Place a call

POST/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.

Body ParametersJSONExpand Collapse

phone_number: string

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

assistant: optional object { prompt, after_call_sms_prompt, background_sound, 24 more }

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.

prompt: string

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

after_call_sms_prompt: optional string

Prompt / instructions for the after-call SMS. Supports {{variable}} placeholders. When null, no after-call SMS is sent.

background_sound: optional "audio/office.ogg"

The background sound to play during the call. Useful to give the impression that your AI agent is in an office, in the street, or anywhere else you want.

calendly: optional object { connection_id, event_type_id }

connection_id: string

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

event_type_id: string

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

call_retry_config: optional object { allowed_days, calling_windows, max_retry_attempts, timezone }

Configuration for call retry behavior including time windows, delays, and max iterations. If not provided, defaults will be used.

allowed_days: array of "monday" or "tuesday" or "wednesday" or 4 more

Days of the week when calls are allowed, in the recipient's timezone. Default: Monday through Friday.

One of the following:

"monday"

"tuesday"

"wednesday"

"thursday"

"friday"

"saturday"

"sunday"

calling_windows: array of object { calling_window_end_time, calling_window_start_time, retry_delay_seconds }

calling_window_end_time: string

End time for the calling window in the recipient's timezone (or timezone_override if provided). Format: 'HH:mm' (24-hour) or 'H:mma' (12-hour). Examples: '17:00', '6pm'. Default: '18:00'.

calling_window_start_time: string

Start time for the calling window in the recipient's timezone (or timezone_override if provided). Format: 'HH:mm' (24-hour) or 'H:mma' (12-hour). Examples: '09:00', '10am'. Default: '10:00'.

retry_delay_seconds: number

Delay between retry attempts in seconds. Default: 7200 (2 hours).

exclusiveMinimum0

maximum9007199254740991

max_retry_attempts: number

Maximum number of call retry attempts. Default: 3.

exclusiveMinimum0

maximum9007199254740991

timezone: optional string

Optional IANA timezone identifier to override the automatic timezone detection from phone number. If not provided, timezone is determined from the recipient's phone number country code. Examples: 'America/New_York', 'Europe/Paris'.

custom_tools: optional array of object { body_template, description, headers, 5 more }

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

body_template: string

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

description: string

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

minLength1

headers: array of object { key, value }

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

key: string

minLength1

value: string

input_schema: array of object { name, required, type, 2 more }

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

minLength1

required: boolean

type: "string" or "number" or "boolean" or 3 more

One of the following:

"string"

"number"

"boolean"

"enum"

"date"

"datetime"

description: optional string

enum_options: optional array of string

method: "GET" or "POST" or "PUT" or 2 more

HTTP method to use when calling the API endpoint

One of the following:

"GET"

"POST"

"PUT"

"PATCH"

"DELETE"

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

minLength1

query_params: array of object { key, value }

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

key: string

minLength1

value: string

url: string

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

minLength1

email_notification_address: optional string

Email address to receive notifications when a call ends with a matching outcome.

formatemail

email_notification_outcomes: optional array of "not_interested" or "interested" or "completed" or 3 more

Which call outcomes trigger an email notification. E.g. ["interested", "completed"].

One of the following:

"not_interested"

"interested"

"completed"

"requested_callback_later"

"requested_callback_new_number"

"do_not_contact"

end_of_call_sentence: optional string

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

faq_items: optional array of object { answer, question }

FAQ items to associate with this assistant. When provided, replaces all existing FAQ items.

answer: string

question: string

first_sentence: optional string

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

first_sentence_delay_ms: optional number

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

minimum0

maximum9007199254740991

first_sentence_mode: optional "generated" or "static" or "none"

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 of the following:

"generated"

"static"

"none"

human_transfer_mode: optional "warm" or "cold"

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

One of the following:

"warm"

"cold"

ivr_navigation_enabled: optional boolean

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

llm_model: optional object { name, type } or object { openrouter_model_id, openrouter_provider, type } or object { api_key, api_url, model_name, type } or object { provider, realtime_model_id, type, realtime_voice_id }

One of the following:

UnionMember0 = object { name, type }

One of the following:

"gpt-4.1"

"ministral-3-8b-instruct"

type: "dedicated-instance"

UnionMember1 = object { openrouter_model_id, openrouter_provider, type }

openrouter_model_id: string

The model ID to use from OpenRouter. eg: openai/gpt-4.1

openrouter_provider: string

The provider to use from OpenRouter. eg: nebius, openai, azure, etc.

type: "openrouter"

Use a model from OpenRouter.

