboard.
+       */
+      voice_id?: string;
+
+      /**
+       * Optionally set the voice model used for the selected voice. Currently only
+       * elevenlab voices have voice model selections. Set to null to remove voice model
+       * selection, and default ones will apply. Check out the dashboard for details on
+       * each voice model.
+       */
+      voice_model?:
+        | 'eleven_turbo_v2'
+        | 'eleven_flash_v2'
+        | 'eleven_turbo_v2_5'
+        | 'eleven_flash_v2_5'
+        | 'eleven_multilingual_v2'
+        | 'tts-1'
+        | 'gpt-4o-mini-tts'
+        | null;
+
+      /**
+       * Controls speed of voice. Value ranging from [0.5,2]. Lower value means slower
+       * speech, while higher value means faster speech rate. If unset, default value 1
+       * will apply.
+       */
+      voice_speed?: number;
+
+      /**
+       * Controls how stable the voice is. Value ranging from [0,2]. Lower value means
+       * more stable, and higher value means more variant speech generation. Currently
+       * this setting only applies to `11labs` voices. If unset, default value 1 will
+       * apply.
+       */
+      voice_temperature?: number;
+
+      /**
+       * If this option is set, the call will try to detect voicemail in the first 3
+       * minutes of the call. Actions defined (hangup, or leave a message) will be
+       * applied when the voicemail is detected. Set this to null to disable voicemail
+       * detection.
+       */
+      voicemail_option?: Agent.VoicemailOption | null;
+
+      /**
+       * If set, will control the volume of the agent. Value ranging from [0,2]. Lower
+       * value means quieter agent speech, while higher value means louder agent speech.
+       * If unset, default value 1 will apply.
+       */
+      volume?: number;
+
+      /**
+       * The timeout for the webhook in milliseconds. If not set, default value of 10000
+       * will apply.
+       */
+      webhook_timeout_ms?: number;
+
+      /**
+       * The webhook for agent to listen to call events. See what events it would get at
+       * [webhook doc](/features/webhook). If set, will binds webhook events for this
+       * agent to the specified url, and will ignore the account level webhook for this
+       * agent. Set to `null` to remove webhook url from this agent.
+       */
+      webhook_url?: string | null;
+    }
+
+    export namespace Agent {
+      /**
+       * Configuration for PII scrubbing from transcripts and recordings.
+       */
+      export interface PiiConfig {
+        /**
+         * List of PII categories to scrub from transcripts and recordings.
+         */
+        categories: Array<
+          | 'person_name'
+          | 'address'
+          | 'email'
+          | 'phone_number'
+          | 'ssn'
+          | 'passport'
+          | 'driver_license'
+          | 'credit_card'
+          | 'bank_account'
+          | 'password'
+          | 'pin'
+          | 'medical_id'
+          | 'date_of_birth'
+        >;
+
+        /**
+         * The processing mode for PII scrubbing. Currently only post-call is supported.
+         */
+        mode: 'post_call';
+      }
+
+      export interface StringAnalysisData {
+        /**
+         * Description of the variable.
+         */
+        description: string;
+
+        /**
+         * Name of the variable.
+         */
+        name: string;
+
+        /**
+         * Type of the variable to extract.
+         */
+        type: 'string';
+
+        /**
+         * Examples of the variable value to teach model the style and syntax.
+         */
+        examples?: Array<string>;
+      }
+
+      export interface EnumAnalysisData {
+        /**
+         * The possible values of the variable, must be non empty array.
+         */
+        choices: Array<string>;
+
+        /**
+         * Description of the variable.
+         */
+        description: string;
+
+        /**
+         * Name of the variable.
+         */
+        name: string;
+
+        /**
+         * Type of the variable to extract.
+         */
+        type: 'enum';
+      }
+
+      export interface BooleanAnalysisData {
+        /**
+         * Description of the variable.
+         */
+        description: string;
+
+        /**
+         * Name of the variable.
+         */
+        name: string;
+
+        /**
+         * Type of the variable to extract.
+         */
+        type: 'boolean';
+      }
+
+      export interface NumberAnalysisData {
+        /**
+         * Description of the variable.
+         */
+        description: string;
+
+        /**
+         * Name of the variable.
+         */
+        name: string;
+
+        /**
+         * Type of the variable to extract.
+         */
+        type: 'number';
+      }
+
+      export interface PronunciationDictionary {
+        /**
+         * The phonetic alphabet to be used for pronunciation.
+         */
+        alphabet: 'ipa' | 'cmu';
+
+        /**
+         * Pronunciation of the word in the format of a IPA / CMU pronunciation.
+         */
+        phoneme: string;
+
+        /**
+         * The string of word / phrase to be annotated with pronunciation.
+         */
+        word: string;
+      }
+
+      export interface ResponseEngineRetellLm {
+        /**
+         * id of the Retell LLM Response Engine.
+         */
+        llm_id: string;
+
+        /**
+         * type of the Response Engine.
+         */
+        type: 'retell-llm';
+
+        /**
+         * Version of the Retell LLM Response Engine.
