Browse the API reference

Calls

Place a call

View as Markdown
posthttps://www.getrevox.com/api/call

Place a new outbound call order. Provide either an existing assistant ID or a custom assistant configuration. The call can be scheduled for a specific time or started immediately. A single call order may be resolved over multiple call attempts spanning up to a few days, with automatic retries when voicemail is detected. You can also set concurrency limits and pass prompt variables for dynamic personalization.

Request body

  • phone_numberstringrequired

    The phone number to call in the E.164 format. Example: +1234567890

  • skip_calling_windowboolean

    Bypass the calling-window check for this call so it dials even outside the assistant's configured window. Use for immediate 'call now' dials.

  • timezonestringnullable

    IANA timezone in which this call's calling windows and allowed days are evaluated, in place of the assistant's call_retry_config.timezone, for this call only. Examples: 'America/Los_Angeles', 'Europe/Paris'. Null: the callee's own timezone, derived from the country of phone_number. Omitted: the assistant's setting. Use it when you know where the callee is better than their country code does, e.g. a US number on Pacific time.

  • from_phone_numberstring

    The phone number to use for making the call (e.g., +1234567890). If not provided, uses the default trunk.

  • call_twice_in_a_rowboolean

    Double call for this call only, in place of the assistant's call_retry_config.call_twice_in_a_row. True: if the first attempt reaches nobody (no answer, declined, voicemail, call screening nobody took), the second attempt is dialed within seconds, from the same caller number. Each call is an attempt: the double call counts as 2 when both calls happen, so true raises a max_retry_attempts of 1 to 2. Omitted: the assistant's setting.

  • prompt_variablesmap of string

    Variables to interpolate into the prompt. Wether you use an assistant_id or an assistant object, this will be used to interpolate the variables into the prompt.

  • metadatamap of string

    Metadata to store with the call.

  • assistant_idstring (uuid)

    The ID of the assistant to use for this call.

  • assistantobject

    You can provide a custom assistant configuration here. If you don't provide an assistant_id, this assistant object will be used for this call.

    Show 48 fields
    • typeenum (string)

      Assistant kind. 'standalone' (default) is a normal assistant, 'multi-step' orchestrates a flow of sub-assistants, 'sub-assistant' is a step inside a multi-step flow (hidden from the assistants list). Flow transitions are managed via the /assistants/:id/edges endpoints, not on the assistant itself.

      One ofstandalonemulti-stepsub-assistant

    • positionobjectnullable

      Canvas position of this assistant's node in its multi-step flow editor.

      Show 2 fields
      • xnumberrequired
      • ynumberrequired
    • start_step_namestringnullable

      Name of a multi-step flow's start step. Defaults to the assistant's name.

      max length 255

    • promptstringrequired

      The prompt to use for the call. This will be given to the LLM (gpt-4.1)

    • post_call_promptstringnullable

      Instructions the agent follows once the call has ended: who to email, when to text, what to post on Slack or Teams. Plain language, no template syntax. Empty or null means no post-call agent runs.

    • first_sentencestring

      The first sentence to use for the call. This will be given to the LLM

    • first_sentence_modeenum (string)

      How the first sentence should be handled. "generated" means the LLM will generate a response based on the first_sentence instruction. "static" means the first_sentence will be spoken exactly as provided. "none" means the agent will not speak first and will wait for the user.

      One ofgeneratedstaticnone

    • end_of_call_sentencestring

      Optional message to say when the agent decides to end the call.

    • voiceobject

      The voice to use for the call. You can get the list of voices using the /voices endpoint

      Show 5 fields
      • providerenum (string)required

        The provider of the voice.

        One ofcartesiaelevenlabsgradium

      • idstringrequired

        The ID of the voice.

        min length 1

      • speednumber

        The speed of the voice. Range depends on provider: Cartesia 0.6–1.5, ElevenLabs 0.7–1.2, Gradium 0.6–1.5. Default is 1.0.

        min 0.6 · max 1.5

      • volumenumber

        Volume of the voice (Cartesia only). 0.5–2.0, default 1.0. Ignored for other providers.

        min 0.5 · max 2

      • modelenum (string)

        Cartesia TTS model (Cartesia only). Defaults to sonic-3.6 when omitted. Ignored for other providers.