UnionMember2 = object { api_key, api_url, model_name, type }

api_key: string

API key sent as Bearer token to the custom endpoint.

minLength1

api_url: string

Base URL for the OpenAI-compatible API, e.g. https://api.together.xyz/v1

formaturi

model_name: string

Model name as expected by the provider, e.g. meta-llama/llama-3-70b

minLength1

type: "custom"

OpenAI-compatible chat completions API (bring your own endpoint and key).

UnionMember3 = object { provider, realtime_model_id, type, realtime_voice_id }

provider: "openai" or "google"

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

One of the following:

"openai"

"google"

realtime_model_id: string

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

type: "realtime"

Use a model from Realtime.

realtime_voice_id: optional string

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

minLength1

max_call_duration_secs: optional number

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

sms_enabled: optional boolean

Enable SMS tool during calls. When enabled, the agent can send SMS messages to the user on the call.

sms_template: optional string

Hardcoded SMS template to send during calls. When set, this exact text is sent instead of letting the agent generate the message. Supports {{variable}} placeholders.

structured_output_config: optional array of object { name, required, type, 2 more }

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.).

minLength1

required: boolean

type: "string" or "number" or "boolean" or 3 more

One of the following:

"string"

"number"

"boolean"

"enum"

"date"

"datetime"

description: optional string

enum_options: optional array of string

structured_output_prompt: optional string

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}}.

transfer_phone_number: optional string

Phone number to transfer calls to when users request to speak to a human agent in E.164 format (e.g. +1234567890).

voice: optional object { id, provider, speed, volume }

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

id: string

The ID of the voice.

minLength1

provider: "cartesia" or "elevenlabs"

The provider of the voice.

One of the following:

"cartesia"

"elevenlabs"

speed: optional number

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

minimum0.6

maximum1.5

volume: optional number

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

minimum0.5

maximum2

voicemail_message: optional string

If set, when voicemail is detected the agent will speak this message then hang up; if null, hang up immediately.

voicemail_sms_prompt: optional string

SMS message to send when the call reaches voicemail. Supports {{variable}} placeholders. When null, no SMS is sent on voicemail.

warm_transfer_summary_instructions: optional string

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.

webhook_url: optional string

The webhook URL to call when the call is completed.

assistant_id: optional string

The ID of the assistant to use for this call.

formatuuid

concurrency: optional object { key, max }

Limit the number of concurrent calls for a given concurrency key.

key: string

The key for which you want to limit the number of concurrent calls.

max: number

The maximum number of concurrent calls to allow for the given concurrency key.

minimum1

force_now: optional boolean

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

from_phone_number: optional string

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

metadata: optional map[string]

Metadata to store with the call.

prompt_variables: optional map[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.

scheduled_at: optional string or unknown

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

One of the following:

UnionMember0 = string

UnionMember1 = unknown

ReturnsExpand Collapse

call: object { id, assistant, call_attempts, 19 more }

This represent a call "order" that was requested by the user. A call order can be resolved over multiple call attempts spanning up to a few days.

id: string

The ID of the call.

assistant: object { id, after_call_sms_prompt, background_sound, 30 more }

id: string

after_call_sms_prompt: string

Prompt / instructions for the after-call SMS. Supports {{variable}} placeholders. When null, no after-call SMS is sent.

background_sound: "audio/office.ogg"

The background sound to play during the call. Useful to give the impression that your AI agent is in an office.

calendly: object { connection_id, event_type_id }

connection_id: string

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

event_type_id: string

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

call_retry_config: object { allowed_days, calling_windows, max_retry_attempts, timezone }

Configuration for call retry behavior including time windows, delays, and max iterations. If not provided, defaults will be used.

allowed_days: array of "monday" or "tuesday" or "wednesday" or 4 more

Days of the week when calls are allowed, in the recipient's timezone. Default: Monday through Friday.

