Get campaign rows

campaigns.get_rows() -> CampaignGetRowsResponse

GET/campaigns/{id}/rows

Retrieve all contact rows for a campaign. Useful for loading draft campaign data for editing.

ParametersExpand Collapse

id: str

ReturnsExpand Collapse

class CampaignGetRowsResponse: …

rows: List[Row]

id: str

input_data: Dict[str, str]

phone_number: str

row_index: float

call: Optional[RowCall]

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: str

The ID of the call.

assignee: Optional[RowCallAssignee]

The team member responsible for following up on this call.

id: str

The database user id of the assignee.

email: str

first_name: Optional[str]

last_name: Optional[str]

assistant: Optional[RowCallAssistant]

id: str

after_call_sms_outcomes: Optional[List[Literal["not_interested", "interested", "completed", 2 more]]]

Which call outcomes trigger the after-call SMS. When empty or null, no after-call SMS is sent. Use "none" when outcome is null.

One of the following:

"not_interested"

"interested"

"completed"

"requested_callback_later"

"none"

after_call_sms_prompt: Optional[str]

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

background_sound: Optional[Literal["audio/office.ogg"]]

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

background_sound_volume: float

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

minimum0

maximum1

calendly: Optional[RowCallAssistantCalendly]

connection_id: str

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

event_type_id: str

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[RowCallAssistantCallRetryConfig]

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

allowed_days: List[Literal["monday", "tuesday", "wednesday", 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"

call_twice_in_a_row: bool

If true and max_retry_attempts >= 2, attempt #2 fires immediately (skipping retry_delay_seconds) when attempt #1 didn't reach a human. Calling-window/allowed-days checks still apply. Only affects the 1→2 transition. Default: false.

calling_windows: List[RowCallAssistantCallRetryConfigCallingWindow]

calling_window_end_time: str

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: str

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: int

Delay between retry attempts in seconds. 0 retries as soon as the calling window allows. Default: 7200 (2 hours).

minimum0

maximum9007199254740991

max_retry_attempts: int

Maximum number of call retry attempts. Default: 3.

exclusiveMinimum0

maximum9007199254740991

timezone: Optional[str]

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'.

cartesia_dictionary_pronunciation_id: Optional[str]

Optional Cartesia pronunciation dictionary ID linked to this assistant.

created_at: object

custom_tools: Optional[List[RowCallAssistantCustomTool]]

body_template: Optional[str]

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

description: str

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

minLength1

headers: List[RowCallAssistantCustomToolHeader]

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

key: str

minLength1

value: str

input_schema: List[RowCallAssistantCustomToolInputSchema]

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

minLength1

required: bool

type: Literal["string", "number", "boolean", 3 more]

One of the following:

"string"

"number"

"boolean"

"enum"

"date"

"datetime"

description: Optional[str]

enum_options: Optional[List[str]]

method: Literal["GET", "POST", "PUT", 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: List[RowCallAssistantCustomToolQueryParam]

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

key: str

minLength1

value: str

url: str

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

minLength1

email_notification_address: Optional[str]

Email address(es) to receive notifications when a call ends with a matching outcome. Accepts a single email or a comma-separated list (e.g. "alice@x.com, bob@y.com").

email_notification_outcomes: Optional[List[Literal["not_interested", "interested", "completed", 2 more]]]

Which call outcomes trigger an email notification. E.g. ["interested", "completed", "none"]. Use "none" when outcome is null.

One of the following:

"not_interested"

"interested"

"completed"

"requested_callback_later"

"none"

end_of_call_sentence: Optional[str]

first_sentence: Optional[str]

first_sentence_delay_ms: int

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

minimum-9007199254740991

maximum9007199254740991

first_sentence_mode: Literal["generated", "static", "none"]

One of the following:

"generated"

"static"

"none"

from_phone_number: Optional[str]

Override the default outbound phone number for calls placed with this assistant. When null, the organization's default phone number is used.

human_transfer_mode: Optional[Literal["warm", "cold"]]

Warm or cold transfer when transfer_destinations is non-empty; null when transfer is not configured.

