Retell AI Create Agent API

openapi: 3.2.0
info:
  title: Retell SDK Add Community Voice Create Agent API
  version: 3.0.0
  contact:
    name: Retell Support
    url: https://www.retellai.com/
    email: support@retellai.com
  license:
    name: Apache 2.0
    url: https://www.apache.org/licenses/LICENSE-2.0.html
servers:
- url: https://api.retellai.com
  description: The production server.
security:
- api_key: []
tags:
- name: Create Agent
paths:
  /create-agent:
    post:
      description: Create a new agent
      operationId: createAgent
      requestBody:
        required: true
        content:
          application/json:
            schema:
              allOf:
              - $ref: '#/components/schemas/AgentRequest'
              - required:
                - response_engine
                - voice_id
      responses:
        '201':
          description: Successfully created a new agent.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AgentResponse'
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '422':
          $ref: '#/components/responses/UnprocessableContent'
        '500':
          $ref: '#/components/responses/InternalServerError'
      tags:
      - Create Agent
components:
  responses:
    Unauthorized:
      description: Unauthorized
      content:
        application/json:
          schema:
            type: object
            properties:
              status:
                type: string
                enum:
                - error
              message:
                type: string
                example: API key is missing or invalid.
    UnprocessableContent:
      description: Unprocessable Content
      content:
        application/json:
          schema:
            type: object
            properties:
              status:
                type: string
                enum:
                - error
              message:
                type: string
                example: Cannot find requested asset under given api key.
    BadRequest:
      description: Bad Request
      content:
        application/json:
          schema:
            type: object
            properties:
              status:
                type: string
                enum:
                - error
              message:
                type: string
                example: Invalid request format, please check API reference.
    InternalServerError:
      description: Internal Server Error
      content:
        application/json:
          schema:
            type: object
            properties:
              status:
                type: string
                enum:
                - error
              message:
                type: string
                example: An unexpected server error occurred.
  schemas:
    AnalysisData:
      oneOf:
      - $ref: '#/components/schemas/StringAnalysisData'
      - $ref: '#/components/schemas/EnumAnalysisData'
      - $ref: '#/components/schemas/BooleanAnalysisData'
      - $ref: '#/components/schemas/NumberAnalysisData'
    IvrAction:
      oneOf:
      - $ref: '#/components/schemas/IvrActionHangup'
    VoicemailActionBridgeTransfer:
      type: object
      properties:
        type:
          type: string
          enum:
          - bridge_transfer
          example: bridge_transfer
      required:
      - type
    EnumAnalysisData:
      type: object
      required:
      - type
      - name
      - description
      - choices
      properties:
        type:
          type: string
          enum:
          - enum
          description: Type of the variable to extract.
          example: enum
        name:
          type: string
          description: Name of the variable.
          example: product_rating
          minLength: 1
        description:
          type: string
          description: Description of the variable.
          example: Rating of the product.
        choices:
          type: array
          items:
            type: string
          description: The possible values of the variable, must be non empty array.
          example:
          - good
        required:
          type: boolean
          description: Whether this data is required. If true and the data is not extracted, the call will be marked as unsuccessful.
        conditional_prompt:
          type: string
          description: Optional instruction to help decide whether this field needs to be populated in the analysis. If not set, the field is always included. If required is true, this is ignored.
    ResponseEngineRetellLm:
      type: object
      required:
      - type
      - llm_id
      properties:
        type:
          type: string
          enum:
          - retell-llm
          description: type of the Response Engine.
        llm_id:
          type: string
          description: id of the Retell LLM Response Engine.
        version:
          type:
          - number
          - 'null'
          example: 0
          description: Version of the Retell LLM Response Engine.
    NumberAnalysisData:
      type: object
      required:
      - type
      - name
      - description
      properties:
        type:
          type: string
          enum:
          - number
          description: Type of the variable to extract.
          example: number
        name:
          type: string
          description: Name of the variable.
          example: order_count
          minLength: 1
        description:
          type: string
          description: Description of the variable.
          example: How many the customer intend to order.
        required:
          type: boolean
          description: Whether this data is required. If true and the data is not extracted, the call will be marked as unsuccessful.
        conditional_prompt:
          type: string
          description: Optional instruction to help decide whether this field needs to be populated in the analysis. If not set, the field is always included. If required is true, this is ignored.
    VoicemailActionHangup:
      type: object
      properties:
        type:
          type: string
          enum:
          - hangup
          example: hangup
      required:
      - type
    PostCallAnalysisData:
      oneOf:
      - $ref: '#/components/schemas/AnalysisData'
      - $ref: '#/components/schemas/CallPresetAnalysisData'
      description: Post-call analysis item (custom data or voice preset). Use for voice agent post_call_analysis_data; validates only call presets (call_summary, call_successful, user_sentiment).