One of the following:

"monday"

"tuesday"

"wednesday"

"thursday"

"friday"

"saturday"

"sunday"

calling_windows: array of object { calling_window_end_time, calling_window_start_time, retry_delay_seconds }

calling_window_end_time: string

End time for the calling window in the recipient's timezone (or timezone_override if provided). Format: 'HH:mm' (24-hour) or 'H:mma' (12-hour). Examples: '17:00', '6pm'. Default: '18:00'.

calling_window_start_time: string

Start time for the calling window in the recipient's timezone (or timezone_override if provided). Format: 'HH:mm' (24-hour) or 'H:mma' (12-hour). Examples: '09:00', '10am'. Default: '10:00'.

retry_delay_seconds: number

Delay between retry attempts in seconds. Default: 7200 (2 hours).

exclusiveMinimum0

maximum9007199254740991

max_retry_attempts: number

Maximum number of call retry attempts. Default: 3.

exclusiveMinimum0

maximum9007199254740991

timezone: optional string

created_at: unknown

custom_tools: array of object { body_template, description, headers, 5 more }

body_template: string

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

description: string

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

minLength1

headers: array of object { key, value }

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

key: string

minLength1

value: string

input_schema: array of object { name, required, type, 2 more }

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

minLength1

required: boolean

type: "string" or "number" or "boolean" or 3 more

One of the following:

"string"

"number"

"boolean"

"enum"

"date"

"datetime"

description: optional string

enum_options: optional array of string

method: "GET" or "POST" or "PUT" or 2 more

HTTP method to use when calling the API endpoint

One of the following:

"GET"

"POST"

"PUT"

"PATCH"

"DELETE"

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

minLength1

query_params: array of object { key, value }

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

key: string

minLength1

value: string

url: string

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

minLength1

email_notification_address: string

Email address to receive notifications when a call ends with a matching outcome.

formatemail

email_notification_outcomes: array of "not_interested" or "interested" or "completed" or 3 more

Which call outcomes trigger an email notification. E.g. ["interested", "completed"].

One of the following:

"not_interested"

"interested"

"completed"

"requested_callback_later"

"requested_callback_new_number"

"do_not_contact"

end_of_call_sentence: string

first_sentence: string

first_sentence_delay_ms: number

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

minimum-9007199254740991

maximum9007199254740991

first_sentence_mode: "generated" or "static" or "none"

One of the following:

"generated"

"static"

"none"

human_transfer_mode: "warm" or "cold"

Warm or cold transfer when transfer_phone_number is set; null when transfer is not configured.

One of the following:

"warm"

"cold"

ivr_navigation_enabled: boolean

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

llm_model: object { name, type } or object { openrouter_model_id, openrouter_provider, type } or object { api_key, api_url, model_name, type } or object { provider, realtime_model_id, type, realtime_voice_id }

One of the following:

UnionMember0 = object { name, type }

One of the following:

"gpt-4.1"

"ministral-3-8b-instruct"

type: "dedicated-instance"

UnionMember1 = object { openrouter_model_id, openrouter_provider, type }

openrouter_model_id: string

The model ID to use from OpenRouter. eg: openai/gpt-4.1

openrouter_provider: string

The provider to use from OpenRouter. eg: nebius, openai, azure, etc.

type: "openrouter"

Use a model from OpenRouter.

UnionMember2 = object { api_key, api_url, model_name, type }

api_key: string

API key sent as Bearer token to the custom endpoint.

minLength1

api_url: string

Base URL for the OpenAI-compatible API, e.g. https://api.together.xyz/v1

formaturi

model_name: string

Model name as expected by the provider, e.g. meta-llama/llama-3-70b

minLength1

type: "custom"

OpenAI-compatible chat completions API (bring your own endpoint and key).