+         */
+        version?: number | null;
+      }
+
+      export interface ResponseEngineCustomLm {
+        /**
+         * LLM websocket url of the custom LLM.
+         */
+        llm_websocket_url: string;
+
+        /**
+         * type of the Response Engine.
+         */
+        type: 'custom-llm';
+      }
+
+      export interface ResponseEngineConversationFlow {
+        /**
+         * ID of the Conversation Flow Response Engine.
+         */
+        conversation_flow_id: string;
+
+        /**
+         * type of the Response Engine.
+         */
+        type: 'conversation-flow';
+
+        /**
+         * Version of the Conversation Flow Response Engine.
+         */
+        version?: number | null;
+      }
+
+      export interface UserDtmfOptions {
+        /**
+         * The maximum number of digits allowed in the user's DTMF (Dual-Tone
+         * Multi-Frequency) input per turn. Once this limit is reached, the input is
+         * considered complete and a response will be generated immediately.
+         */
+        digit_limit?: number | null;
+
+        /**
+         * A single key that signals the end of DTMF input. Acceptable values include any
+         * digit (0–9), the pound/hash symbol (#), or the asterisk (\*).
+         */
+        termination_key?: string | null;
+
+        /**
+         * The time (in milliseconds) to wait for user DTMF input before timing out. The
+         * timer resets with each digit received.
+         */
+        timeout_ms?: number;
+      }
+
+      /**
+       * If this option is set, the call will try to detect voicemail in the first 3
+       * minutes of the call. Actions defined (hangup, or leave a message) will be
+       * applied when the voicemail is detected. Set this to null to disable voicemail
+       * detection.
+       */
+      export interface VoicemailOption {
+        action:
+          | VoicemailOption.VoicemailActionPrompt
+          | VoicemailOption.VoicemailActionStaticText
+          | VoicemailOption.VoicemailActionHangup;
+      }
+
+      export namespace VoicemailOption {
+        export interface VoicemailActionPrompt {
+          /**
+           * The prompt used to generate the text to be spoken when the call is detected to
+           * be in voicemail.
+           */
+          text: string;
+
+          type: 'prompt';
+        }
+
+        export interface VoicemailActionStaticText {
+          /**
+           * The text to be spoken when the call is detected to be in voicemail.
+           */
+          text: string;
+
+          type: 'static_text';
+        }
+
+        export interface VoicemailActionHangup {
+          type: 'hangup';
+        }
+      }
+    }
+
+    /**
+     * Override conversation flow configuration settings. Only applicable when using
+     * conversation flow as the response engine. Supported attributes - model_choice,
+     * model_temperature, knowledge_base_ids, kb_config, start_speaker,
+     * begin_after_user_silence_ms.
+     */
+    export interface ConversationFlow {
+      /**
+       * If set, the AI will begin the conversation after waiting for the user for the
+       * duration (in milliseconds) specified by this attribute. This only applies if the
+       * agent is configured to wait for the user to speak first. If not set, the agent
+       * will wait indefinitely for the user to speak.
+       */
+      begin_after_user_silence_ms?: number | null;
+
+      /**
+       * Knowledge base configuration for RAG retrieval.
+       */
+      kb_config?: ConversationFlow.KBConfig;
+
+      /**
+       * Knowledge base IDs for RAG (Retrieval-Augmented Generation).
+       */
+      knowledge_base_ids?: Array<string> | null;
+
+      /**
+       * The model choice for the conversation flow.
+       */
+      model_choice?: ConversationFlow.ModelChoice;
+
+      /**
+       * Controls the randomness of the model's responses. Lower values make responses
+       * more deterministic.
+       */
+      model_temperature?: number | null;
+
+      /**
+       * Who starts the conversation - user or agent.
+       */
+      start_speaker?: 'user' | 'agent';
+    }
+
+    export namespace ConversationFlow {
+      /**
+       * Knowledge base configuration for RAG retrieval.
+       */
+      export interface KBConfig {
+        /**
+         * Similarity threshold for filtering search results
+         */
+        filter_score?: number;
+
+        /**
+         * Max number of knowledge base chunks to retrieve
+         */
+        top_k?: number;
+      }
+
+      /**
+       * The model choice for the conversation flow.
+       */
+      export interface ModelChoice {
+        /**
+         * The LLM model to use
+         */
+        model:
+          | 'gpt-5'
+          | 'gpt-5-mini'
+          | 'gpt-5-nano'
+          | 'gpt-4o'
+          | 'gpt-4o-mini'
+          | 'gpt-4.1'
+          | 'gpt-4.1-mini'
+          | 'gpt-4.1-nano'
+          | 'claude-3.7-sonnet'
+          | 'claude-3.5-haiku'
+          | 'gemini-2.0-flash'
+          | 'gemini-2.0-flash-lite'
+          | 'gemini-2.5-flash'
+          | 'gemini-2.5-flash-lite';
+
+        /**
+         * Type of model choice
+         */
+        type: 'cascading';
+
+        /**
+         * Whether to use high priority pool with more dedicated resource, default false
+         */
+        high_priority?: boolean;
+      }
+    }
+
+    /**
+     * Override Retell LLM configuration settings. Only applicable when using Retell
+     * LLM as the response engine. Supported attributes - model, s2s_model,
+     * model_temperature, knowledge_base_ids, kb_config, start_speaker,
+     * begin_after_user_silence_ms, begin_message.