    ResponseEngineCustomLm:
      type: object
      required:
      - type
      - llm_websocket_url
      properties:
        type:
          type: string
          enum:
          - custom-llm
          description: type of the Response Engine.
        llm_websocket_url:
          type: string
          description: LLM websocket url of the custom LLM.
    StringAnalysisData:
      type: object
      required:
      - type
      - name
      - description
      properties:
        type:
          type: string
          enum:
          - string
          description: Type of the variable to extract.
          example: string
        name:
          type: string
          description: Name of the variable.
          example: customer_name
          minLength: 1
        description:
          type: string
          description: Description of the variable.
          example: The name of the customer.
        examples:
          type: array
          items:
            type: string
          description: Examples of the variable value to teach model the style and syntax.
          example:
          - John Doe
          - Jane Smith
        required:
          type: boolean
          description: Whether this data is required. If true and the data is not extracted, the call will be marked as unsuccessful.
        conditional_prompt:
          type: string
          description: Optional instruction to help decide whether this field needs to be populated in the analysis. If not set, the field is always included. If required is true, this is ignored.
    BooleanAnalysisData:
      type: object
      required:
      - type
      - name
      - description
      properties:
        type:
          type: string
          enum:
          - boolean
          description: Type of the variable to extract.
          example: boolean
        name:
          type: string
          description: Name of the variable.
          example: is_converted
          minLength: 1
        description:
          type: string
          description: Description of the variable.
          example: Whether the customer converted.
        required:
          type: boolean
          description: Whether this data is required. If true and the data is not extracted, the call will be marked as unsuccessful.
        conditional_prompt:
          type: string
          description: Optional instruction to help decide whether this field needs to be populated in the analysis. If not set, the field is always included. If required is true, this is ignored.
    LanguageLegacy:
      oneOf:
      - $ref: '#/components/schemas/Language'
      - type: string
        enum:
        - multi
      example: en-US
      description: Legacy single-string language format. Accepts any concrete locale from `Language`, plus the special scalar value `multi` for multilingual support. If unset, will use default value `en-US`.
    AgentRequest:
      type: object
      properties:
        response_engine:
          $ref: '#/components/schemas/ResponseEngine'
          description: 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.
          example:
            type: retell-llm
            llm_id: llm_234sdertfsdsfsdf
            version: 0
        agent_name:
          type:
          - string
          - 'null'
          example: Jarvis
          description: The name of the agent. Only used for your own reference.
        version_description:
          type:
          - string
          - 'null'
          example: Customer support agent for handling product inquiries
          description: Optional description of the agent version. Used for your own reference and documentation.
        voice_id:
          type: string
          example: retell-Cimo
          description: Unique voice id used for the agent. Find list of available voices and their preview in Dashboard.
        voice_model:
          type:
          - string
          - 'null'
          enum:
          - eleven_turbo_v2
          - eleven_flash_v2
          - eleven_turbo_v2_5
          - eleven_flash_v2_5
          - eleven_multilingual_v2
          - eleven_v3
          - sonic-3
          - sonic-3-latest
          - tts-1
          - gpt-4o-mini-tts
          - speech-02-turbo
          - speech-2.8-turbo
          - s1
          - s2-pro
          - null
          description: Select the voice model used for the selected voice. Each provider has a set of available voice models. Set to null to remove voice model selection, and default ones will apply. Check out dashboard for more details of each voice model.
        fallback_voice_ids:
          type:
          - array
          - 'null'
          items:
            type: string
          example:
          - cartesia-Cimo
          - minimax-Cimo
          description: 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.
        voice_temperature:
          type: number
          example: 1
          description: Controls how stable the voice is. Value ranging from [0,2]. Lower value means more stable, and higher value means more variant speech generation. Check the dashboard to see what provider supports this feature. If unset, default value 1 will apply.
        voice_speed:
          type: number
          minimum: 0.5
          maximum: 2
          example: 1
          description: 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.
        enable_dynamic_voice_speed:
          type: boolean
          example: true
          description: If set to true, will enable dynamic voice speed adjustment based on the user's speech rate and conversation context. If unset, default value false will apply.
        enable_dynamic_responsiveness:
          type: boolean
          example: true
          description: If set to true, the agent will dynamically adjust how quickly it responds based on the user's speech rate and past turn-taking behavior in the call. If unset, default value false will apply.
        volume:
          type: number
          example: 1
          description: 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.
        voice_emotion:
          type:
          - string
          - 'null'
          enum:
          - calm
          - sympathetic
          - happy
          - sad
          - angry
          - fearful
          - surprised
          - null
          example: calm
          description: 'Controls the emotional tone of the agent''s voice. Currently supported for Cartesia and Minimax TTS providers. If unset, no emotion will be used.