UnionMember3 = object { provider, realtime_model_id, type, realtime_voice_id }

provider: "openai" or "google"

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

One of the following:

"openai"

"google"

realtime_model_id: string

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

type: "realtime"

Use a model from Realtime.

realtime_voice_id: optional string

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

minLength1

max_call_duration_secs: number

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

organization_id: string

prompt: string

sms_enabled: boolean

Enable SMS tool during calls. When enabled, the agent can send SMS messages to the user on the call.

sms_template: string

Hardcoded SMS template to send during calls. When set, this exact text is sent instead of letting the agent generate the message. Supports {{variable}} placeholders.

structured_output_config: array of object { name, required, type, 2 more }

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.).

minLength1

required: boolean

type: "string" or "number" or "boolean" or 3 more

One of the following:

"string"

"number"

"boolean"

"enum"

"date"

"datetime"

description: optional string

enum_options: optional array of string

structured_output_prompt: string

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}}.

transfer_phone_number: string

Phone number to transfer calls to when users request to speak to a human agent.

updated_at: unknown

voice: object { id, provider, speed, volume }

id: string

The ID of the voice.

minLength1

provider: "cartesia" or "elevenlabs"

The provider of the voice.

One of the following:

"cartesia"

"elevenlabs"

speed: optional number

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

minimum0.6

maximum1.5

volume: optional number

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

minimum0.5

maximum2

voicemail_message: string

If set, when voicemail is detected the agent will speak this message then hang up; if null, hang up immediately.

voicemail_sms_prompt: string

Prompt / instructions for the voicemail SMS. Supports {{variable}} placeholders. When null, no SMS is sent on voicemail.

warm_transfer_summary_instructions: string

Warm transfer only: instructions for the supervisor handoff summary; null when not configured or cold transfer.

webhook_url: string

The webhook URL to call when the call is completed.

faq_items: optional array of object { answer, question, id, 2 more }

answer: string

question: string

id: optional string

needs_human_answer: optional boolean

source: optional "human" or "ai"

One of the following:

"human"

"ai"

pending_faq_count: optional number

call_attempts: array of object { id, answered_at, dial_error, 10 more }

All call attempts for this call order, ordered by most recent first.

id: string

The ID of the call attempt.

answered_at: unknown

The time the call was answered.

dial_error: "number_non_attributed" or "too_many_calls" or "busy" or 5 more

The SIP error that occurred.

One of the following:

"number_non_attributed"

"too_many_calls"

"busy"

"temporarily_unavailable"

"no_answer"

"no_international_permission"

"precondition_failed"

"non_classified_error"

ended_at: unknown

The time the call ended.

phone_number: string

The phone number that was called. Formatted in E.164 format. Example: +1234567890

recording_url: string

The URL of the audio recording of the call.

result: "IVR" or "voicemail" or "human" or 2 more

One of the following:

"IVR"

"voicemail"

"human"

"unknown"

"ios-screening-filter"

started_at: unknown

The time the call started.

status: "queued" or "ringing" or "ongoing" or 2 more

The status of the call attempt.

One of the following:

"queued"

"ringing"

"ongoing"

"completed"

"error"

end_reason: optional string

Reason for ending the call when ended_by is 'agent'. E.g. 'tool_end_call', 'voicemail', 'transfer', 'ivr_no_navigate'.

ended_by: optional "agent" or "user" or "system"

Who ended the call: 'agent' (AI agent), 'user' (caller/callee hung up), or 'system' (e.g. max duration limit).

One of the following:

"agent"

"user"

"system"

structured_output: optional map[unknown]

The data extracted from the call, using the structured output config from the parent call object.

transcript: optional array of object { content, role, tool_arguments, 3 more }

The transcript of the call.

content: string

role: "user" or "assistant" or "tool"

One of the following:

"user"

"assistant"

"tool"

tool_arguments: optional map[unknown] or string

One of the following:

UnionMember0 = map[unknown]

UnionMember1 = string

tool_is_error: optional boolean

tool_name: optional string

tool_output: optional string

call_retry_config: object { allowed_days, calling_windows, max_retry_attempts, timezone }

Configuration for call retry behavior including time windows, delays, and max iterations. If not provided, defaults will be used.

allowed_days: array of "monday" or "tuesday" or "wednesday" or 4 more

Days of the week when calls are allowed, in the recipient's timezone. Default: Monday through Friday.