One of the following:

"warm"

"cold"

ivr_navigation_enabled: bool

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

llm_model: RowCallAssistantLlmModel

One of the following:

class RowCallAssistantLlmModelUnionMember0: …

One of the following:

"gpt-4.1"

"ministral-3-8b-instruct"

type: Literal["dedicated-instance"]

class RowCallAssistantLlmModelUnionMember1: …

openrouter_model_id: str

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

openrouter_provider: str

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

type: Literal["openrouter"]

Use a model from OpenRouter.

class RowCallAssistantLlmModelUnionMember2: …

api_key: str

API key sent as Bearer token to the custom endpoint.

minLength1

api_url: str

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

formaturi

model_name: str

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

minLength1

type: Literal["custom"]

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

class RowCallAssistantLlmModelUnionMember3: …

provider: Literal["openai", "google"]

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

One of the following:

"openai"

"google"

realtime_model_id: str

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

type: Literal["realtime"]

Use a model from Realtime.

realtime_voice_id: Optional[str]

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

minLength1

logo_url: Optional[str]

Public URL of the brand logo shown on the assistant's demo page. Null when unset.

max_call_duration_secs: float

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

max_duration_end_message: Optional[str]

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 null, the call ends silently.

maxLength150

organization_id: str

position: Optional[RowCallAssistantPosition]

x: float

y: float

precall_lookup_url: Optional[str]

URL fetched before an inbound call is answered to resolve the assistant's prompt variables. Null when no lookup is configured.

prompt: str

prompt_flow: Optional[RowCallAssistantPromptFlow]

edges: List[RowCallAssistantPromptFlowEdge]

id: str

source: str

target: str

nodes: List[RowCallAssistantPromptFlowNode]

id: str

data: RowCallAssistantPromptFlowNodeData

body: str

title: str

position: RowCallAssistantPromptFlowNodePosition

x: float

y: float

type: Literal["promptBlock"]

slack: Optional[RowCallAssistantSlack]

channels: List[RowCallAssistantSlackChannel]

The Slack channels eligible to receive the notification. When more than one is configured, the agent prompt may define routing rules to narrow it down per call; with no such rules every channel here is notified.

id: str

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

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

connection_id: str

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

outcomes: List[Literal["not_interested", "interested", "completed", 2 more]]

Which call outcomes trigger a Slack notification (e.g. ['interested', 'none']). Use 'none' to notify when outcome is null.

One of the following:

"not_interested"

"interested"

"completed"

"requested_callback_later"

"none"

Optional message template. Supports {{summary}}, {{outcome}}, {{phone}}, {{call_url}}, {{assistant_name}}, {{campaign_name}}, {{first_name}}, {{last_name}}, {{email}}, {{company}}, {{job_title}}, {{contact_name}}, {{contact_line}}, plus prompt_variables and structured_output keys. When null/empty a default template is used.

sms_enabled: bool

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

sms_template: Optional[str]

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[List[RowCallAssistantStructuredOutputConfig]]

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: bool

type: Literal["string", "number", "boolean", 3 more]

One of the following:

"string"

"number"

"boolean"

"enum"

"date"

"datetime"

description: Optional[str]

enum_options: Optional[List[str]]

structured_output_prompt: Optional[str]

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}}.

stt_context: Optional[RowCallAssistantSttContext]

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.

general: List[RowCallAssistantSttContextGeneral]

key: str

minLength1

value: str

minLength1

terms: List[str]

stt_model: Literal["stt-rt-v4", "stt-rt-v5"]

Transcriber (speech-to-text) model used for the assistant.

