Call
Get call by ID
Place a call
Get calls
Export calls history
Pause a call
Resume a paused call
Cancel a call
Get phone number history across the organization
ModelsExpand Collapse
CallRetrieveResponse object { call }
call: object { id, assignee, assistant, 27 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.
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.
assignee: object { id, email, first_name, last_name } The team member responsible for following up on this call.
The team member responsible for following up on this call.
assistant: object { id, after_call_sms_outcomes, after_call_sms_prompt, 51 more }
after_call_sms_outcomes: array of "not_interested" or "interested" or "completed" or 2 moreWhich call outcomes trigger the after-call SMS. When empty or null, no after-call SMS is sent. Use “none” when outcome is null.
Which call outcomes trigger the after-call SMS. When empty or null, no after-call SMS is sent. Use “none” when outcome is null.
Prompt / instructions for the after-call SMS. Supports {{variable}} placeholders. When null, no after-call SMS is sent.
Ambient background sound to play during the call. null disables it.
Volume of the ambient background sound (0 = silent, 1 = max).
calendly: object { connection_id, event_type_id }
The connection ID representing the link between your Calendly account and Revox.
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, call_twice_in_a_row, calling_windows, 2 more } Configuration for call retry behavior including time windows, delays, and max iterations. If not provided, defaults will be used.
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 moreDays of the week when calls are allowed, in the recipient’s timezone. Default: Monday through Friday.
Days of the week when calls are allowed, in the recipient’s timezone. Default: Monday through Friday.
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: array of object { calling_window_end_time, calling_window_start_time, retry_delay_seconds }
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’.
Optional Cartesia pronunciation dictionary ID linked to this assistant.
custom_tools: array of object { body_template, description, headers, 5 more }
JSON body template for the request. Use quoted {{variable}} placeholders (e.g. “{{name}}”) for dynamic values
Human-readable description of what the tool does, used by the LLM to decide when to call it
headers: array of object { key, value } HTTP headers to include in the request. Values support {{variable}} placeholders
HTTP headers to include in the request. Values support {{variable}} placeholders
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
Schema defining the parameters the LLM should extract from the conversation to pass to this tool
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: array of "not_interested" or "interested" or "completed" or 2 moreWhich call outcomes trigger an email notification. E.g. [“interested”, “completed”, “none”]. Use “none” when outcome is null.
Which call outcomes trigger an email notification. E.g. [“interested”, “completed”, “none”]. Use “none” when outcome is null.
Delay in milliseconds before speaking the first sentence. Default: 400.
Override the default outbound phone number for calls placed with this assistant. When null, the organization’s default phone number is used.
hubspot: object { connection_id, meeting_links, precall_lookup_enabled }
meeting_links: array of object { booking_url, duration_ms, is_fallback, 2 more } 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.
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.
Public URL of the scheduling page (e.g. https://meetings-eu1.hubspot.com/julien). The agent texts this to the caller when it can’t complete the booking itself. Null on calendars saved before this field existed.
Meeting duration in milliseconds, chosen among the durations the scheduling page offers (e.g. 1800000 for 30 minutes).
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.
human_transfer_mode: "warm" or "cold"Warm or cold transfer when transfer_destinations is non-empty; null when transfer is not configured.
Warm or cold transfer when transfer_destinations is non-empty; null when transfer is not configured.
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 }
The maximum duration of the call in seconds. This is the maximum time the call will be allowed to run.
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.
URL fetched before an inbound call is answered to resolve the assistant’s prompt variables. Null when no lookup is configured.
slack: object { channels, connection_id, outcomes, template }
channels: array of object { id, name } 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.
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.
outcomes: array of "not_interested" or "interested" or "completed" or 2 moreWhich call outcomes trigger a Slack notification (e.g. [‘interested’, ‘none’]). Use ‘none’ to notify when outcome is null.
Which call outcomes trigger a Slack notification (e.g. [‘interested’, ‘none’]). Use ‘none’ to notify when outcome is null.
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.
Enable SMS tool during calls. When enabled, the agent can send SMS messages to the user on the call.
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.).
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.).
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: object { general, terms } 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.
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.
thinking_sound: "city-ambience.ogg" or "forest-ambience.ogg" or "office-ambience.ogg" or 4 moreAudio clip to play while the agent is processing a response. One of the built-in LiveKit audio clips; null disables it.
Audio clip to play while the agent is processing a response. One of the built-in LiveKit audio clips; null disables it.
Probability [0..1] that the thinking sound plays on any given turn; otherwise the agent is silent while thinking.
transfer_destinations: array of object { label, phone_number } Where calls can be transferred to when users ask to speak to a human. Null or empty when transfer is not configured.