One of the following:

"monday"

"tuesday"

"wednesday"

"thursday"

"friday"

"saturday"

"sunday"

calling_windows: array of object { calling_window_end_time, calling_window_start_time, retry_delay_seconds }

calling_window_end_time: string

End time for the calling window in the recipient's timezone (or timezone_override if provided). Format: 'HH:mm' (24-hour) or 'H:mma' (12-hour). Examples: '17:00', '6pm'. Default: '18:00'.

calling_window_start_time: string

Start time for the calling window in the recipient's timezone (or timezone_override if provided). Format: 'HH:mm' (24-hour) or 'H:mma' (12-hour). Examples: '09:00', '10am'. Default: '10:00'.

retry_delay_seconds: number

Delay between retry attempts in seconds. Default: 7200 (2 hours).

exclusiveMinimum0

maximum9007199254740991

max_retry_attempts: number

Maximum number of call retry attempts. Default: 3.

exclusiveMinimum0

maximum9007199254740991

timezone: optional string

calls_count: number

The number of call attempts made.

campaign: object { id, name }

id: string

created_at: unknown

The time the call order was created.

direction: "inbound" or "outbound"

Whether the call is inbound or outbound.

One of the following:

"inbound"

"outbound"

first_sentence_delay_ms: number

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

minimum-9007199254740991

maximum9007199254740991

from_phone_number: string

The phone number that made the call. Formatted in E.164 format. Example: +1234567890

is_cancelled: boolean

DEPRECATED: Whether the call has been cancelled. This is derived from status. Use status instead.

is_completed: boolean

DEPRECATED: Whether the call has completed. This is derived from status. Use status instead.

last_call_attempt: object { id, answered_at, dial_error, 10 more }

This represent a single call attempt. A call attempt is a single call made to the phone number.

id: string

The ID of the call attempt.

answered_at: unknown

The time the call was answered.

dial_error: "number_non_attributed" or "too_many_calls" or "busy" or 5 more

The SIP error that occurred.

One of the following:

"number_non_attributed"

"too_many_calls"

"busy"

"temporarily_unavailable"

"no_answer"

"no_international_permission"

"precondition_failed"

"non_classified_error"

ended_at: unknown

The time the call ended.

phone_number: string

The phone number that was called. Formatted in E.164 format. Example: +1234567890

recording_url: string

The URL of the audio recording of the call.

result: "IVR" or "voicemail" or "human" or 2 more

One of the following:

"IVR"

"voicemail"

"human"

"unknown"

"ios-screening-filter"

started_at: unknown

The time the call started.

status: "queued" or "ringing" or "ongoing" or 2 more

The status of the call attempt.

One of the following:

"queued"

"ringing"

"ongoing"

"completed"

"error"

end_reason: optional string

Reason for ending the call when ended_by is 'agent'. E.g. 'tool_end_call', 'voicemail', 'transfer', 'ivr_no_navigate'.

ended_by: optional "agent" or "user" or "system"

Who ended the call: 'agent' (AI agent), 'user' (caller/callee hung up), or 'system' (e.g. max duration limit).

One of the following:

"agent"

"user"

"system"

structured_output: optional map[unknown]

The data extracted from the call, using the structured output config from the parent call object.

transcript: optional array of object { content, role, tool_arguments, 3 more }

The transcript of the call.

content: string

role: "user" or "assistant" or "tool"

One of the following:

"user"

"assistant"

"tool"

tool_arguments: optional map[unknown] or string

One of the following:

UnionMember0 = map[unknown]

UnionMember1 = string

tool_is_error: optional boolean

tool_name: optional string

tool_output: optional string

One of the following:

UnionMember0 = object { name, type }

One of the following:

"gpt-4.1"

"ministral-3-8b-instruct"

type: "dedicated-instance"

UnionMember1 = object { openrouter_model_id, openrouter_provider, type }

openrouter_model_id: string

The model ID to use from OpenRouter. eg: openai/gpt-4.1

openrouter_provider: string

The provider to use from OpenRouter. eg: nebius, openai, azure, etc.

type: "openrouter"

Use a model from OpenRouter.