One of the following:

"stt-rt-v4"

"stt-rt-v5"

thinking_sound: Optional[Literal["city-ambience.ogg", "forest-ambience.ogg", "office-ambience.ogg", 4 more]]

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

One of the following:

"city-ambience.ogg"

"forest-ambience.ogg"

"office-ambience.ogg"

"crowded-room.ogg"

"keyboard-typing.ogg"

"keyboard-typing2.ogg"

"hold_music.ogg"

thinking_sound_probability: float

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

minimum0

maximum1

thinking_sound_volume: float

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

minimum0

maximum1

transfer_destinations: Optional[List[RowCallAssistantTransferDestination]]

Where calls can be transferred to when users ask to speak to a human. Null or empty when transfer is not configured.

label: str

minLength1

maxLength60

phone_number: str

type: Literal["standalone", "multi-step", "sub-assistant"]

One of the following:

"standalone"

"multi-step"

"sub-assistant"

updated_at: object

voice: Optional[RowCallAssistantVoice]

id: str

The ID of the voice.

minLength1

provider: Literal["cartesia", "elevenlabs", "gradium"]

The provider of the voice.

One of the following:

"cartesia"

"elevenlabs"

"gradium"

model: Optional[Literal["sonic-3", "sonic-3.5"]]

Cartesia TTS model (Cartesia only). Defaults to sonic-3 when omitted. Ignored for other providers.

One of the following:

"sonic-3"

"sonic-3.5"

speed: Optional[float]

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.

minimum0.6

maximum1.5

volume: Optional[float]

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

minimum0.5

maximum2

voicemail_message: Optional[str]

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

voicemail_sms_prompt: Optional[str]

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

warm_transfer_summary_instructions: Optional[str]

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

webhook_url: Optional[str]

The webhook URL to call when the call is completed.

zoho: Optional[RowCallAssistantZoho]

connection_id: str

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

field_mapping: List[RowCallAssistantZohoFieldMapping]

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

source: str

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

minLength1

zoho_field: str

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

minLength1

log_call_activity: bool

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

module: str

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

minLength1

outcomes: List[Literal["not_interested", "interested", "completed", 2 more]]

Which call outcomes trigger the Zoho push (e.g. ['interested', 'none']). Use 'none' to push when outcome is null.

One of the following:

"not_interested"

"interested"

"completed"

"requested_callback_later"

"none"

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.

created_by: Optional[RowCallAssistantCreatedBy]

The user who created the assistant.

id: str

The database user id of the creator.

email: str

first_name: Optional[str]

last_name: Optional[str]

faq_items: Optional[List[RowCallAssistantFaqItem]]

answer: str

question: str

id: Optional[str]

needs_human_answer: Optional[bool]

source: Optional[Literal["human", "ai"]]

One of the following:

"human"

"ai"

is_inbound_receptionist: Optional[bool]

is_realestate_assistant: Optional[bool]

pending_faq_count: Optional[float]

call_attempts: List[RowCallCallAttempt]

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

id: str

The ID of the call attempt.

answered_at: object

The time the call was answered.

dial_error: Optional[Literal["number_non_attributed", "too_many_calls", "busy", 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: object

The time the call ended.

handled_by_ai: bool

Whether the AI agent conducted the conversation on this attempt. False for a silent speed-dial probe (whose agent only detects a human) and for attempts that were never answered.

handled_by_human: bool

Whether a human operator conducted (part of) this attempt — a jump-in takeover or a speed-dial operator connection (both stamp human_takeover_at).

handled_by_user: Optional[RowCallCallAttemptHandledByUser]

The team member responsible for following up on this call.

id: str

The database user id of the assignee.

email: str

first_name: Optional[str]

last_name: Optional[str]

phone_number: str

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

recording_url: Optional[str]

The URL of the audio recording of the call.

result: Optional[Literal["IVR", "voicemail", "human", 2 more]]

One of the following:

"IVR"

"voicemail"

"human"

"unknown"

"ios-screening-filter"

started_at: object

The time the call started.

status: Literal["queued", "ringing", "ongoing", 2 more]

The status of the call attempt.