Where calls can be transferred to when users ask to speak to a human. Null or empty when transfer is not configured.
voice: object { id, provider, model, 2 more }
model: optional "sonic-3" or "sonic-3.5" or "sonic-3.6"Cartesia TTS model (Cartesia only). Defaults to sonic-3.6 when omitted. Ignored for other providers.
Cartesia TTS model (Cartesia only). Defaults to sonic-3.6 when omitted. Ignored for other providers.
If set, when voicemail is detected the agent will speak this message then hang up; if null, hang up immediately.
Prompt / instructions for the voicemail SMS. Supports {{variable}} placeholders. When null, no SMS is sent on voicemail.
Warm transfer only: instructions for the supervisor handoff summary; null when not configured or cold transfer.
zoho: object { connection_id, field_mapping, log_call_activity, 3 more }
field_mapping: array of object { source, zoho_field } Maps extracted call fields (structured_output / prompt variables) onto Zoho field API names on the upserted record.
Maps extracted call fields (structured_output / prompt variables) onto Zoho field API names on the upserted record.
When true, also log the call as a record in Zoho’s Calls module (related to the upserted prospect via Who_Id).
Zoho module the prospect record is upserted into (e.g. ‘Leads’ or ‘Contacts’).
outcomes: array of "not_interested" or "interested" or "completed" or 2 moreWhich call outcomes trigger the Zoho push (e.g. [‘interested’, ‘none’]). Use ‘none’ to push when outcome is null.
Which call outcomes trigger the Zoho push (e.g. [‘interested’, ‘none’]). Use ‘none’ to push when outcome is null.
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 object { id, email, first_name, last_name } The user who created the assistant.
The user who created the assistant.
call_attempts: array of object { id, answered_at, dial_error, 18 more } All call attempts for this call order, ordered by most recent first.
All call attempts for this call order, ordered by most recent first.
dial_error: "number_non_attributed" or "too_many_calls" or "busy" or 5 moreThe SIP error that occurred.
The SIP error that occurred.
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.
Whether a human conducted (part of) this attempt — a jump-in / speed-dial takeover, or a transfer to a rep.
handled_by_user: object { id, email, first_name, last_name } The team member responsible for following up on this call.
The team member responsible for following up on this call.
The phone number that was called. Formatted in E.164 format. Example: +1234567890
Assistant node ids entered during this attempt, in traversal order.
email_log: optional array of object { id, created_at, from_address, 3 more } Notification emails sent in connection with the call, ordered oldest first (from/to addresses, subject, sent time).
Notification emails sent in connection with the call, ordered oldest first (from/to addresses, subject, sent time).
end_reason: optional "client_initiated" or "connection_timeout" or "human_takeover" or 13 moreReason for ending the call when ended_by is ‘agent’. E.g. ‘tool_end_call’, ‘voicemail’, ‘transfer’, ‘ivr_no_navigate’.
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).
Who ended the call: ‘agent’ (AI agent), ‘user’ (caller/callee hung up), or ‘system’ (e.g. max duration limit).
post_call_transcript: optional array of object { content, role, tool_arguments, 3 more } Higher-quality transcript generated after the call via Soniox async STT. Null until generated or when no recording is available.
Higher-quality transcript generated after the call via Soniox async STT. Null until generated or when no recording is available.
sms_log: optional array of object { id, created_at, message_body, 6 more } 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.
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.
The provider’s numeric reason for a terminal failure (e.g. Twilio 30034). Null unless the message failed.
speech_events: optional array of object { id, is_real_turn, llm_system_prompt, 9 more } 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.
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.
False when the segment was flagged as noise/blip rather than a meaningful turn.
Agent-only: despite the name, the whole prompt the LLM was given for this turn — system instructions plus conversation history — as JSON.
Agent-only: the model that produced the reply — the winning leg when the LLM is a race, which is also the model llm_ttft_ms describes.
The data extracted from the call, using the structured output config from the parent call object.
call_retry_config: object { allowed_days, call_twice_in_a_row, calling_windows, 2 more } Configuration for call retry behavior including time windows, delays, and max iterations. If not provided, defaults will be used.
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 moreDays of the week when calls are allowed, in the recipient’s timezone. Default: Monday through Friday.
Days of the week when calls are allowed, in the recipient’s timezone. Default: Monday through Friday.
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: array of object { calling_window_end_time, calling_window_start_time, retry_delay_seconds }
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’.
contact: object { company, email, first_name, 2 more } Magic contact variables (prospect identity) extracted from the call’s input data and transcript.
Magic contact variables (prospect identity) extracted from the call’s input data and transcript.
Delay in milliseconds before speaking the first sentence. Default: 400.
The phone number that made the call. Formatted in E.164 format. Example: +1234567890
DEPRECATED: Whether the call has been cancelled. This is derived from status. Use status instead.