UnionMember2 = object { api_key, api_url, model_name, type }

api_key: string

API key sent as Bearer token to the custom endpoint.

minLength1

api_url: string

Base URL for the OpenAI-compatible API, e.g. https://api.together.xyz/v1

formaturi

model_name: string

Model name as expected by the provider, e.g. meta-llama/llama-3-70b

minLength1

type: "custom"

OpenAI-compatible chat completions API (bring your own endpoint and key).

UnionMember3 = object { provider, realtime_model_id, type, realtime_voice_id }

provider: "openai" or "google"

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

One of the following:

"openai"

"google"

realtime_model_id: string

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

type: "realtime"

Use a model from Realtime.

realtime_voice_id: optional string

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

minLength1

metadata: map[string]

Metadata stored with the call.

organization_id: string

The ID of the organization that owns the call.

prompt_variables: map[string]

Variables used to interpolate the prompt.

scheduled_at: unknown

The time the call order is scheduled to start.

status: "initializing" or "queued_for_calling" or "calling" or 4 more

The status of the call.

One of the following:

"initializing"

"queued_for_calling"

"calling"

"scheduled"

"completed"

"cancelled"

"errored"

to_phone_number: string

The phone number that received the call. Formatted in E.164 format. Example: +1234567890

outcome: optional "not_interested" or "interested" or "completed" or 3 more

Business outcome of the call. Null if not computed or no transcript.

One of the following:

"not_interested"

"interested"

"completed"

"requested_callback_later"

"requested_callback_new_number"

"do_not_contact"

outcome_summary: optional string

LLM explanation for the outcome, when outcome was computed from the transcript.

Place a call

curl https://www.getrevox.com/api/call \
    -H 'Content-Type: application/json' \
    -H "Authorization: Bearer $REVOX_API_KEY" \
    -d '{
          "phone_number": "phone_number"
        }'