+     */
+    export interface RetellLlm {
+      /**
+       * If set, the AI will begin the conversation after waiting for the user for the
+       * duration (in milliseconds) specified by this attribute. This only applies if the
+       * agent is configured to wait for the user to speak first. If not set, the agent
+       * will wait indefinitely for the user to speak.
+       */
+      begin_after_user_silence_ms?: number | null;
+
+      /**
+       * First utterance said by the agent in the call. If not set, LLM will dynamically
+       * generate a message. If set to "", agent will wait for user to speak first.
+       */
+      begin_message?: string | null;
+
+      /**
+       * Knowledge base configuration for RAG retrieval.
+       */
+      kb_config?: RetellLlm.KBConfig | null;
+
+      /**
+       * A list of knowledge base ids to use for this resource.
+       */
+      knowledge_base_ids?: Array<string> | null;
+
+      /**
+       * Select the underlying text LLM. If not set, would default to gpt-4.1.
+       */
+      model?:
+        | 'gpt-5'
+        | 'gpt-5-mini'
+        | 'gpt-5-nano'
+        | 'gpt-4o'
+        | 'gpt-4o-mini'
+        | 'gpt-4.1'
+        | 'gpt-4.1-mini'
+        | 'gpt-4.1-nano'
+        | 'claude-3.7-sonnet'
+        | 'claude-3.5-haiku'
+        | 'gemini-2.0-flash'
+        | 'gemini-2.0-flash-lite'
+        | 'gemini-2.5-flash'
+        | 'gemini-2.5-flash-lite'
+        | null;
+
+      /**
+       * If set, will control the randomness of the response. Value ranging from [0,1].
+       * Lower value means more deterministic, while higher value means more random. If
+       * unset, default value 0 will apply. Note that for tool calling, a lower value is
+       * recommended.
+       */
+      model_temperature?: number;
+
+      /**
+       * Select the underlying speech to speech model. Can only set this or model, not
+       * both.
+       */
+      s2s_model?: 'gpt-4o-realtime' | 'gpt-4o-mini-realtime' | 'gpt-realtime' | null;
+
+      /**
+       * The speaker who starts the conversation. Required. Must be either 'user' or
+       * 'agent'.
+       */
+      start_speaker?: 'user' | 'agent';
+    }
+
+    export namespace RetellLlm {
+      /**
+       * Knowledge base configuration for RAG retrieval.
+       */
+      export interface KBConfig {
+        /**
+         * Similarity threshold for filtering search results
+         */
+        filter_score?: number;
+
+        /**
+         * Max number of knowledge base chunks to retrieve
+         */
+        top_k?: number;
+      }
+    }
+  }
+}
+
+export interface CallRegisterPhoneCallParams {
+  /**
+   * The agent to use for the call.
+   */
+  agent_id: string;
+
+  /**
+   * Override configuration for agent, retell LLM, or conversation flow settings for
+   * a specific call.
+   */
+  agent_override?: CallRegisterPhoneCallParams.AgentOverride;
+
+  /**
+   * The version of the agent to use for the call.
+   */
+  agent_version?: number;
+
+  /**
+   * Direction of the phone call. Stored for tracking purpose.
+   */
+  direction?: 'inbound' | 'outbound';
+
+  /**
+   * The number you own in E.164 format. Stored for tracking purpose.
+   */
+  from_number?: string;
+
+  /**
+   * An arbitrary object for storage purpose only. You can put anything here like
+   * your internal customer id associated with the call. Not used for processing. You
+   * can later get this field from the call object.
+   */
+  metadata?: unknown;
+
+  /**
+   * Add optional dynamic variables in key value pairs of string that injects into
+   * your Response Engine prompt and tool description. Only applicable for Response
+   * Engine.
+   */
+  retell_llm_dynamic_variables?: { [key: string]: unknown };
+
+  /**
+   * The number you want to call, in E.164 format. Stored for tracking purpose.
+   */
+  to_number?: string;
+}
+
+export namespace CallRegisterPhoneCallParams {
+  /**
+   * Override configuration for agent, retell LLM, or conversation flow settings for
+   * a specific call.
+   */
+  export interface AgentOverride {
+    /**
+     * Override agent configuration settings. Any properties specified here will
+     * override the base agent configuration for this call.
+     */
+    agent?: AgentOverride.Agent;
+
+    /**
+     * Override conversation flow configuration settings. Only applicable when using
+     * conversation flow as the response engine. Supported attributes - model_choice,
+     * model_temperature, knowledge_base_ids, kb_config, start_speaker,
+     * begin_after_user_silence_ms.
+     */
+    conversation_flow?: AgentOverride.ConversationFlow;
+
+    /**
+     * Override Retell LLM configuration settings. Only applicable when using Retell
+     * LLM as the response engine. Supported attributes - model, s2s_model,
+     * model_temperature, knowledge_base_ids, kb_config, start_speaker,
+     * begin_after_user_silence_ms, begin_message.