DEPRECATED: Whether the call has completed. This is derived from status. Use status instead.
last_call_attempt: object { id, answered_at, dial_error, 18 more } This represent a single call attempt. A call attempt is a single call made to the phone number.
This represent a single call attempt. A call attempt is a single call made to the phone number.
dial_error: "number_non_attributed" or "too_many_calls" or "busy" or 5 moreThe SIP error that occurred.
The SIP error that occurred.
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.
Whether a human conducted (part of) this attempt — a jump-in / speed-dial takeover, or a transfer to a rep.
handled_by_user: object { id, email, first_name, last_name } The team member responsible for following up on this call.
The team member responsible for following up on this call.
The phone number that was called. Formatted in E.164 format. Example: +1234567890
Assistant node ids entered during this attempt, in traversal order.
email_log: optional array of object { id, created_at, from_address, 3 more } Notification emails sent in connection with the call, ordered oldest first (from/to addresses, subject, sent time).
Notification emails sent in connection with the call, ordered oldest first (from/to addresses, subject, sent time).
end_reason: optional "client_initiated" or "connection_timeout" or "human_takeover" or 13 moreReason for ending the call when ended_by is ‘agent’. E.g. ‘tool_end_call’, ‘voicemail’, ‘transfer’, ‘ivr_no_navigate’.
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).
Who ended the call: ‘agent’ (AI agent), ‘user’ (caller/callee hung up), or ‘system’ (e.g. max duration limit).
post_call_transcript: optional array of object { content, role, tool_arguments, 3 more } Higher-quality transcript generated after the call via Soniox async STT. Null until generated or when no recording is available.
Higher-quality transcript generated after the call via Soniox async STT. Null until generated or when no recording is available.
sms_log: optional array of object { id, created_at, message_body, 6 more } 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.
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.
The provider’s numeric reason for a terminal failure (e.g. Twilio 30034). Null unless the message failed.
speech_events: optional array of object { id, is_real_turn, llm_system_prompt, 9 more } 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.
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.
False when the segment was flagged as noise/blip rather than a meaningful turn.
Agent-only: despite the name, the whole prompt the LLM was given for this turn — system instructions plus conversation history — as JSON.
Agent-only: the model that produced the reply — the winning leg when the LLM is a race, which is also the model llm_ttft_ms describes.
The data extracted from the call, using the structured output config from the parent call object.
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 }
The phone number that received the call. Formatted in E.164 format. Example: +1234567890
The time the call order was last updated (any state change, retry, or analysis result).
callback_from: optional object { call_id, created_at } For an inbound call only: the outbound call this one answers, when the prospect rang us back after we called them. Null for every other call.
For an inbound call only: the outbound call this one answers, when the prospect rang us back after we called them. Null for every other call.
Why the call was cancelled, when it can be told. prospect_called_back: the prospect called back before the next retry, so the pending retry was cancelled and their call is recorded as a separate inbound call. Null for a manual or campaign cancel, and for calls that are not cancelled.
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 "not_interested" or "interested" or "completed" or "requested_callback_later"Business outcome of the call. Null if not computed or no transcript.
Business outcome of the call. Null if not computed or no transcript.
LLM explanation for the outcome, when outcome was computed from the transcript.
CallCreateResponse object { call }
call: object { id, assignee, assistant, 27 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.
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.
assignee: object { id, email, first_name, last_name } The team member responsible for following up on this call.
The team member responsible for following up on this call.
assistant: object { id, after_call_sms_outcomes, after_call_sms_prompt, 51 more }
after_call_sms_outcomes: array of "not_interested" or "interested" or "completed" or 2 moreWhich call outcomes trigger the after-call SMS. When empty or null, no after-call SMS is sent. Use “none” when outcome is null.
Which call outcomes trigger the after-call SMS. When empty or null, no after-call SMS is sent. Use “none” when outcome is null.
Prompt / instructions for the after-call SMS. Supports {{variable}} placeholders. When null, no after-call SMS is sent.
Ambient background sound to play during the call. null disables it.
Volume of the ambient background sound (0 = silent, 1 = max).
calendly: object { connection_id, event_type_id }
The connection ID representing the link between your Calendly account and Revox.
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, call_twice_in_a_row, calling_windows, 2 more } Configuration for call retry behavior including time windows, delays, and max iterations. If not provided, defaults will be used.
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 moreDays of the week when calls are allowed, in the recipient’s timezone. Default: Monday through Friday.
Days of the week when calls are allowed, in the recipient’s timezone. Default: Monday through Friday.
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: array of object { calling_window_end_time, calling_window_start_time, retry_delay_seconds }
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’.