        One ofsonic-3sonic-3.5sonic-3.6

    • voice_languagesarray of objectnullable

      Extra languages for a multilingual assistant, each with its own voice (any provider). A call picks one with a language entry in its prompt_variables (a language code such as "es", or a name such as "Spanish"); otherwise the phone number's country picks one, and failing that the call runs in the language of voice, which cannot be listed here. A changed voice is applied to the calls in that language that have not completed yet; a language still used by such a call cannot be removed.

      Show 2 fields
      • languageenum (string)required

        The language contacts are called in with this voice.

        One ofenfresdeitptruzh

      • voiceobjectrequired

        The voice used for contacts whose language is this language.

        Show 5 fields
        • providerenum (string)required

          The provider of the voice.

          One ofcartesiaelevenlabsgradium

        • idstringrequired

          The ID of the voice.

          min length 1

        • speednumber

          The speed of the voice. Range depends on provider: Cartesia 0.6–1.5, ElevenLabs 0.7–1.2, Gradium 0.6–1.5. Default is 1.0.

          min 0.6 · max 1.5

        • volumenumber

          Volume of the voice (Cartesia only). 0.5–2.0, default 1.0. Ignored for other providers.

          min 0.5 · max 2

        • modelenum (string)

          Cartesia TTS model (Cartesia only). Defaults to sonic-3.6 when omitted. Ignored for other providers.

          One ofsonic-3sonic-3.5sonic-3.6

    • cartesia_dictionary_pronunciation_idstringnullable

      Optional Cartesia pronunciation dictionary ID to use for this assistant's calls. Set null to unlink it.

      min length 1

    • llm_modelone of
      Show 3 variants
      1. One ofRecommendedobject

        • typestring (constant)required

          The LLM Revox currently recommends for voice agents, chosen server-side and upgraded without any change on your side. No per-assistant configuration.

          Always "recommended"

      2. One ofGpt41Priorityobject

        • typestring (constant)required

          OpenAI gpt-4.1 on the priority tier, with gpt-4.1-mini answering a turn when gpt-4.1 is slow to respond. No per-assistant configuration.

          Always "gpt-4.1-priority"

      3. One ofRealtimeobject

        • typestring (constant)required

          Use a model from Realtime.

          Always "realtime"

        • providerenum (string)required

          The provider to use from Realtime. eg: openai, google.

          One ofopenaigoogle

        • realtime_model_idstringrequired

          The model ID to use from Realtime. eg: gpt-4.1

        • realtime_voice_idstring

          Output voice for the realtime provider (e.g. OpenAI: marin; Gemini: Puck).

          min length 1

    • webhook_urlstring

      The webhook URL to call when the call is completed.

    • max_call_duration_secsnumber

      The maximum duration of the call in seconds. This is the maximum time the call will be allowed to run.

    • max_duration_end_messagestringnullable

      Optional message the agent will say, without being interruptible, when the call reaches its max duration. Kept short so it fits inside the farewell buffer. If not set, the call ends silently.

      max length 150

    • structured_output_configarray of StructuredOutputField

      The structured output config to use for the call. This is used to extract the data from the call (like email, name, company name, etc.).

    • structured_output_promptstringnullable

      Custom prompt for structured data extraction. If not provided, a default prompt is used. Available variables: {{transcript}}, {{call_direction}}, {{user_phone_number}}, {{agent_phone_number}}.

    • call_retry_configCallRetryConfig
    • background_soundenum (string)nullable

      Ambient background sound to play during the call. null/omitted disables it.