            '
        responsiveness:
          type: number
          minimum: 0
          maximum: 1
          example: 1
          description: 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.
        interruption_sensitivity:
          type: number
          minimum: 0
          maximum: 1
          example: 1
          description: 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.
        enable_backchannel:
          type: boolean
          example: true
          description: 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.
        backchannel_frequency:
          type: number
          example: 0.9
          description: 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_words:
          type:
          - array
          - 'null'
          items:
            type: string
          example:
          - yeah
          - uh-huh
          description: 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.
        reminder_trigger_ms:
          type: number
          example: 10000
          description: 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_max_count:
          type: integer
          example: 2
          description: 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.
        ambient_sound:
          type:
          - string
          - 'null'
          enum:
          - coffee-shop
          - convention-hall
          - summer-outdoor
          - mountain-outdoor
          - static-noise
          - call-center
          - null
          description: '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_volume:
          type: number
          example: 1
          description: 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.
        language:
          oneOf:
          - $ref: '#/components/schemas/LanguageLegacy'
          - type: array
            items:
              $ref: '#/components/schemas/Language'
          description: Specifies what language(s) the agent will operate in. Accepts either a single scalar locale (e.g. `en-US`), the legacy scalar value `multi` for multilingual support, or an array of concrete locale codes for explicit multi-locale selection (e.g. `["en-US","es-ES"]`). The array form must contain concrete locale codes only — the `multi` value is valid only as the scalar legacy form and must not appear inside an array. Single-element arrays are normalized to the equivalent scalar on output. If unset, defaults to `en-US`.
        webhook_url:
          type:
          - string
          - 'null'
          example: https://webhook-url-here
          description: 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_events:
          type:
          - array
          - 'null'
          items:
            type: string
            enum:
            - call_started
            - call_ended
            - call_analyzed
            - transcript_updated
            - transfer_started
            - transfer_bridged
            - transfer_cancelled
            - transfer_ended
          description: Which webhook events this agent should receive. If not set, defaults to call_started, call_ended, call_analyzed.
        webhook_timeout_ms:
          type: integer
          example: 10000
          description: The timeout for the webhook in milliseconds. If not set, default value of 10000 will apply.
        boosted_keywords:
          type:
          - array
          - 'null'
          items:
            type: string
          example:
          - retell
          - kroger
          description: 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.
        data_storage_setting:
          type: string
          enum:
          - everything
          - everything_except_pii
          - basic_attributes_only
          example: everything
          description: '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_retention_days:
          type:
          - integer
          - 'null'
          minimum: 1
          maximum: 730
          example: 30
          description: Number of days to retain call/chat data before automatic deletion. Must be between 1 and 730 days. If not set, data is retained forever (no automatic deletion).
        opt_in_signed_url:
          type: boolean
          example: true
          description: 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.
        signed_url_expiration_ms:
          type:
          - integer
          - 'null'
          example: 86400000
          description: The expiration time for the signed url in milliseconds. Only applicable when opt_in_signed_url is true. If not set, default value of 86400000 (24 hours) will apply.
        pronunciation_dictionary:
          type:
          - array
          - 'null'
          items:
            type: object
            required:
            - word
            - alphabet
            - phoneme
            properties:
              word:
                type: string
                example: actually
                description: The string of word / phrase to be annotated with pronunciation.
              alphabet:
                type: string
                enum:
                - ipa
                - cmu
                example: ipa
                description: The phonetic alphabet to be used for pronunciation.
              phoneme:
                type: string
                example: ˈæktʃuəli
                description: Pronunciation of the word in the format of a IPA / CMU pronunciation.
          description: A list of words / phrases and their pronunciation to be used to guide the audio synthesize for consistent pronunciation. Check the dashboard to see what provider supports this feature. Set to null to remove pronunciation dictionary from this agent.
        end_call_after_silence_ms:
          type: integer
          example: 600000
          description: 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).
        max_call_duration_ms:
          type: integer
          example: 3600000
          description: 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).
        voicemail_message:
          type: string
          example: Hi, please give us a callback.
          description: The message to be played when the call enters a voicemail. Note that this feature is only available for phone calls. If you want to hangup after hitting voicemail, set this to empty string.
        voicemail_detection_timeout_ms:
          type: integer
          example: 30000
          description: Configures when to stop running voicemail detection, as it becomes unlikely to hit voicemail after a couple minutes, and keep running it will only have negative impact. The minimum value allowed is 5,000 ms (5 s), and maximum value allowed is 180,000 (3 minutes). By default, this is set to 30,000 (30 s).
        voicemail_option:
          type:
          - object
          - 'null'
          properties:
            action:
              $ref: '#/components/schemas/VoicemailAction'
            detection_prompt:
              type:
              - string
              - 'null'
              maxLength: 2000
              description: Optionally describe what should be treated as voicemail. Leave as null to use the default definition.
          required:
          - action
          description: 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.