Optional Cartesia pronunciation dictionary ID linked to this assistant.
custom_tools: array of object { body_template, description, headers, 5 more }
JSON body template for the request. Use quoted {{variable}} placeholders (e.g. “{{name}}”) for dynamic values
Human-readable description of what the tool does, used by the LLM to decide when to call it
headers: array of object { key, value } HTTP headers to include in the request. Values support {{variable}} placeholders
HTTP headers to include in the request. Values support {{variable}} placeholders
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
Schema defining the parameters the LLM should extract from the conversation to pass to this tool
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: array of "not_interested" or "interested" or "completed" or 2 moreWhich call outcomes trigger an email notification. E.g. [“interested”, “completed”, “none”]. Use “none” when outcome is null.
Which call outcomes trigger an email notification. E.g. [“interested”, “completed”, “none”]. Use “none” when outcome is null.
Delay in milliseconds before speaking the first sentence. Default: 400.
Override the default outbound phone number for calls placed with this assistant. When null, the organization’s default phone number is used.
hubspot: object { connection_id, meeting_links, precall_lookup_enabled }
meeting_links: array of object { booking_url, duration_ms, is_fallback, 2 more } 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.
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.
Public URL of the scheduling page (e.g. https://meetings-eu1.hubspot.com/julien). The agent texts this to the caller when it can’t complete the booking itself. Null on calendars saved before this field existed.
Meeting duration in milliseconds, chosen among the durations the scheduling page offers (e.g. 1800000 for 30 minutes).
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.
human_transfer_mode: "warm" or "cold"Warm or cold transfer when transfer_destinations is non-empty; null when transfer is not configured.
Warm or cold transfer when transfer_destinations is non-empty; null when transfer is not configured.
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 }
The maximum duration of the call in seconds. This is the maximum time the call will be allowed to run.
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.
URL fetched before an inbound call is answered to resolve the assistant’s prompt variables. Null when no lookup is configured.
slack: object { channels, connection_id, outcomes, template }
channels: array of object { id, name } 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.
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.
outcomes: array of "not_interested" or "interested" or "completed" or 2 moreWhich call outcomes trigger a Slack notification (e.g. [‘interested’, ‘none’]). Use ‘none’ to notify when outcome is null.
Which call outcomes trigger a Slack notification (e.g. [‘interested’, ‘none’]). Use ‘none’ to notify when outcome is null.
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.
Enable SMS tool during calls. When enabled, the agent can send SMS messages to the user on the call.
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.).
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.).
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: object { general, terms } 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.
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.
thinking_sound: "city-ambience.ogg" or "forest-ambience.ogg" or "office-ambience.ogg" or 4 moreAudio clip to play while the agent is processing a response. One of the built-in LiveKit audio clips; null disables it.
Audio clip to play while the agent is processing a response. One of the built-in LiveKit audio clips; null disables it.
Probability [0..1] that the thinking sound plays on any given turn; otherwise the agent is silent while thinking.
transfer_destinations: array of object { label, phone_number } Where calls can be transferred to when users ask to speak to a human. Null or empty when transfer is not configured.
Where calls can be transferred to when users ask to speak to a human. Null or empty when transfer is not configured.
voice: object { id, provider, model, 2 more }
model: optional "sonic-3" or "sonic-3.5" or "sonic-3.6"Cartesia TTS model (Cartesia only). Defaults to sonic-3.6 when omitted. Ignored for other providers.
Cartesia TTS model (Cartesia only). Defaults to sonic-3.6 when omitted. Ignored for other providers.
If set, when voicemail is detected the agent will speak this message then hang up; if null, hang up immediately.
Prompt / instructions for the voicemail SMS. Supports {{variable}} placeholders. When null, no SMS is sent on voicemail.
Warm transfer only: instructions for the supervisor handoff summary; null when not configured or cold transfer.
zoho: object { connection_id, field_mapping, log_call_activity, 3 more }
field_mapping: array of object { source, zoho_field } Maps extracted call fields (structured_output / prompt variables) onto Zoho field API names on the upserted record.
Maps extracted call fields (structured_output / prompt variables) onto Zoho field API names on the upserted record.
When true, also log the call as a record in Zoho’s Calls module (related to the upserted prospect via Who_Id).
Zoho module the prospect record is upserted into (e.g. ‘Leads’ or ‘Contacts’).
outcomes: array of "not_interested" or "interested" or "completed" or 2 moreWhich call outcomes trigger the Zoho push (e.g. [‘interested’, ‘none’]). Use ‘none’ to push when outcome is null.
Which call outcomes trigger the Zoho push (e.g. [‘interested’, ‘none’]). Use ‘none’ to push when outcome is null.
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 object { id, email, first_name, last_name } The user who created the assistant.