One of the following:

"queued"

"ringing"

"ongoing"

"completed"

"error"

assistants_used: Optional[List[str]]

Assistant node ids entered during this attempt, in traversal order.

email_log: Optional[List[RowCallCallAttemptEmailLog]]

Notification emails sent in connection with the call, ordered oldest first (from/to addresses, subject, sent time).

id: str

created_at: object

When the email was sent.

from_address: str

resend_message_id: Optional[str]

subject: str

to_emails: List[str]

end_reason: Optional[Literal["client_initiated", "connection_timeout", "human_takeover", 13 more]]

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

One of the following:

"client_initiated"

"connection_timeout"

"human_takeover"

"ivr_no_navigate"

"max_duration"

"participant_removed"

"tool_end_call"

"transfer"

"user_inactive"

"user_rejected"

"user_unavailable"

"voicemail"

"speed_dial_abandoned"

"speed_dial_operator_missed"

"speed_dial_timeout"

"speed_dial_hangup"

ended_by: Optional[Literal["agent", "user", "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"

post_call_transcript: Optional[List[RowCallCallAttemptPostCallTranscript]]

Higher-quality transcript generated after the call via Soniox async STT. Null until generated or when no recording is available.

content: str

role: Literal["user", "assistant", "human_agent", "tool"]

One of the following:

"user"

"assistant"

"human_agent"

"tool"

tool_arguments: Optional[Union[Dict[str, object], str, null]]

One of the following:

Dict[str, object]

str

tool_is_error: Optional[bool]

tool_name: Optional[str]

tool_output: Optional[str]

sms_log: Optional[List[RowCallCallAttemptSMSLog]]

Automatic SMS sent after the call (voicemail and after-call), ordered oldest first. The in-call send_sms is excluded — it already appears in the transcript as a tool call.

id: str

created_at: object

When the SMS was sent.

message_body: str

to_phone_number: str

twilio_message_sid: Optional[str]

type: Literal["in_call", "voicemail", "after_call"]

One of the following:

"in_call"

"voicemail"

"after_call"

speech_events: Optional[List[RowCallCallAttemptSpeechEvent]]

Per-turn speech segments (VAD-derived) with timing and pipeline latencies, ordered by started_speaking_at_ms. Empty for calls recorded before this was tracked or for realtime sessions that don't emit them.

id: str

is_real_turn: bool

False when the segment was flagged as noise/blip rather than a meaningful turn.

llm_ttft_ms: Optional[float]

Agent-only: LLM time-to-first-token for the reply, in ms.

speaker: Literal["user", "agent"]

Who was speaking during this segment.

One of the following:

"user"

"agent"

started_speaking_at_ms: float

Milliseconds since session start when speech began.

stopped_speaking_at_ms: Optional[float]

Milliseconds since session start when speech ended. Null when the session ended before the turn closed.

stt_transcription_delay_ms: Optional[float]

User-only: time from end-of-speech to final transcript, in ms.

transcript: Optional[str]

Recognized text for this segment, when available.

tts_ttfb_ms: Optional[float]

Agent-only: TTS time-to-first-audio-byte for the reply, in ms.

was_cut: Optional[bool]

Agent-only: true when the agent's audio was interrupted (real or auto-resumed). Null on user segments.

structured_output: Optional[Dict[str, object]]

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

transcript: Optional[List[RowCallCallAttemptTranscript]]

The live transcript of the call, built in real time.

content: str

role: Literal["user", "assistant", "human_agent", "tool"]

One of the following:

"user"

"assistant"

"human_agent"

"tool"

tool_arguments: Optional[Union[Dict[str, object], str, null]]

One of the following:

Dict[str, object]

str

tool_is_error: Optional[bool]

tool_name: Optional[str]

tool_output: Optional[str]

call_retry_config: Optional[RowCallCallRetryConfig]

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

allowed_days: List[Literal["monday", "tuesday", "wednesday", 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"

call_twice_in_a_row: bool

calling_windows: List[RowCallCallRetryConfigCallingWindow]

calling_window_end_time: str

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: str

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: int

Delay between retry attempts in seconds. 0 retries as soon as the calling window allows. Default: 7200 (2 hours).