+     */
+    retell_llm?: AgentOverride.RetellLlm;
+  }
+
+  export namespace AgentOverride {
+    /**
+     * Override agent configuration settings. Any properties specified here will
+     * override the base agent configuration for this call.
+     */
+    export interface Agent {
+      /**
+       * The name of the agent. Only used for your own reference.
+       */
+      agent_name?: string | null;
+
+      /**
+       * If set to true, DTMF input will be accepted and processed. If false, any DTMF
+       * input will be ignored. Default to true.
+       */
+      allow_user_dtmf?: boolean;
+
+      /**
+       * If set, will add ambient environment sound to the call to make experience more
+       * realistic. Currently supports the following options:
+       *
+       * - `coffee-shop`: Coffee shop ambience with people chatting in background.
+       *   [Listen to Ambience](https://retell-utils-public.s3.us-west-2.amazonaws.com/coffee-shop.wav)
+       *
+       * - `convention-hall`: Convention hall ambience, with some echo and people
+       *   chatting in background.
+       *   [Listen to Ambience](https://retell-utils-public.s3.us-west-2.amazonaws.com/convention-hall.wav)
+       *
+       * - `summer-outdoor`: Summer outdoor ambience with cicada chirping.
+       *   [Listen to Ambience](https://retell-utils-public.s3.us-west-2.amazonaws.com/summer-outdoor.wav)
+       *
+       * - `mountain-outdoor`: Mountain outdoor ambience with birds singing.
+       *   [Listen to Ambience](https://retell-utils-public.s3.us-west-2.amazonaws.com/mountain-outdoor.wav)
+       *
+       * - `static-noise`: Constant static noise.
+       *   [Listen to Ambience](https://retell-utils-public.s3.us-west-2.amazonaws.com/static-noise.wav)
+       *
+       * - `call-center`: Call center work noise.
+       *   [Listen to Ambience](https://retell-utils-public.s3.us-west-2.amazonaws.com/call-center.wav)
+       *
+       * Set to `null` to remove ambient sound from this agent.
+       */
+      ambient_sound?:
+        | 'coffee-shop'
+        | 'convention-hall'
+        | 'summer-outdoor'
+        | 'mountain-outdoor'
+        | 'static-noise'
+        | 'call-center'
+        | null;
+
+      /**
+       * If set, will control the volume of the ambient sound. Value ranging from [0,2].
+       * Lower value means quieter ambient sound, while higher value means louder ambient
+       * sound. If unset, default value 1 will apply.
+       */
+      ambient_sound_volume?: number;
+
+      /**
+       * Only applicable when enable_backchannel is true. Controls how often the agent
+       * would backchannel when a backchannel is possible. Value ranging from [0,1].
+       * Lower value means less frequent backchannel, while higher value means more
+       * frequent backchannel. If unset, default value 0.8 will apply.
+       */
+      backchannel_frequency?: number;
+
+      /**
+       * Only applicable when enable_backchannel is true. A list of words that the agent
+       * would use as backchannel. If not set, default backchannel words will apply.
+       * Check out
+       * [backchannel default words](/agent/interaction-configuration#backchannel) for
+       * more details. Note that certain voices do not work too well with certain words,
+       * so it's recommended to experiment before adding any words.
+       */
+      backchannel_words?: Array<string> | null;
+
+      /**
+       * If set, will delay the first message by the specified amount of milliseconds, so
+       * that it gives user more time to prepare to take the call. Valid range is [0,
+       * 5000]. If not set or set to 0, agent will speak immediately. Only applicable
+       * when agent speaks first.
+       */
+      begin_message_delay_ms?: number;
+
+      /**
+       * Provide a customized list of keywords to bias the transcriber model, so that
+       * these words are more likely to get transcribed. Commonly used for names, brands,
+       * street, etc.
+       */
+      boosted_keywords?: Array<string> | null;
+
+      /**
+       * Granular setting to manage how Retell stores sensitive data (transcripts,
+       * recordings, logs, etc.). This replaces the deprecated
+       * `opt_out_sensitive_data_storage` field.
+       *
+       * - `everything`: Store all data including transcripts, recordings, and logs.
+       * - `everything_except_pii`: Store data without PII when PII is detected.
+       * - `basic_attributes_only`: Store only basic attributes; no
+       *   transcripts/recordings/logs. If not set, default value of "everything" will
+       *   apply.
+       */
+      data_storage_setting?: 'everything' | 'everything_except_pii' | 'basic_attributes_only';
+
+      /**
+       * If set, determines what denoising mode to use. Default to noise-cancellation.
+       */
+      denoising_mode?: 'noise-cancellation' | 'noise-and-background-speech-cancellation';
+
+      /**
+       * Controls whether the agent would backchannel (agent interjects the speaker with
+       * phrases like "yeah", "uh-huh" to signify interest and engagement). Backchannel
+       * when enabled tends to show up more in longer user utterances. If not set, agent
+       * will not backchannel.