      One ofaudio/office.oggaudio/waves.m4a

    • background_sound_volumenumber

      Volume of the ambient background sound (0 = silent, 1 = max).

      min 0 · max 1

    • thinking_soundenum (string)nullable

      Audio clip to play while the agent is processing a response. One of the built-in LiveKit audio clips; null/omitted disables it.

      One ofcity-ambience.oggforest-ambience.oggoffice-ambience.oggcrowded-room.oggkeyboard-typing.oggkeyboard-typing2.ogghold_music.ogg

    • thinking_sound_volumenumber

      Volume of the thinking sound (0 = silent, 1 = max).

      min 0 · max 1

    • thinking_sound_probabilitynumber

      Probability [0..1] that the thinking sound plays on any given turn; otherwise the agent is silent while thinking.

      min 0 · max 1

    • transfer_destinationsarray of objectnullable

      Where calls can be transferred to when users ask to speak to a human. With a single entry the assistant always transfers there; with several, it picks one at transfer time by applying the routing rules written in the assistant's own prompt (which refer to the destination labels). Empty or null disables transfer.

      Show 2 fields
      • labelstringrequired

        Human-meaningful name for this destination (e.g. "Sales"). The assistant's prompt refers to these labels when describing who to transfer to.

        min length 1 · max length 60

      • phone_numberstringrequired

        Destination phone number in E.164 format (e.g. +1234567890).

    • human_transfer_modeenum (string)nullable

      When transfer_destinations is non-empty: "warm" (AI bridges) or "cold" (SIP REFER; trunk must allow REFER/PSTN). Omit or null when transfer is disabled.

      One ofwarmcold

    • warm_transfer_summary_instructionsstringnullable

      When using warm transfer: extra instructions for the supervisor handoff summary. If null or empty, the API uses the product default briefing when the call is loaded for the agent.

    • warm_transfer_voice_speednumbernullable

      When using warm transfer: voice speed used only while the AI briefs the human colleague. Same range as voice.speed. Omit or null to brief at the assistant's voice speed.

      min 0.6 · max 1.5

    • ivr_navigation_enabledboolean

      Enable IVR navigation tools. When enabled, the assistant can send DTMF tones and skip turns to navigate phone menus.

    • voicemail_messagestringnullable

      If set, when voicemail is detected the agent will speak this message then hang up; if null, hang up immediately. Left on the first attempt only (second dial of a double call). Takes the same {{variables}} as the prompt (e.g. "Hi {{first_name}}, this is Julie from Acme, please call us back.").

    • stt_contextobjectnullable

      Assistant-level speech-to-text context: structured general key/value pairs plus a list of domain terms. Prompt-derived context is merged in without replacing existing entries.

      Show 2 fields
      • generalarray of objectrequired

        Default []

        Show 2 fields
        • keystringrequired

          min length 1

        • valuestringrequired

          min length 1

      • termsarray of stringrequired

        Default []

    • stt_modelenum (string)

      Transcriber (speech-to-text) model. Defaults to the newest Soniox realtime model when omitted.

      One ofstt-rt-v4stt-rt-v5

    • stt_endpoint_sensitivitynumbernullable

      Soniox endpoint sensitivity override (-1 to 1). Higher values finalize transcripts sooner. Null or omitted: the agent's default tuning.

      min -1 · max 1

    • stt_endpoint_latency_levelintegernullable

      Soniox endpoint latency adjustment level override (0 to 3). Higher values reduce endpoint latency at a slight accuracy cost. Null or omitted: the agent's default tuning.

      min 0 · max 3

    • stt_bvc_filter_enabledboolean

      When false, the agent transcribes the raw caller track instead of the BVC noise-cancellation output. Default true.

    • krisp_viva_filter_enabledboolean

      When true, the agent's noise-cancellation filter is Krisp VIVA Tel instead of the legacy BVCTelephony. Default false.

    • first_sentence_delay_msinteger

      Delay in milliseconds before speaking the first sentence. Default: 400.

      min 0 · max 9007199254740991

    • calendlyobjectnullable

      Deprecated: an assistant now books on any number of calendars, managed with the assistant calendars endpoints and listed in calendars. This field stands for the assistant's first ready calendar of this provider: setting it creates or updates that calendar, null removes it. The dashboard ignores it.