          example:
            action:
              type: static_text
              text: Please give us a callback tomorrow at 10am.
        ivr_option:
          type:
          - object
          - 'null'
          properties:
            action:
              $ref: '#/components/schemas/IvrAction'
            detection_prompt:
              type:
              - string
              - 'null'
              maxLength: 2000
              description: Optionally describe what should be treated as an IVR. Leave as null to use the default definition.
          required:
          - action
          description: If this option is set, the call will try to detect IVR in the first 3 minutes of the call. Actions defined will be applied when the IVR is detected. Set this to null to disable IVR detection.
          example:
            action:
              type: hangup
        call_screening_option:
          $ref: '#/components/schemas/CallScreeningOption'
        post_call_analysis_data:
          type:
          - array
          - 'null'
          items:
            $ref: '#/components/schemas/PostCallAnalysisData'
          description: 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_model:
          $ref: '#/components/schemas/NullableLLMModel'
          example: gpt-4.1-mini
          description: The model to use for post call analysis. Default to gpt-4.1.
        analysis_successful_prompt:
          type:
          - string
          - 'null'
          maxLength: 2000
          example: The agent finished the task and the call was complete without being cutoff.
          description: Prompt to determine whether the post call or chat analysis should mark the interaction as successful. Set to null to use the default prompt.
        analysis_summary_prompt:
          type:
          - string
          - 'null'
          maxLength: 2000
          example: Summarize the outcome of the conversation in two sentences.
          description: Prompt to guide how the post call or chat analysis summary should be generated. When unset, the default system prompt is used. Set to null to use the default prompt.
        analysis_user_sentiment_prompt:
          type:
          - string
          - 'null'
          maxLength: 2000
          example: Evaluate the user's sentiment based on their tone and satisfaction level.
          description: Prompt to guide how the post call or chat analysis should evaluate user sentiment. When unset, the default system prompt is used. Set to null to use the default prompt.
        begin_message_delay_ms:
          type: integer
          example: 1000
          description: 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.
        ring_duration_ms:
          type: integer
          minimum: 5000
          maximum: 300000
          example: 30000
          description: 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, 300000].
        stt_mode:
          type: string
          enum:
          - fast
          - accurate
          - custom
          example: fast
          description: If set, determines whether speech to text should focus on latency or accuracy. Default to fast mode. When set to custom, custom_stt_config must be provided.
        custom_stt_config:
          type:
          - object
          - 'null'
          description: Custom STT configuration. Only used when stt_mode is set to custom.
          properties:
            provider:
              allOf:
              - $ref: '#/components/schemas/AsrProvider'
              description: The STT provider to use.
            endpointing_ms:
              type: integer
              description: Endpointing timeout in milliseconds. Minimum is 100 for Azure, 10 for Deepgram, 500 for Soniox
          required:
          - provider
          - endpointing_ms
        vocab_specialization:
          type: string
          enum:
          - general
          - medical
          example: general
          description: 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.
        allow_user_dtmf:
          type: boolean
          example: true
          description: If set to true, DTMF input will be accepted and processed. If false, any DTMF input will be ignored. Default to true.
        allow_dtmf_interruption:
          type: boolean
          example: false
          description: If set to true, DTMF input will interrupt the agent even when interruption_sensitivity is 0. Can be overridden per conversation or subagent node. Default to false.
        user_dtmf_options:
          type:
          - object
          - 'null'
          properties:
            digit_limit:
              type:
              - number
              - 'null'
              description: 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.
              minimum: 1
              maximum: 50
            termination_key:
              type:
              - string
              - 'null'
              description: A single key that signals the end of DTMF input. Acceptable values include any digit (0-9), the pound/hash symbol (#), or the asterisk (*).
              example: '#'
            timeout_ms:
              type: integer
              description: The time (in milliseconds) to wait for user DTMF input before timing out. The timer resets with each digit received.
              minimum: 1000
              maximum: 15000
        denoising_mode:
          type: string
          enum:
          - no-denoise
          - noise-cancellation
          - noise-and-background-speech-cancellation
          example: noise-cancellation
          description: If set, determines what denoising mode to use. Use "no-denoise" to bypass all audio denoising. Default to noise-cancellation.
        pii_config:
          $ref: '#/components/schemas/PIIConfig'
          description: Configuration for PII scrubbing from transcripts and recordings.
        guardrail_config:
          $ref: '#/components/schemas/GuardrailConfig'
          description: Configuration for guardrail checks to detect and prevent prohibited topics in agent output and user input.
        handbook_config:
          $ref: '#/components/schemas/VoiceHandbookConfig'
          description: Toggle behavior presets on/off to influence agent response style and behaviors.
   

# --- truncated at 32 KB (43 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/retell-ai/refs/heads/main/openapi/retell-ai-create-agent-api-openapi.yml