+       */
+      enable_backchannel?: boolean;
+
+      /**
+       * If users stay silent for a period after agent speech, end the call. The minimum
+       * value allowed is 10,000 ms (10 s). By default, this is set to 600000 (10 min).
+       */
+      end_call_after_silence_ms?: number;
+
+      /**
+       * When TTS provider for the selected voice is experiencing outages, we would use
+       * fallback voices listed here for the agent. Voice id and the fallback voice ids
+       * must be from different TTS providers. The system would go through the list in
+       * order, if the first one in the list is also having outage, it would use the next
+       * one. Set to null to remove voice fallback for the agent.
+       */
+      fallback_voice_ids?: Array<string> | null;
+
+      /**
+       * Controls how sensitive the agent is to user interruptions. Value ranging from
+       * [0,1]. Lower value means it will take longer / more words for user to interrupt
+       * agent, while higher value means it's easier for user to interrupt agent. If
+       * unset, default value 1 will apply. When this is set to 0, agent would never be
+       * interrupted.
+       */
+      interruption_sensitivity?: number;
+
+      /**
+       * Specifies what language (and dialect) the speech recognition will operate in.
+       * For instance, selecting `en-GB` optimizes speech recognition for British
+       * English. If unset, will use default value `en-US`. Select `multi` for
+       * multilingual support, currently this supports Spanish and English.
+       */
+      language?:
+        | 'en-US'
+        | 'en-IN'
+        | 'en-GB'
+        | 'en-AU'
+        | 'en-NZ'
+        | 'de-DE'
+        | 'es-ES'
+        | 'es-419'
+        | 'hi-IN'
+        | 'fr-FR'
+        | 'fr-CA'
+        | 'ja-JP'
+        | 'pt-PT'
+        | 'pt-BR'
+        | 'zh-CN'
+        | 'ru-RU'
+        | 'it-IT'
+        | 'ko-KR'
+        | 'nl-NL'
+        | 'nl-BE'
+        | 'pl-PL'
+        | 'tr-TR'
+        | 'th-TH'
+        | 'vi-VN'
+        | 'ro-RO'
+        | 'bg-BG'
+        | 'ca-ES'
+        | 'da-DK'
+        | 'fi-FI'
+        | 'el-GR'
+        | 'hu-HU'
+        | 'id-ID'
+        | 'no-NO'
+        | 'sk-SK'
+        | 'sv-SE'
+        | 'multi';
+
+      /**
+       * Maximum allowed length for the call, will force end the call if reached. The
+       * minimum value allowed is 60,000 ms (1 min), and maximum value allowed is
+       * 7,200,000 (2 hours). By default, this is set to 3,600,000 (1 hour).
+       */
+      max_call_duration_ms?: number;
+
+      /**
+       * If set to true, will normalize the some part of text (number, currency, date,
+       * etc) to spoken to its spoken form for more consistent speech synthesis
+       * (sometimes the voice synthesize system itself might read these wrong with the
+       * raw text). For example, it will convert "Call my number 2137112342 on Jul 5th,
+       * 2024 for the $24.12 payment" to "Call my number two one three seven one one two
+       * three four two on july fifth, twenty twenty four for the twenty four dollars
+       * twelve cents payment" before starting audio generation.
+       */
+      normalize_for_speech?: boolean;
+
+      /**
+       * Whether this agent opts in for signed URLs for public logs and recordings. When
+       * enabled, the generated URLs will include security signatures that restrict
+       * access and automatically expire after 24 hours.
+       */
+      opt_in_signed_url?: boolean;
+
+      /**
+       * Configuration for PII scrubbing from transcripts and recordings.
+       */
+      pii_config?: Agent.PiiConfig;
+
+      /**
+       * Post call analysis data to extract from the call. This data will augment the
+       * pre-defined variables extracted in the call analysis. This will be available
+       * after the call ends.
+       */
+      post_call_analysis_data?: Array<
+        | Agent.StringAnalysisData
+        | Agent.EnumAnalysisData
+        | Agent.BooleanAnalysisData
+        | Agent.NumberAnalysisData
+      > | null;
+
+      /**
+       * The model to use for post call analysis. Default to gpt-4o-mini.
+       */
+      post_call_analysis_model?:
+        | 'gpt-4o'
+        | 'gpt-4o-mini'
+        | 'gpt-4.1'
+        | 'gpt-4.1-mini'
+        | 'gpt-4.1-nano'
+        | 'gpt-5'
+        | 'gpt-5-mini'
+        | 'gpt-5-nano'
+        | 'claude-4.5-sonnet'
+        | 'claude-4.0-sonnet'
+        | 'claude-3.7-sonnet'
+        | 'claude-3.5-haiku'
+        | 'gemini-2.0-flash'
+        | 'gemini-2.0-flash-lite'
+        | 'gemini-2.5-flash'
+        | 'gemini-2.5-flash-lite';
+
+      /**
+       * A list of words / phrases and their pronunciation to be used to guide the audio
+       * synthesize for consistent pronunciation. Currently only supported for English &
+       * 11labs voices. Set to null to remove pronunciation dictionary from this agent.