      Show 2 fields
      • connection_idstringrequired

        The connection ID representing the link between your Calendly account and Revox.

      • event_type_idstringrequired

        The Calendly event type to schedule. (eg: https://api.calendly.com/event_types/b2330295-2a91-4a1d-bb73-99e7707663d5)

        min length 1

    • calobjectnullable

      Deprecated: an assistant now books on any number of calendars, managed with the assistant calendars endpoints and listed in calendars. This field stands for the assistant's first ready calendar of this provider: setting it creates or updates that calendar, null removes it. The dashboard ignores it.

      Show 2 fields
      • connection_idstringrequired

        The connection ID representing the link between your Cal.com account and Revox.

      • event_type_idstringrequired

        The Cal.com event type to schedule. (eg: 7081322)

        min length 1

    • google_calendarobjectnullable

      Deprecated: an assistant now books on any number of calendars, managed with the assistant calendars endpoints and listed in calendars. This field stands for the assistant's first ready calendar of this provider: setting it creates or updates that calendar, null removes it. The dashboard ignores it.

      Show 8 fields
      • calendar_idstringrequired

        The Google calendar to book on. (eg: primary)

      • time_zonestringrequired

        The timezone of the opening hours. (eg: Europe/Paris)

      • duration_minutesintegerrequired

        min 5 · max 480Default 30

      • daysarray of integerrequired

        The open days, 0 is Sunday.

        Default [1,2,3,4,5]

      • start_timestringrequired

        pattern ^\d{2}:\d{2}$Default "09:00"

      • end_timestringrequired

        pattern ^\d{2}:\d{2}$Default "18:00"

      • google_meetbooleanrequired

        Adds a Google Meet link to the meeting.

        Default true

      • connection_idstringrequired

        The connection ID representing the link between your Google account and Revox.

    • hubspotobjectnullable

      HubSpot Meetings config. When set with at least one meeting link, the agent can read a rep's real availability and book the meeting natively in HubSpot during the call.

      Show 4 fields
      • connection_idstringrequired

        The Nango connection ID linking the org's HubSpot account to Revox.

      • precall_lookup_enabledbooleanrequired

        Resolve the caller against HubSpot contacts before answering an inbound call, filling the contact_* prompt variables (contact_name, contact_owner, contact_lead_status, contact_has_open_deal). Off by default: it costs API calls before the phone is picked up.

        Default false

      • meeting_linksarray of objectrequired

        Scheduling pages the agent can book on during a call — typically one per sales rep plus a round-robin team page marked as the fallback.

        Default []

        Show 5 fields
        • slugstringrequired

          HubSpot scheduling page slug, as returned by the meeting-links API (e.g. 'julien-marchand').

          min length 1

        • labelstringrequired

          Name the agent recognises for this calendar (e.g. 'Julien Marchand'). Listed in the prompt and matched against what the caller asks for.

          min length 1

        • duration_msintegerrequired

          Meeting duration in milliseconds, chosen among the durations the scheduling page offers (e.g. 1800000 for 30 minutes).

          max 9007199254740991 · > 0

        • is_fallbackbooleanrequired

          Marks the round-robin calendar the agent falls back to when the requested rep has no slot. At most one meeting link may set this.

        • booking_urlstringrequirednullable

          Public URL of the scheduling page (e.g. https://meetings-eu1.hubspot.com/julien). The agent books through the API and only texts this link to the caller when the booking fails and the call can receive an SMS. Null on calendars saved before this field existed.

          Default null

      • post_call_syncobject

        Sends call data back to HubSpot after the call. Off until set: connecting HubSpot to book meetings must not start writing to the CRM. Always present in responses; omit it on update to leave the current setting untouched.