The user who created the assistant.
call_attempts: array of object { id, answered_at, dial_error, 18 more } All call attempts for this call order, ordered by most recent first.
All call attempts for this call order, ordered by most recent first.
dial_error: "number_non_attributed" or "too_many_calls" or "busy" or 5 moreThe SIP error that occurred.
The SIP error that occurred.
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.
Whether a human conducted (part of) this attempt — a jump-in / speed-dial takeover, or a transfer to a rep.
handled_by_user: object { id, email, first_name, last_name } The team member responsible for following up on this call.
The team member responsible for following up on this call.
The phone number that was called. Formatted in E.164 format. Example: +1234567890
Assistant node ids entered during this attempt, in traversal order.
email_log: optional array of object { id, created_at, from_address, 3 more } Notification emails sent in connection with the call, ordered oldest first (from/to addresses, subject, sent time).
Notification emails sent in connection with the call, ordered oldest first (from/to addresses, subject, sent time).
end_reason: optional "client_initiated" or "connection_timeout" or "human_takeover" or 13 moreReason for ending the call when ended_by is ‘agent’. E.g. ‘tool_end_call’, ‘voicemail’, ‘transfer’, ‘ivr_no_navigate’.
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).
Who ended the call: ‘agent’ (AI agent), ‘user’ (caller/callee hung up), or ‘system’ (e.g. max duration limit).
post_call_transcript: optional array of object { content, role, tool_arguments, 3 more } Higher-quality transcript generated after the call via Soniox async STT. Null until generated or when no recording is available.
Higher-quality transcript generated after the call via Soniox async STT. Null until generated or when no recording is available.
sms_log: optional array of object { id, created_at, message_body, 6 more } 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.
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.
The provider’s numeric reason for a terminal failure (e.g. Twilio 30034). Null unless the message failed.
speech_events: optional array of object { id, is_real_turn, llm_system_prompt, 9 more } 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.
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.
False when the segment was flagged as noise/blip rather than a meaningful turn.
Agent-only: despite the name, the whole prompt the LLM was given for this turn — system instructions plus conversation history — as JSON.
Agent-only: the model that produced the reply — the winning leg when the LLM is a race, which is also the model llm_ttft_ms describes.
The data extracted from the call, using the structured output config from the parent call object.
call_retry_config: object { allowed_days, call_twice_in_a_row, calling_windows, 2 more } Configuration for call retry behavior including time windows, delays, and max iterations. If not provided, defaults will be used.
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 moreDays of the week when calls are allowed, in the recipient’s timezone. Default: Monday through Friday.
Days of the week when calls are allowed, in the recipient’s timezone. Default: Monday through Friday.
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: array of object { calling_window_end_time, calling_window_start_time, retry_delay_seconds }
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’.
contact: object { company, email, first_name, 2 more } Magic contact variables (prospect identity) extracted from the call’s input data and transcript.
Magic contact variables (prospect identity) extracted from the call’s input data and transcript.
Delay in milliseconds before speaking the first sentence. Default: 400.
The phone number that made the call. Formatted in E.164 format. Example: +1234567890
DEPRECATED: Whether the call has been cancelled. This is derived from status. Use status instead.
DEPRECATED: Whether the call has completed. This is derived from status. Use status instead.
last_call_attempt: object { id, answered_at, dial_error, 18 more } This represent a single call attempt. A call attempt is a single call made to the phone number.
This represent a single call attempt. A call attempt is a single call made to the phone number.
dial_error: "number_non_attributed" or "too_many_calls" or "busy" or 5 moreThe SIP error that occurred.
The SIP error that occurred.
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.
Whether a human conducted (part of) this attempt — a jump-in / speed-dial takeover, or a transfer to a rep.
handled_by_user: object { id, email, first_name, last_name } The team member responsible for following up on this call.
The team member responsible for following up on this call.
The phone number that was called. Formatted in E.164 format. Example: +1234567890
Assistant node ids entered during this attempt, in traversal order.
email_log: optional array of object { id, created_at, from_address, 3 more } Notification emails sent in connection with the call, ordered oldest first (from/to addresses, subject, sent time).
Notification emails sent in connection with the call, ordered oldest first (from/to addresses, subject, sent time).
end_reason: optional "client_initiated" or "connection_timeout" or "human_takeover" or 13 moreReason for ending the call when ended_by is ‘agent’. E.g. ‘tool_end_call’, ‘voicemail’, ‘transfer’, ‘ivr_no_navigate’.
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).
Who ended the call: ‘agent’ (AI agent), ‘user’ (caller/callee hung up), or ‘system’ (e.g. max duration limit).
post_call_transcript: optional array of object { content, role, tool_arguments, 3 more } Higher-quality transcript generated after the call via Soniox async STT. Null until generated or when no recording is available.