+       */
+      pronunciation_dictionary?: Array<Agent.PronunciationDictionary> | null;
+
+      /**
+       * If set, controls how many times agent would remind user when user is
+       * unresponsive. Must be a non negative integer. If unset, default value of 1 will
+       * apply (remind once). Set to 0 to disable agent from reminding.
+       */
+      reminder_max_count?: number;
+
+      /**
+       * If set (in milliseconds), will trigger a reminder to the agent to speak if the
+       * user has been silent for the specified duration after some agent speech. Must be
+       * a positive number. If unset, default value of 10000 ms (10 s) will apply.
+       */
+      reminder_trigger_ms?: number;
+
+      /**
+       * The Response Engine to attach to the agent. It is used to generate responses for
+       * the agent. You need to create a Response Engine first before attaching it to an
+       * agent.
+       */
+      response_engine?:
+        | Agent.ResponseEngineRetellLm
+        | Agent.ResponseEngineCustomLm
+        | Agent.ResponseEngineConversationFlow;
+
+      /**
+       * Controls how responsive is the agent. Value ranging from [0,1]. Lower value
+       * means less responsive agent (wait more, respond slower), while higher value
+       * means faster exchanges (respond when it can). If unset, default value 1 will
+       * apply.
+       */
+      responsiveness?: number;
+
+      /**
+       * If set, the phone ringing will last for the specified amount of milliseconds.
+       * This applies for both outbound call ringtime, and call transfer ringtime.
+       * Default to 30000 (30 s). Valid range is [5000, 90000].
+       */
+      ring_duration_ms?: number;
+
+      /**
+       * If set, determines whether speech to text should focus on latency or accuracy.
+       * Default to fast mode.
+       */
+      stt_mode?: 'fast' | 'accurate';
+
+      user_dtmf_options?: Agent.UserDtmfOptions | null;
+
+      /**
+       * If set, determines the vocabulary set to use for transcription. This setting
+       * only applies for English agents, for non English agent, this setting is a no-op.
+       * Default to general.
+       */
+      vocab_specialization?: 'general' | 'medical';
+
+      /**
+       * Unique voice id used for the agent. Find list of available voices and their
+       * preview in Dashboard.
+       */
+      voice_id?: string;
+
+      /**
+       * Optionally set the voice model used for the selected voice. Currently only
+       * elevenlab voices have voice model selections. Set to null to remove voice model
+       * selection, and default ones will apply. Check out the dashboard for details on
+       * each voice model.
+       */
+      voice_model?:
+        | 'eleven_turbo_v2'
+        | 'eleven_flash_v2'
+        | 'eleven_turbo_v2_5'
+        | 'eleven_flash_v2_5'
+        | 'eleven_multilingual_v2'
+        | 'tts-1'
+        | 'gpt-4o-mini-tts'
+        | null;
+
+      /**
+       * Controls speed of voice. Value ranging from [0.5,2]. Lower value means slower
+       * speech, while higher value means faster speech rate. If unset, default value 1
+       * will apply.
+       */
+      voice_speed?: number;
+
+      /**
+       * Controls how stable the voice is. Value ranging from [0,2]. Lower value means
+       * more stable, and higher value means more variant speech generation. Currently
+       * this setting only applies to `11labs` voices. If unset, default value 1 will
+       * apply.
+       */
+      voice_temperature?: number;
+
+      /**
+       * If this option is set, the call will try to detect voicemail in the first 3
+       * minutes of the call. Actions defined (hangup, or leave a message) will be
+       * applied when the voicemail is detected. Set this to null to disable voicemail
+       * detection.
+       */
+      voicemail_option?: Agent.VoicemailOption | null;
+
+      /**
+       * If set, will control the volume of the agent. Value ranging from [0,2]. Lower
+       * value means quieter agent speech, while higher value means louder agent speech.
+       * If unset, default value 1 will apply.
+       */
+      volume?: number;
+
+      /**
+       * The timeout for the webhook in milliseconds. If not set, default value of 10000
+       * will apply.
+       */
+      webhook_timeout_ms?: number;
+
+      /**
+       * The webhook for agent to listen to call events. See what events it would get at
+       * [webhook doc](/features/webhook). If set, will binds webhook events for this
+       * agent to the specified url, and will ignore the account level webhook for this
+       * agent. Set to `null` to remove webhook url from this agent.
+       */
+      webhook_url?: string | null;
+    }
+
+    export namespace Agent {
+      /**
+       * Configuration for PII scrubbing from transcripts and recordings.
+       */
+      export interface PiiConfig {
+        /**
+         * List of PII categories to scrub from transcripts and recordings.
+         */
+        categories: Array<
+          | 'person_name'
+          | 'address'
+          | 'email'
+          | 'phone_number'
+          | 'ssn'
+          | 'passport'
+          | 'driver_license'
+          | 'credit_card'
+          | 'bank_account'
+          | 'password'
+          | 'pin'
+          | 'medical_id'
+          | 'date_of_birth'
+        >;
+
+        /**
+         * The processing mode for PII scrubbing. Currently only post-call is supported.