{
  "call": {
    "id": "id",
    "assistant": {
      "id": "id",
      "after_call_sms_prompt": "after_call_sms_prompt",
      "background_sound": "audio/office.ogg",
      "calendly": {
        "connection_id": "connection_id",
        "event_type_id": "event_type_id"
      },
      "call_retry_config": {
        "allowed_days": [
          "monday"
        ],
        "calling_windows": [
          {
            "calling_window_end_time": "calling_window_end_time",
            "calling_window_start_time": "calling_window_start_time",
            "retry_delay_seconds": 1
          }
        ],
        "max_retry_attempts": 1,
        "timezone": "timezone"
      },
      "created_at": {},
      "custom_tools": [
        {
          "body_template": "body_template",
          "description": "x",
          "headers": [
            {
              "key": "x",
              "value": "value"
            }
          ],
          "input_schema": [
            {
              "name": "x",
              "required": true,
              "type": "string",
              "description": "description",
              "enum_options": [
                "string"
              ]
            }
          ],
          "method": "GET",
          "name": "name",
          "query_params": [
            {
              "key": "x",
              "value": "value"
            }
          ],
          "url": "x"
        }
      ],
      "email_notification_address": "dev@stainless.com",
      "email_notification_outcomes": [
        "not_interested"
      ],
      "end_of_call_sentence": "end_of_call_sentence",
      "first_sentence": "first_sentence",
      "first_sentence_delay_ms": -9007199254740991,
      "first_sentence_mode": "generated",
      "human_transfer_mode": "warm",
      "ivr_navigation_enabled": true,
      "llm_model": {
        "name": "gpt-4.1",
        "type": "dedicated-instance"
      },
      "max_call_duration_secs": 0,
      "name": "name",
      "organization_id": "organization_id",
      "prompt": "prompt",
      "sms_enabled": true,
      "sms_template": "sms_template",
      "structured_output_config": [
        {
          "name": "x",
          "required": true,
          "type": "string",
          "description": "description",
          "enum_options": [
            "string"
          ]
        }
      ],
      "structured_output_prompt": "structured_output_prompt",
      "transfer_phone_number": "transfer_phone_number",
      "updated_at": {},
      "voice": {
        "id": "x",
        "provider": "cartesia",
        "speed": 0.6,
        "volume": 0.5
      },
      "voicemail_message": "voicemail_message",
      "voicemail_sms_prompt": "voicemail_sms_prompt",
      "warm_transfer_summary_instructions": "warm_transfer_summary_instructions",
      "webhook_url": "webhook_url",
      "faq_items": [
        {
          "answer": "answer",
          "question": "question",
          "id": "id",
          "needs_human_answer": true,
          "source": "human"
        }
      ],
      "pending_faq_count": 0
    },
    "call_attempts": [
      {
        "id": "id",
        "answered_at": {},
        "dial_error": "number_non_attributed",
        "ended_at": {},
        "phone_number": "phone_number",
        "recording_url": "recording_url",
        "result": "IVR",
        "started_at": {},
        "status": "queued",
        "end_reason": "end_reason",
        "ended_by": "agent",
        "structured_output": {
          "foo": "bar"
        },
        "transcript": [
          {
            "content": "content",
            "role": "user",
            "tool_arguments": {
              "foo": "bar"
            },
            "tool_is_error": true,
            "tool_name": "tool_name",
            "tool_output": "tool_output"
          }
        ]
      }
    ],
    "call_retry_config": {
      "allowed_days": [
        "monday"
      ],
      "calling_windows": [
        {
          "calling_window_end_time": "calling_window_end_time",
          "calling_window_start_time": "calling_window_start_time",
          "retry_delay_seconds": 1
        }
      ],
      "max_retry_attempts": 1,
      "timezone": "timezone"
    },
    "calls_count": 0,
    "campaign": {
      "id": "id",
      "name": "name"
    },
    "created_at": {},
    "direction": "inbound",
    "first_sentence_delay_ms": -9007199254740991,
    "from_phone_number": "from_phone_number",
    "is_cancelled": true,
    "is_completed": true,
    "last_call_attempt": {
      "id": "id",
      "answered_at": {},
      "dial_error": "number_non_attributed",
      "ended_at": {},
      "phone_number": "phone_number",
      "recording_url": "recording_url",
      "result": "IVR",
      "started_at": {},
      "status": "queued",
      "end_reason": "end_reason",
      "ended_by": "agent",
      "structured_output": {
        "foo": "bar"
      },
      "transcript": [
        {
          "content": "content",
          "role": "user",
          "tool_arguments": {
            "foo": "bar"
          },
          "tool_is_error": true,
          "tool_name": "tool_name",
          "tool_output": "tool_output"
        }
      ]
    },
    "llm_model": {
      "name": "gpt-4.1",
      "type": "dedicated-instance"
    },
    "metadata": {
      "foo": "string"
    },
    "organization_id": "organization_id",
    "prompt_variables": {
      "foo": "string"
    },
    "scheduled_at": {},
    "status": "initializing",
    "to_phone_number": "to_phone_number",
    "outcome": "not_interested",
    "outcome_summary": "outcome_summary"
  }
}