minimum0

maximum9007199254740991

max_retry_attempts: int

Maximum number of call retry attempts. Default: 3.

exclusiveMinimum0

maximum9007199254740991

timezone: Optional[str]

calls_count: float

The number of call attempts made.

campaign: Optional[RowCallCampaign]

id: str

contact: RowCallContact

Magic contact variables (prospect identity) extracted from the call's input data and transcript.

company: Optional[str]

email: Optional[str]

first_name: Optional[str]

job_title: Optional[str]

last_name: Optional[str]

created_at: object

The time the call order was created.

direction: Literal["inbound", "outbound"]

Whether the call is inbound or outbound.

One of the following:

"inbound"

"outbound"

first_sentence_delay_ms: int

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

minimum-9007199254740991

maximum9007199254740991

from_phone_number: str

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

is_cancelled: bool

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

is_completed: bool

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

last_call_attempt: Optional[RowCallLastCallAttempt]

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

id: str

The ID of the call attempt.

answered_at: object

The time the call was answered.

dial_error: Optional[Literal["number_non_attributed", "too_many_calls", "busy", 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: object

The time the call ended.

handled_by_ai: bool

Whether the AI agent conducted the conversation on this attempt. False for a silent speed-dial probe (whose agent only detects a human) and for attempts that were never answered.

handled_by_human: bool

Whether a human operator conducted (part of) this attempt — a jump-in takeover or a speed-dial operator connection (both stamp human_takeover_at).

handled_by_user: Optional[RowCallLastCallAttemptHandledByUser]

The team member responsible for following up on this call.

id: str

The database user id of the assignee.

email: str

first_name: Optional[str]

last_name: Optional[str]

phone_number: str

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

recording_url: Optional[str]

The URL of the audio recording of the call.

result: Optional[Literal["IVR", "voicemail", "human", 2 more]]

One of the following:

"IVR"

"voicemail"

"human"

"unknown"

"ios-screening-filter"

started_at: object

The time the call started.

status: Literal["queued", "ringing", "ongoing", 2 more]

The status of the call attempt.

One of the following:

"queued"

"ringing"

"ongoing"

"completed"

"error"

assistants_used: Optional[List[str]]

Assistant node ids entered during this attempt, in traversal order.

email_log: Optional[List[RowCallLastCallAttemptEmailLog]]

Notification emails sent in connection with the call, ordered oldest first (from/to addresses, subject, sent time).

id: str

created_at: object

When the email was sent.

from_address: str

resend_message_id: Optional[str]

subject: str

to_emails: List[str]

end_reason: Optional[Literal["client_initiated", "connection_timeout", "human_takeover", 13 more]]

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

One of the following:

"client_initiated"

"connection_timeout"

"human_takeover"

"ivr_no_navigate"

"max_duration"

"participant_removed"

"tool_end_call"

"transfer"

"user_inactive"

"user_rejected"

"user_unavailable"

"voicemail"

"speed_dial_abandoned"

"speed_dial_operator_missed"

"speed_dial_timeout"

"speed_dial_hangup"

ended_by: Optional[Literal["agent", "user", "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"

post_call_transcript: Optional[List[RowCallLastCallAttemptPostCallTranscript]]

Higher-quality transcript generated after the call via Soniox async STT. Null until generated or when no recording is available.

content: str

role: Literal["user", "assistant", "human_agent", "tool"]

One of the following:

"user"

"assistant"

"human_agent"

"tool"

tool_arguments: Optional[Union[Dict[str, object], str, null]]

One of the following:

Dict[str, object]

str

tool_is_error: Optional[bool]

tool_name: Optional[str]

tool_output: Optional[str]

sms_log: Optional[List[RowCallLastCallAttemptSMSLog]]

Automatic SMS sent after the call (voicemail and after-call), ordered oldest first. The in-call send_sms is excluded — it already appears in the transcript as a tool call.

id: str

created_at: object

When the SMS was sent.

message_body: str

to_phone_number: str

twilio_message_sid: Optional[str]

type: Literal["in_call", "voicemail", "after_call"]

One of the following:

"in_call"

"voicemail"

"after_call"

speech_events: Optional[List[RowCallLastCallAttemptSpeechEvent]]

id: str

is_real_turn: bool

False when the segment was flagged as noise/blip rather than a meaningful turn.

llm_ttft_ms: Optional[float]

Agent-only: LLM time-to-first-token for the reply, in ms.

speaker: Literal["user", "agent"]

Who was speaking during this segment.