+         */
+        mode: 'post_call';
+      }
+
+      export interface StringAnalysisData {
+        /**
+         * Description of the variable.
+         */
+        description: string;
+
+        /**
+         * Name of the variable.
+         */
+        name: string;
+
+        /**
+         * Type of the variable to extract.
+         */
+        type: 'string';
+
+        /**
+         * Examples of the variable value to teach model the style and syntax.
+         */
+        examples?: Array<string>;
+      }
+
+      export interface EnumAnalysisData {
+        /**
+         * The possible values of the variable, must be non empty array.
+         */
+        choices: Array<string>;
+
+        /**
+         * Description of the variable.
+         */
+        description: string;
+
+        /**
+         * Name of the variable.
+         */
+        name: string;
+
+        /**
+         * Type of the variable to extract.
+         */
+        type: 'enum';
+      }
+
+      export interface BooleanAnalysisData {
+        /**
+         * Description of the variable.
+         */
+        description: string;
+
+        /**
+         * Name of the variable.
+         */
+        name: string;
+
+        /**
+         * Type of the variable to extract.
+         */
+        type: 'boolean';
+      }
+
+      export interface NumberAnalysisData {
+        /**
+         * Description of the variable.
+         */
+        description: string;
+
+        /**
+         * Name of the variable.
+         */
+        name: string;
+
+        /**
+         * Type of the variable to extract.
+         */
+        type: 'number';
+      }
+
+      export interface PronunciationDictionary {
+        /**
+         * The phonetic alphabet to be used for pronunciation.
+         */
+        alphabet: 'ipa' | 'cmu';
+
+        /**
+         * Pronunciation of the word in the format of a IPA / CMU pronunciation.
+         */
+        phoneme: string;
+
+        /**
+         * The string of word / phrase to be annotated with pronunciation.
+         */
+        word: string;
+      }
+
+      export interface ResponseEngineRetellLm {
+        /**
+         * id of the Retell LLM Response Engine.
+         */
+        llm_id: string;
+
+        /**
+         * type of the Response Engine.
+         */
+        type: 'retell-llm';
+
+        /**
+         * Version of the Retell LLM Response Engine.
+         */
+        version?: number | null;
+      }
+
+      export interface ResponseEngineCustomLm {
+        /**
+         * LLM websocket url of the custom LLM.
+         */
+        llm_websocket_url: string;
+
+        /**
+         * type of the Response Engine.
+         */
+        type: 'custom-llm';
+      }
+
+      export interface ResponseEngineConversationFlow {
+        /**
+         * ID of the Conversation Flow Response Engine.
+         */
+        conversation_flow_id: string;
+
+        /**
+         * type of the Response Engine.
+         */
+        type: 'conversation-flow';
+
+        /**
+         * Version of the Conversation Flow Response Engine.
+         */
+        version?: number | null;
+      }
+
+      export interface UserDtmfOptions {
+        /**
+         * The maximum number of digits allowed in the user's DTMF (Dual-Tone
+         * Multi-Frequency) input per turn. Once this limit is reached, the input is
+         * considered complete and a response will be generated immediately.
+         */
+        digit_limit?: number | null;
+
+        /**
+         * A single key that signals the end of DTMF input. Acceptable values include any
+         * digit (0–9), the pound/hash symbol (#), or the asterisk (\*).
+         */
+        termination_key?: string | null;
+
+        /**
+         * The time (in milliseconds) to wait for user DTMF input before timing out. The
+         * timer resets with each digit received.
+         */
+        timeout_ms?: number;
+      }
+
+      /**
+       * If this option is set, the call will try to detect voicemail in the first 3
+       * minutes of the call. Actions defined (hangup, or leave a message) will be
+       * applied when the voicemail is detected. Set this to null to disable voicemail
+       * detection.
+       */
+      export interface VoicemailOption {
+        action:
+          | VoicemailOption.VoicemailActionPrompt
+          | VoicemailOption.VoicemailActionStaticText
+          | VoicemailOption.VoicemailActionHangup;
+      }
+
+      export namespace VoicemailOption {
+        export interface VoicemailActionPrompt {
+          /**
+           * The prompt used to generate the text to be spoken when the call is detected to
+           * be in voicemail.
+           */
+          text: string;
+
+          type: 'prompt';
+        }
+
+        export interface VoicemailActionStaticText {
+          /**
+           * The text to be spoken when the call is detected to be in voicemail.
+           */
+          text: string;
+
+          type: 'static_text';
+        }
+
+        export interface VoicemailActionHangup {
+          type: 'hangup';
+        }
+      }
+    }
+
+    /**
+     * Override conversation flow configuration settings. Only applicable when using
+     * conversation flow as the response engine. Supported attributes - model_choice,
+     * model_temperature, knowledge_base_ids, kb_config, start_speaker,
+     * begin_after_user_silence_ms.
+     */
+    export interface ConversationFlow {
+      /**
+       * If set, the AI will begin the conversation after waiting for the user for the
+       * duration (in milliseconds) specified by this attribute. This only applies if the
+       * agent is configured to wait for the user to speak first. If not set, the agent
+       * will wait indefinitely for the user to speak.