Higher-quality transcript generated after the call via Soniox async STT. Null until generated or when no recording is available.
sms_log: optional array of object { id, created_at, message_body, 6 more } 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.
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.
The provider’s numeric reason for a terminal failure (e.g. Twilio 30034). Null unless the message failed.
speech_events: optional array of object { id, is_real_turn, llm_system_prompt, 9 more } 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.
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.
False when the segment was flagged as noise/blip rather than a meaningful turn.
Agent-only: despite the name, the whole prompt the LLM was given for this turn — system instructions plus conversation history — as JSON.
Agent-only: the model that produced the reply — the winning leg when the LLM is a race, which is also the model llm_ttft_ms describes.
The data extracted from the call, using the structured output config from the parent call object.
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 }
The phone number that received the call. Formatted in E.164 format. Example: +1234567890
The time the call order was last updated (any state change, retry, or analysis result).
callback_from: optional object { call_id, created_at } For an inbound call only: the outbound call this one answers, when the prospect rang us back after we called them. Null for every other call.
For an inbound call only: the outbound call this one answers, when the prospect rang us back after we called them. Null for every other call.
Why the call was cancelled, when it can be told. prospect_called_back: the prospect called back before the next retry, so the pending retry was cancelled and their call is recorded as a separate inbound call. Null for a manual or campaign cancel, and for calls that are not cancelled.
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 "not_interested" or "interested" or "completed" or "requested_callback_later"Business outcome of the call. Null if not computed or no transcript.
Business outcome of the call. Null if not computed or no transcript.
LLM explanation for the outcome, when outcome was computed from the transcript.
CallSearchResponse object { calls, total_count }
calls: array of object { id, assignee, assistant, 27 more }
assignee: object { id, email, first_name, last_name } The team member responsible for following up on this call.
The team member responsible for following up on this call.
assistant: object { id, after_call_sms_outcomes, after_call_sms_prompt, 51 more }
after_call_sms_outcomes: array of "not_interested" or "interested" or "completed" or 2 moreWhich call outcomes trigger the after-call SMS. When empty or null, no after-call SMS is sent. Use “none” when outcome is null.
Which call outcomes trigger the after-call SMS. When empty or null, no after-call SMS is sent. Use “none” when outcome is null.
Prompt / instructions for the after-call SMS. Supports {{variable}} placeholders. When null, no after-call SMS is sent.
Ambient background sound to play during the call. null disables it.
Volume of the ambient background sound (0 = silent, 1 = max).
calendly: object { connection_id, event_type_id }
The connection ID representing the link between your Calendly account and Revox.
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, call_twice_in_a_row, calling_windows, 2 more } Configuration for call retry behavior including time windows, delays, and max iterations. If not provided, defaults will be used.
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 moreDays of the week when calls are allowed, in the recipient’s timezone. Default: Monday through Friday.
Days of the week when calls are allowed, in the recipient’s timezone. Default: Monday through Friday.
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: array of object { calling_window_end_time, calling_window_start_time, retry_delay_seconds }
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’.
Optional Cartesia pronunciation dictionary ID linked to this assistant.
custom_tools: array of object { body_template, description, headers, 5 more }
JSON body template for the request. Use quoted {{variable}} placeholders (e.g. “{{name}}”) for dynamic values
Human-readable description of what the tool does, used by the LLM to decide when to call it
headers: array of object { key, value } HTTP headers to include in the request. Values support {{variable}} placeholders
HTTP headers to include in the request. Values support {{variable}} placeholders
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
Schema defining the parameters the LLM should extract from the conversation to pass to this tool
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: array of "not_interested" or "interested" or "completed" or 2 moreWhich call outcomes trigger an email notification. E.g. [“interested”, “completed”, “none”]. Use “none” when outcome is null.
Which call outcomes trigger an email notification. E.g. [“interested”, “completed”, “none”]. Use “none” when outcome is null.
Delay in milliseconds before speaking the first sentence. Default: 400.
Override the default outbound phone number for calls placed with this assistant. When null, the organization’s default phone number is used.
hubspot: object { connection_id, meeting_links, precall_lookup_enabled }
meeting_links: array of object { booking_url, duration_ms, is_fallback, 2 more } 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.
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.
Public URL of the scheduling page (e.g. https://meetings-eu1.hubspot.com/julien). The agent texts this to the caller when it can’t complete the booking itself. Null on calendars saved before this field existed.
Meeting duration in milliseconds, chosen among the durations the scheduling page offers (e.g. 1800000 for 30 minutes).
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.
human_transfer_mode: "warm" or "cold"Warm or cold transfer when transfer_destinations is non-empty; null when transfer is not configured.