One of the following:

"user"

"agent"

started_speaking_at_ms: float

Milliseconds since session start when speech began.

stopped_speaking_at_ms: Optional[float]

Milliseconds since session start when speech ended. Null when the session ended before the turn closed.

stt_transcription_delay_ms: Optional[float]

User-only: time from end-of-speech to final transcript, in ms.

transcript: Optional[str]

Recognized text for this segment, when available.

tts_ttfb_ms: Optional[float]

Agent-only: TTS time-to-first-audio-byte for the reply, in ms.

was_cut: Optional[bool]

Agent-only: true when the agent's audio was interrupted (real or auto-resumed). Null on user segments.

structured_output: Optional[Dict[str, object]]

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

transcript: Optional[List[RowCallLastCallAttemptTranscript]]

The live transcript of the call, built in real time.

content: str

role: Literal["user", "assistant", "human_agent", "tool"]

One of the following:

"user"

"assistant"

"human_agent"

"tool"

tool_arguments: Optional[Union[Dict[str, object], str, null]]

One of the following:

Dict[str, object]

str

tool_is_error: Optional[bool]

tool_name: Optional[str]

tool_output: Optional[str]

llm_model: RowCallLlmModel

One of the following:

class RowCallLlmModelUnionMember0: …

One of the following:

"gpt-4.1"

"ministral-3-8b-instruct"

type: Literal["dedicated-instance"]

class RowCallLlmModelUnionMember1: …

openrouter_model_id: str

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

openrouter_provider: str

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

type: Literal["openrouter"]

Use a model from OpenRouter.

class RowCallLlmModelUnionMember2: …

api_key: str

API key sent as Bearer token to the custom endpoint.

minLength1

api_url: str

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

formaturi

model_name: str

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

minLength1

type: Literal["custom"]

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

class RowCallLlmModelUnionMember3: …

provider: Literal["openai", "google"]

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

One of the following:

"openai"

"google"

realtime_model_id: str

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

type: Literal["realtime"]

Use a model from Realtime.

realtime_voice_id: Optional[str]

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

minLength1

metadata: Optional[Dict[str, str]]

Metadata stored with the call.

organization_id: str

The ID of the organization that owns the call.

prompt_variables: Optional[Dict[str, str]]

Variables used to interpolate the prompt.

scheduled_at: object

The time the call order is scheduled to start.

status: Literal["initializing", "queued_for_calling", "calling", 6 more]

The status of the call.

One of the following:

"initializing"

"queued_for_calling"

"calling"

"post_processing"

"scheduled"

"paused"

"completed"

"cancelled"

"errored"

to_phone_number: str

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

updated_at: object

The time the call order was last updated (any state change, retry, or analysis result).

follow_up_emails: Optional[List[str]]

Extra notification recipients resolved from the agent prompt's own routing rules, when it defines any. Added to the assistant's configured notification recipients; never replaces them. Null when the prompt defines no routing rules.

outcome: Optional[Literal["not_interested", "interested", "completed", "requested_callback_later"]]

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

One of the following:

"not_interested"

"interested"

"completed"

"requested_callback_later"

outcome_summary: Optional[str]

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

slack_channel_ids: Optional[List[str]]

Slack channels resolved from the agent prompt's own routing rules, when it defines any. Always a subset of the channels configured on the assistant. Null when the prompt defines no routing rules, in which case every configured channel is notified.