+       */
+      begin_after_user_silence_ms?: number | null;
+
+      /**
+       * Knowledge base configuration for RAG retrieval.
+       */
+      kb_config?: ConversationFlow.KBConfig;
+
+      /**
+       * Knowledge base IDs for RAG (Retrieval-Augmented Generation).
+       */
+      knowledge_base_ids?: Array<string> | null;
+
+      /**
+       * The model choice for the conversation flow.
+       */
+      model_choice?: ConversationFlow.ModelChoice;
+
+      /**
+       * Controls the randomness of the model's responses. Lower values make responses
+       * more deterministic.
+       */
+      model_temperature?: number | null;
+
+      /**
+       * Who starts the conversation - user or agent.
+       */
+      start_speaker?: 'user' | 'agent';
+    }
+
+    export namespace ConversationFlow {
+      /**
+       * Knowledge base configuration for RAG retrieval.
+       */
+      export interface KBConfig {
+        /**
+         * Similarity threshold for filtering search results
+         */
+        filter_score?: number;
+
+        /**
+         * Max number of knowledge base chunks to retrieve
+         */
+        top_k?: number;
+      }
+
+      /**
+       * The model choice for the conversation flow.
+       */
+      export interface ModelChoice {
+        /**
+         * The LLM model to use
+         */
+        model:
+          | 'gpt-5'
+          | 'gpt-5-mini'
+          | 'gpt-5-nano'
+          | 'gpt-4o'
+          | 'gpt-4o-mini'
+          | 'gpt-4.1'
+          | 'gpt-4.1-mini'
+          | 'gpt-4.1-nano'
+          | 'claude-3.7-sonnet'
+          | 'claude-3.5-haiku'
+          | 'gemini-2.0-flash'
+          | 'gemini-2.0-flash-lite'
+          | 'gemini-2.5-flash'
+          | 'gemini-2.5-flash-lite';
+
+        /**
+         * Type of model choice
+         */
+        type: 'cascading';
+
+        /**
+         * Whether to use high priority pool with more dedicated resource, default false
+         */
+        high_priority?: boolean;
+      }
+    }
+
+    /**
+     * Override Retell LLM configuration settings. Only applicable when using Retell
+     * LLM as the response engine. Supported attributes - model, s2s_model,
+     * model_temperature, knowledge_base_ids, kb_config, start_speaker,
+     * begin_after_user_silence_ms, begin_message.
+     */
+    export interface RetellLlm {
+      /**
+       * If set, the AI will begin the conversation after waiting for the user for the
+       * duration (in milliseconds) specified by this attribute. This only applies if the
+       * agent is configured to wait for the user to speak first. If not set, the agent
+       * will wait indefinitely for the user to speak.
+       */
+      begin_after_user_silence_ms?: number | null;
+
+      /**
+       * First utterance said by the agent in the call. If not set, LLM will dynamically
+       * generate a message. If set to "", agent will wait for user to speak first.
+       */
+      begin_message?: string | null;
+
+      /**
+       * Knowledge base configuration for RAG retrieval.
+       */
+      kb_config?: RetellLlm.KBConfig | null;
+
+      /**
+       * A list of knowledge base ids to use for this resource.
+       */
+      knowledge_base_ids?: Array<string> | null;
+
+      /**
+       * Select the underlying text LLM. If not set, would default to gpt-4.1.
+       */
+      model?:
+        | 'gpt-5'
+        | 'gpt-5-mini'
+        | 'gpt-5-nano'
+        | 'gpt-4o'
+        | 'gpt-4o-mini'
+        | 'gpt-4.1'
+        | 'gpt-4.1-mini'
+        | 'gpt-4.1-nano'
+        | 'claude-3.7-sonnet'
+        | 'claude-3.5-haiku'
+        | 'gemini-2.0-flash'
+        | 'gemini-2.0-flash-lite'
+        | 'gemini-2.5-flash'
+        | 'gemini-2.5-flash-lite'
+        | null;
+
+      /**
+       * If set, will control the randomness of the response. Value ranging from [0,1].
+       * Lower value means more deterministic, while higher value means more random. If
+       * unset, default value 0 will apply. Note that for tool calling, a lower value is
+       * recommended.
+       */
+      model_temperature?: number;
+
+      /**
+       * Select the underlying speech to speech model. Can only set this or model, not
+       * both.
+       */
+      s2s_model?: 'gpt-4o-realtime' | 'gpt-4o-mini-realtime' | 'gpt-realtime' | null;
+
+      /**
+       * The speaker who starts the conversation. Required. Must be either 'user' or
+       * 'agent'.
+       */
+      start_speaker?: 'user' | 'agent';
+    }
+
+    export namespace RetellLlm {
+      /**
+       * Knowledge base configuration for RAG retrieval.
+       */
+      export interface KBConfig {
+        /**
+         * Similarity threshold for filtering search results
+         */
+        filter_score?: number;
+
+        /**
+         * Max number of knowledge base chunks to retrieve
+         */
+        top_k?: number;
+      }
+    }
+  }
 }
 
 export declare namespace Call {