Warm or cold transfer when transfer_destinations is non-empty; null when transfer is not configured.
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 }
The maximum duration of the call in seconds. This is the maximum time the call will be allowed to run.
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.
URL fetched before an inbound call is answered to resolve the assistant’s prompt variables. Null when no lookup is configured.
slack: object { channels, connection_id, outcomes, template }
channels: array of object { id, name } 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.
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.
outcomes: array of "not_interested" or "interested" or "completed" or 2 moreWhich call outcomes trigger a Slack notification (e.g. [‘interested’, ‘none’]). Use ‘none’ to notify when outcome is null.
Which call outcomes trigger a Slack notification (e.g. [‘interested’, ‘none’]). Use ‘none’ to notify when outcome is null.
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.
Enable SMS tool during calls. When enabled, the agent can send SMS messages to the user on the call.
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.).
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.).
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: object { general, terms } 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.
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.
thinking_sound: "city-ambience.ogg" or "forest-ambience.ogg" or "office-ambience.ogg" or 4 moreAudio clip to play while the agent is processing a response. One of the built-in LiveKit audio clips; null disables it.
Audio clip to play while the agent is processing a response. One of the built-in LiveKit audio clips; null disables it.
Probability [0..1] that the thinking sound plays on any given turn; otherwise the agent is silent while thinking.
transfer_destinations: array of object { label, phone_number } Where calls can be transferred to when users ask to speak to a human. Null or empty when transfer is not configured.
Where calls can be transferred to when users ask to speak to a human. Null or empty when transfer is not configured.
voice: object { id, provider, model, 2 more }
model: optional "sonic-3" or "sonic-3.5" or "sonic-3.6"Cartesia TTS model (Cartesia only). Defaults to sonic-3.6 when omitted. Ignored for other providers.
Cartesia TTS model (Cartesia only). Defaults to sonic-3.6 when omitted. Ignored for other providers.
If set, when voicemail is detected the agent will speak this message then hang up; if null, hang up immediately.
Prompt / instructions for the voicemail SMS. Supports {{variable}} placeholders. When null, no SMS is sent on voicemail.
Warm transfer only: instructions for the supervisor handoff summary; null when not configured or cold transfer.
zoho: object { connection_id, field_mapping, log_call_activity, 3 more }
field_mapping: array of object { source, zoho_field } Maps extracted call fields (structured_output / prompt variables) onto Zoho field API names on the upserted record.
Maps extracted call fields (structured_output / prompt variables) onto Zoho field API names on the upserted record.
When true, also log the call as a record in Zoho’s Calls module (related to the upserted prospect via Who_Id).
Zoho module the prospect record is upserted into (e.g. ‘Leads’ or ‘Contacts’).
outcomes: array of "not_interested" or "interested" or "completed" or 2 moreWhich call outcomes trigger the Zoho push (e.g. [‘interested’, ‘none’]). Use ‘none’ to push when outcome is null.
Which call outcomes trigger the Zoho push (e.g. [‘interested’, ‘none’]). Use ‘none’ to push when outcome is null.
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 object { id, email, first_name, last_name } The user who created the assistant.
The user who created the assistant.
call_attempts: array of object { id, answered_at, dial_error, 18 more } All call attempts for this call order, ordered by most recent first.
All call attempts for this call order, ordered by most recent first.
dial_error: "number_non_attributed" or "too_many_calls" or "busy" or 5 moreThe SIP error that occurred.
The SIP error that occurred.
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.
Whether a human conducted (part of) this attempt — a jump-in / speed-dial takeover, or a transfer to a rep.
handled_by_user: object { id, email, first_name, last_name } The team member responsible for following up on this call.
The team member responsible for following up on this call.
The phone number that was called. Formatted in E.164 format. Example: +1234567890
Assistant node ids entered during this attempt, in traversal order.
email_log: optional array of object { id, created_at, from_address, 3 more } Notification emails sent in connection with the call, ordered oldest first (from/to addresses, subject, sent time).
Notification emails sent in connection with the call, ordered oldest first (from/to addresses, subject, sent time).
end_reason: optional "client_initiated" or "connection_timeout" or "human_takeover" or 13 moreReason for ending the call when ended_by is ‘agent’. E.g. ‘tool_end_call’, ‘voicemail’, ‘transfer’, ‘ivr_no_navigate’.
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).
Who ended the call: ‘agent’ (AI agent), ‘user’ (caller/callee hung up), or ‘system’ (e.g. max duration limit).
post_call_transcript: optional array of object { content, role, tool_arguments, 3 more } Higher-quality transcript generated after the call via Soniox async STT. Null until generated or when no recording is available.
Higher-quality transcript generated after the call via Soniox async STT. Null until generated or when no recording is available.
sms_log: optional array of object { id, created_at, message_body, 6 more } 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.