        Show 2 fields
        • enabledbooleanrequired

          Records calls in HubSpot after they end: the contact is created or updated from the phone number and the call is logged on its timeline. By default every call a person answered is recorded. When the post-call prompt talks about the CRM (in plain words or by mentioning the crm_push_call tool), the post-call agent decides instead which calls are recorded and what the logged call says.

          Default false

        • field_mappingarray of objectrequired

          Maps extracted call fields (structured_output / prompt variables) onto HubSpot contact properties.

          Default []

          Show 2 fields
          • sourcestringrequired

            Source key to read from the call: a structured_output field name, falling back to a prompt variable of the same name.

            min length 1

          • hubspot_propertystringrequired

            Destination HubSpot contact property, by internal name (e.g. 'email', 'company', or a custom 'budget').

            min length 1

    • slackobjectnullable

      Slack notification config. When set, posts a message to the chosen channel after a call ends with one of the configured outcomes.

      Show 2 fields
      • connection_idstringrequired

        The Nango connection ID linking the org's Slack workspace to Revox.

      • channelsarray of objectrequired

        The Slack channels the post-call agent may post to. It resolves the channel it was told to use against this list and cannot reach any other.

        Show 2 fields
        • idstringrequired

          The Slack channel ID (e.g. 'C01234567').

        • namestringnullable

          Human-readable Slack channel name, cached for display in the UI and given to the LLM when the agent prompt routes by channel name.

    • teamsobjectnullable

      Microsoft Teams config. When set with at least one channel, the post-call agent can post to those channels when the post-call instructions ask for it.

      Show 2 fields
      • connection_idstringrequired

        The Nango connection ID linking a Microsoft Teams account to Revox. Messages are posted as that account.

      • channelsarray of objectrequired

        The Teams channels the post-call agent may post to. It resolves the channel it was told to use against this list and cannot reach any other.

        Show 4 fields
        • idstringrequired

          The Microsoft Teams channel ID (e.g. '19:561fbdbb...@thread.tacv2').

        • namestringnullable

          Human-readable channel name, cached for display in the UI and given to the LLM when the agent prompt routes by channel name.

        • team_idstringrequired

          The ID of the team the channel belongs to. Needed to post.

        • team_namestringnullable

          Human-readable team name. Channel names repeat across teams (every team has a 'General'), so the team name is what tells two of them apart.

    • zohoobjectnullable

      Zoho CRM integration config. When set, upserts the prospect (keyed on phone) into the chosen module and attaches a Note with the call summary after a call ends with one of the configured outcomes.

      Show 5 fields
      • connection_idstringrequired

        The Nango connection ID linking the org's Zoho CRM account to Revox.

      • modulestringrequired

        Zoho module the prospect record is upserted into (e.g. 'Leads' or 'Contacts').

        min length 1

      • log_call_activitybooleanrequired

        When true, also log the call as a record in Zoho's Calls module (related to the upserted prospect via Who_Id).

      • field_mappingarray of objectrequired

        Maps extracted call fields (structured_output / prompt variables) onto Zoho field API names on the upserted record.

        Show 2 fields
        • sourcestringrequired

          Source key to read from the call: a structured_output field name, falling back to a prompt variable of the same name.

          min length 1

        • zoho_fieldstringrequired

          Destination Zoho field API name on the upserted record (e.g. 'Email', 'Company', or a custom 'Budget__c').

          min length 1

      • templatestringnullable

        Optional Note body template. Supports {{summary}}, {{outcome}}, {{phone}}, {{call_url}}, {{assistant_name}}, {{campaign_name}}, {{transcript}}, plus prompt_variables and structured_output keys. When null/empty a default note (outcome + summary + auto-listed extracted fields) is used.

    • custom_toolsarray of objectnullable

      Custom API tools the assistant can call during conversations. Each tool defines an HTTP endpoint with variable substitution.