Returns Examples

{
  "call": {
    "id": "id",
    "assistant": {
      "id": "id",
      "after_call_sms_prompt": "after_call_sms_prompt",
      "background_sound": "audio/office.ogg",
      "calendly": {
        "connection_id": "connection_id",
        "event_type_id": "event_type_id"
      },
      "call_retry_config": {
        "allowed_days": [
          "monday"
        ],
        "calling_windows": [
          {
            "calling_window_end_time": "calling_window_end_time",
            "calling_window_start_time": "calling_window_start_time",
            "retry_delay_seconds": 1
          }
        ],
        "max_retry_attempts": 1,
        "timezone": "timezone"
      },
      "created_at": {},
      "custom_tools": [
        {
          "body_template": "body_template",
          "description": "x",
          "headers": [
            {
              "key": "x",
              "value": "value"
            }
          ],
          "input_schema": [
            {
              "name": "x",
              "required": true,
              "type": "string",
              "description": "description",
              "enum_options": [
                "string"
              ]
            }
          ],
          "method": "GET",
          "name": "name",
          "query_params": [
            {
              "key": "x",
              "value": "value"
            }
          ],
          "url": "x"
        }
      ],
      "email_notification_address": "dev@stainless.com",
      "email_notification_outcomes": [
        "not_interested"
      ],
      "end_of_call_sentence": "end_of_call_sentence",
      "first_sentence": "first_sentence",
      "first_sentence_delay_ms": -9007199254740991,
      "first_sentence_mode": "generated",
      "human_transfer_mode": "warm",
      "ivr_navigation_enabled": true,
      "llm_model": {
        "name": "gpt-4.1",
        "type": "dedicated-instance"
      },
      "max_call_duration_secs": 0,
      "name": "name",
      "organization_id": "organization_id",
      "prompt": "prompt",
      "sms_enabled": true,
      "sms_template": "sms_template",
      "structured_output_config": [
        {
          "name": "x",
          "required": true,
          "type": "string",
          "description": "description",
          "enum_options": [
            "string"
          ]
        }
      ],
      "structured_output_prompt": "structured_output_prompt",
      "transfer_phone_number": "transfer_phone_number",
      "updated_at": {},
      "voice": {
        "id": "x",
        "provider": "cartesia",
        "speed": 0.6,
        "volume": 0.5
      },
      "voicemail_message": "voicemail_message",
      "voicemail_sms_prompt": "voicemail_sms_prompt",
      "warm_transfer_summary_instructions": "warm_transfer_summary_instructions",
      "webhook_url": "webhook_url",
      "faq_items": [
        {
          "answer": "answer",
          "question": "question",
          "id": "id",
          "needs_human_answer": true,
          "source": "human"
        }
      ],
      "pending_faq_count": 0
    },
    "call_attempts": [
      {
        "id": "id",
        "answered_at": {},
        "dial_error": "number_non_attributed",
        "ended_at": {},
        "phone_number": "phone_number",
        "recording_url": "recording_url",
        "result": "IVR",
        "started_at": {},
        "status": "queued",
        "end_reason": "end_reason",
        "ended_by": "agent",
        "structured_output": {
          "foo": "bar"
        },
        "transcript": [
          {
            "content": "content",
            "role": "user",
            "tool_arguments": {
              "foo": "bar"
            },
            "tool_is_error": true,
            "tool_name": "tool_name",
            "tool_output": "tool_output"
          }
        ]
      }
    ],
    "call_retry_config": {
      "allowed_days": [
        "monday"
      ],
      "calling_windows": [
        {
          "calling_window_end_time": "calling_window_end_time",
          "calling_window_start_time": "calling_window_start_time",
          "retry_delay_seconds": 1
        }
      ],
      "max_retry_attempts": 1,
      "timezone": "timezone"
    },
    "calls_count": 0,
    "campaign": {
      "id": "id",
      "name": "name"
    },
    "created_at": {},
    "direction": "inbound",
    "first_sentence_delay_ms": -9007199254740991,
    "from_phone_number": "from_phone_number",
    "is_cancelled": true,
    "is_completed": true,
    "last_call_attempt": {
      "id": "id",
      "answered_at": {},
      "dial_error": "number_non_attributed",
      "ended_at": {},
      "phone_number": "phone_number",
      "recording_url": "recording_url",
      "result": "IVR",
      "started_at": {},
      "status": "queued",
      "end_reason": "end_reason",
      "ended_by": "agent",
      "structured_output": {
        "foo": "bar"
      },
      "transcript": [
        {
          "content": "content",
          "role": "user",
          "tool_arguments": {
            "foo": "bar"
          },
          "tool_is_error": true,
          "tool_name": "tool_name",
          "tool_output": "tool_output"
        }
      ]
    },
    "llm_model": {
      "name": "gpt-4.1",
      "type": "dedicated-instance"
    },
    "metadata": {
      "foo": "string"
    },
    "organization_id": "organization_id",
    "prompt_variables": {
      "foo": "string"
    },
    "scheduled_at": {},
    "status": "initializing",
    "to_phone_number": "to_phone_number",
    "outcome": "not_interested",
    "outcome_summary": "outcome_summary"
  }
}

Place a call

Body ParametersJSONExpand Collapse

ReturnsExpand Collapse

Place a call

Returns Examples

What can I help you with?

Suggestions