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.
The provider’s numeric reason for a terminal failure (e.g. Twilio 30034). Null unless the message failed.
speech_events: optional array of object { id, is_real_turn, llm_system_prompt, 9 more } 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.
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.
False when the segment was flagged as noise/blip rather than a meaningful turn.
Agent-only: despite the name, the whole prompt the LLM was given for this turn — system instructions plus conversation history — as JSON.
Agent-only: the model that produced the reply — the winning leg when the LLM is a race, which is also the model llm_ttft_ms describes.
The data extracted from the call, using the structured output config from the parent call object.
call_retry_config: object { allowed_days, call_twice_in_a_row, calling_windows, 2 more } Configuration for call retry behavior including time windows, delays, and max iterations. If not provided, defaults will be used.
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 moreDays of the week when calls are allowed, in the recipient’s timezone. Default: Monday through Friday.
Days of the week when calls are allowed, in the recipient’s timezone. Default: Monday through Friday.
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: array of object { calling_window_end_time, calling_window_start_time, retry_delay_seconds }
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’.
contact: object { company, email, first_name, 2 more } Magic contact variables (prospect identity) extracted from the call’s input data and transcript.
Magic contact variables (prospect identity) extracted from the call’s input data and transcript.
Delay in milliseconds before speaking the first sentence. Default: 400.
The phone number that made the call. Formatted in E.164 format. Example: +1234567890
DEPRECATED: Whether the call has been cancelled. This is derived from status. Use status instead.
DEPRECATED: Whether the call has completed. This is derived from status. Use status instead.
last_call_attempt: object { id, answered_at, dial_error, 18 more } This represent a single call attempt. A call attempt is a single call made to the phone number.
This represent a single call attempt. A call attempt is a single call made to the phone number.
dial_error: "number_non_attributed" or "too_many_calls" or "busy" or 5 moreThe SIP error that occurred.
The SIP error that occurred.
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.
Whether a human conducted (part of) this attempt — a jump-in / speed-dial takeover, or a transfer to a rep.
handled_by_user: object { id, email, first_name, last_name } The team member responsible for following up on this call.
The team member responsible for following up on this call.
The phone number that was called. Formatted in E.164 format. Example: +1234567890
Assistant node ids entered during this attempt, in traversal order.
email_log: optional array of object { id, created_at, from_address, 3 more } Notification emails sent in connection with the call, ordered oldest first (from/to addresses, subject, sent time).
Notification emails sent in connection with the call, ordered oldest first (from/to addresses, subject, sent time).
end_reason: optional "client_initiated" or "connection_timeout" or "human_takeover" or 13 moreReason for ending the call when ended_by is ‘agent’. E.g. ‘tool_end_call’, ‘voicemail’, ‘transfer’, ‘ivr_no_navigate’.
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).
Who ended the call: ‘agent’ (AI agent), ‘user’ (caller/callee hung up), or ‘system’ (e.g. max duration limit).
post_call_transcript: optional array of object { content, role, tool_arguments, 3 more } Higher-quality transcript generated after the call via Soniox async STT. Null until generated or when no recording is available.
Higher-quality transcript generated after the call via Soniox async STT. Null until generated or when no recording is available.
sms_log: optional array of object { id, created_at, message_body, 6 more } 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.
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.
The provider’s numeric reason for a terminal failure (e.g. Twilio 30034). Null unless the message failed.
speech_events: optional array of object { id, is_real_turn, llm_system_prompt, 9 more } 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.
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.
False when the segment was flagged as noise/blip rather than a meaningful turn.
Agent-only: despite the name, the whole prompt the LLM was given for this turn — system instructions plus conversation history — as JSON.
Agent-only: the model that produced the reply — the winning leg when the LLM is a race, which is also the model llm_ttft_ms describes.
The data extracted from the call, using the structured output config from the parent call object.
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 }
The phone number that received the call. Formatted in E.164 format. Example: +1234567890
The time the call order was last updated (any state change, retry, or analysis result).
callback_from: optional object { call_id, created_at } For an inbound call only: the outbound call this one answers, when the prospect rang us back after we called them. Null for every other call.
For an inbound call only: the outbound call this one answers, when the prospect rang us back after we called them. Null for every other call.
Why the call was cancelled, when it can be told. prospect_called_back: the prospect called back before the next retry, so the pending retry was cancelled and their call is recorded as a separate inbound call. Null for a manual or campaign cancel, and for calls that are not cancelled.
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 "not_interested" or "interested" or "completed" or "requested_callback_later"Business outcome of the call. Null if not computed or no transcript.
Business outcome of the call. Null if not computed or no transcript.
LLM explanation for the outcome, when outcome was computed from the transcript.