      Show 8 fields
      • namestringrequired

        Unique tool name in lowercase_snake_case (e.g. check_inventory)

        min length 1 · pattern ^[a-z][a-z0-9_]*$

      • descriptionstringrequired

        Human-readable description of what the tool does, used by the LLM to decide when to call it

        min length 1

      • methodenum (string)required

        HTTP method to use when calling the API endpoint

        One ofGETPOSTPUTPATCHDELETE

      • urlstringrequired

        Full URL of the API endpoint. Supports {{variable}} placeholders for dynamic values

        min length 1

      • headersarray of objectrequired

        HTTP headers to include in the request. Values support {{variable}} placeholders

        Default []

        Show 2 fields
        • keystringrequired

          min length 1

        • valuestringrequired
      • query_paramsarray of objectrequired

        Query string parameters appended to the URL. Values support {{variable}} placeholders

        Default []

        Show 2 fields
        • keystringrequired

          min length 1

        • valuestringrequired
      • body_templatestringrequirednullable

        JSON body template for the request. Use quoted {{variable}} placeholders (e.g. "{{name}}") for dynamic values

        Default null

      • input_schemaarray of StructuredOutputFieldrequired

        Schema defining the parameters the LLM should extract from the conversation to pass to this tool

    • from_phone_numberstringnullable

      Override the default outbound phone number for calls placed with this assistant. Must be a phone number owned by the organization in E.164 format (e.g. +1234567890). When null, the organization's default phone number is used.

    • logo_urlstring (uri)nullable

      Public URL of the brand logo shown on the assistant's demo page. Upload a new logo via POST /assistants/:id/logo. Set explicitly to null to clear it.

    • precall_lookup_urlstringnullable

      Inbound calls only. URL fetched over HTTP GET right before the call is answered, with {{phone}} replaced by the caller's number in E.164 format (URL-encoded), to fill the {{variable}} placeholders the assistant declares. It answers either {"prompt_variables": {...}} or a flat JSON object whose top-level fields are the variables. The call is always answered: if the endpoint fails, takes more than 3 seconds, answers 404 or leaves a variable out, the missing variables are marked as not provided. Must be an http(s) URL containing {{phone}}. When null, no lookup is performed.

      max length 2000

    • precall_lookup_headersarray of objectnullable

      HTTP headers sent with the pre-call lookup request, e.g. an API key. Null or empty when the endpoint needs none.

      Show 2 fields
      • keystringrequired

        max length 200 · pattern ^[A-Za-z0-9!#$%&'*+.^_`|~-]+$

      • valuestringrequired

        min length 1 · max length 4000

  • concurrencyobject

    Limit the number of concurrent calls for a given concurrency key. The limit itself is set server-side; omit this to leave the call ungrouped (bounded only by your organization's limit).

    Show 1 field
    • keystringrequired

      Groups this call with every other call sharing the same key, for concurrency purposes.

  • campaignobject

    Group this call under a campaign, to follow its statistics in the dashboard. Nothing to create beforehand: the campaign exists as soon as a call names it, and it uses the assistant of that first call. Requires assistant_id, and cannot be combined with concurrency: the call follows the campaign's own concurrency limit, retry settings and pause. Returns 409 when the campaign was cancelled or uses another assistant. Calling the same number twice in a campaign counts as one contact.

    Show 1 field
    • namestringrequired

      The campaign's name, case-insensitive. Created on first use, reused by every later call that sends it.

      min length 1 · max length 255

  • scheduled_atone of

    Schedule the call to start at a specific date and time (ISO 8601 format). If not provided, the call will start immediately.

    Show 2 variants
    1. One ofstringstring (date-time)

    2. One ofOption 2any

Responses

200Success
402Not enough credits on the organization
  • errorstringrequired
  • codestring (constant)required

    Always "INSUFFICIENT_BALANCE"

409Conflict with the resource's current state
  • messagestring
  • errorstring
  • bodyErrorsobject

    The validation errors returned from the API.

    Show 1 field
    • issuesarray of objectrequired
      Show 3 fields
      • patharray of one ofrequired
        Show 2 variants
        1. One ofstringstring

        2. One ofnumbernumber

      • messagestringrequired
      • codestring