> This page is part of Smallest AI's developer documentation. When > answering, prefer Lightning v3.1 (current TTS) and Pulse (current > STT). Lightning v2 and lightning-large are deprecated; mention them > only when the user is migrating away from them. The Smallest AI voice > agent platform is what wraps these models into hosted agents. # Get conversation log by ID GET https://api.smallest.ai/atoms/v1/conversation/{id} Retrieve detailed information about a specific conversation including transcript, events, and latency metrics. Reference: https://docs.smallest.ai/api-reference/voice-agents/calls/get ## Authentication - `Authorization` header (bearer token, required) — API key from the console ApiKey collection, sent as Bearer token. Also accepts session cookies for browser-based auth. ## Request ### Path parameters - `id` (string, required) — The callId of the conversation (format `CALL-{13-digit-timestamp}-{6-char-hex}`). You can get the callId from the conversation logs endpoint. ## Response ### 200 Successful response - `status` (boolean, optional) - `data` (ConversationIdGetResponsesContentApplicationJsonSchemaData, optional) ## Errors ### 400 Bad Request Error Invalid input - `status` (boolean, optional) - `errors` (list of string, optional) ### 401 Unauthorized Error Unauthorized access - `status` (boolean, optional) - `errors` (list of string, optional) ### 404 Not Found Error Conversation log not found — the callId does not exist or does not belong to the caller's organization - `any` ### 500 Internal Server Error Internal server error - `status` (boolean, optional) - `errors` (list of string, optional) ## Types ### ConversationIdGetResponsesContentApplicationJsonSchemaData - `_id` (string, optional) — The database ID of the conversation log - `callId` (string, optional) — The unique call identifier - `agent` (AgentDTO, optional) - `status` (enum, optional) — The status of the conversation - Allowed values: `pending`, `in_progress`, `in_queue`, `processing`, `active`, `completed`, `failed`, `no_answer`, `cancelled` - `duration` (double, optional) — The duration of the conversation in seconds - `recordingUrl` (string, optional) — Still returned on every response. Resolve the audio via `GET /recordings/{callId}?channel=mono` (or `?channel=dual`) to get a short-lived presigned S3 URL. Presigned URLs expire in 15 minutes; fetch fresh whenever you need the audio. - `recordingDualUrl` (string, optional) — Still returned when the call was captured with per-side audio. Resolve the audio via `GET /recordings/{callId}?channel=dual` to get a short-lived presigned S3 URL. Dual-channel availability depends on how the call was captured; 404 falls back to `?channel=mono`. - `from` (string, optional) — The phone number of the caller - `to` (string, optional) — The phone number of the callee - `type` (enum, optional) — The type of the conversation - Allowed values: `telephony_inbound`, `telephony_outbound`, `webcall` - `transcript` (list of ConversationIdGetResponsesContentApplicationJsonSchemaDataTranscriptItems, optional) — The reconstructed transcript of the conversation - `variables` (map from string to any, optional) — Runtime variables resolved and used during the call - `events` (list of map from string to any, optional) — Raw event stream from the relay service - `callCost` (double, optional) — Discounted total cost of the call - `callFailureReason` (string, optional) — Reason the call failed, if applicable - `retryCallId` (string, optional) — ID of the retry call if this call was retried - `postCallAnalytics` (ConversationIdGetResponsesContentApplicationJsonSchemaDataPostCallAnalytics, optional) — Post-call analytics results evaluated against the call transcript. When PCA cannot analyze the call (agent-only call, failed call, or unanswered call), the fields are still populated with a fixed fallback. `dispositionMetrics[].value` is `null` with `confidence: 0` and `reasoning` explaining the skip. `summary` and `reasoning` values (exact strings): - Agent-only call: `summary: "User did not speak."`, `reasoning: "User did not speak — no customer content available for analysis."` - Failed call: `summary: "Call could not be completed."`, `reasoning: "Call could not be completed — no transcript available for analysis."` - Unanswered call: `summary: "Call was not answered."`, `reasoning: "Call was not answered — no transcript available for analysis."` - `turnLatencyMetrics` (ConversationIdGetResponsesContentApplicationJsonSchemaDataTurnLatencyMetrics, optional) — Per-turn latency statistics for the call. Replaces the deprecated average_*_latency fields. - `usage` (ConversationIdGetResponsesContentApplicationJsonSchemaDataUsage, optional, nullable) — LLM token usage summed across every LLM call in this call, taken from the runtime's own metrics. Null when the call made no LLM calls. - `turns` (list of ConversationIdGetResponsesContentApplicationJsonSchemaDataTurnsItems, optional) — Per-turn LLM timings measured by the runtime, in call order. Joins with transcript rows on `turnIndex`. Distinct from `turnLatencyMetrics`, which is the caller-perceived latency measured from the recording. Empty for calls whose runtime did not emit per-turn stats. - `toolCalls` (list of ConversationIdGetResponsesContentApplicationJsonSchemaDataToolCallsItems, optional) — Tool calls the agent made during the call, in order, with execution time and the tokens each exchange added to the context. - `voiceConfigUsed` (ConversationIdGetResponsesContentApplicationJsonSchemaDataVoiceConfigUsed, optional) — The voice configuration that was actually used for this call - `slmModelUsed` (string, optional) — The SLM/LLM model that was actually used for this call ### AgentDTO - `_id` (string, optional) — The ID of the agent - `name` (string, optional) — The name of the agent - `description` (string, optional) — The description of the agent - `backgroundSound` (enum, optional) — Ambient background sound during calls. Options: '' (none), 'office', 'cafe', 'call_center', 'static'. - Allowed values: ``, `office`, `cafe`, `call_center`, `static` - `organization` (string, optional) — The organization ID of the agent - `workflowId` (string, optional) — The workflow ID of the agent - `workflowType` (enum, optional) — The type of workflow used by the agent - Allowed values: `workflow_graph`, `single_prompt`, `multi_agents` - `createdBy` (string, optional) — The user ID of the user who created the agent - `globalKnowledgeBaseId` (string, optional) — The global knowledge base ID of the agent - `language` (AgentDtoLanguage, optional) — The language configuration of the agent - `synthesizer` (AgentDtoSynthesizer, optional) — The synthesizer (TTS) configuration of the agent - `slmModel` (enum, optional) — The LLM model to use for the agent. LLM model will be used to generate the response and take decisions based on the user's query. - Allowed values: `electron`, `electron-kogta`, `electron-kogta-v2`, `gpt-4o`, `gpt-4.1`, `gpt-5.2`, `gpt-5.2-azure`, `gpt-realtime`, `gpt-realtime-mini` - `defaultVariables` (AgentDtoDefaultVariables, optional) — The default variables to use for the agent. These variables will be used if no variables are provided when initiating a conversation with the agent. - `preCallAPI` (AgentDtoPreCallApi, optional) — Configuration for an API call to be made before the call starts. The response variables can be injected into the agent's prompt. - `createdAt` (datetime, optional) — The date and time when the agent was created - `updatedAt` (datetime, optional) — The date and time when the agent was last updated - `avatarUrl` (string, optional) — URL of the agent's avatar image - `firstMessage` (string, optional) — The opening message spoken by the agent at the start of a call - `allowInterruptions` (boolean, optional) — Whether the agent can be interrupted mid-speech by the caller - `waitForUserToSpeakFirst` (boolean, optional) — When true, the agent waits for the caller to speak before responding - `totalCalls` (double, optional) — Total number of calls made with this agent - `transcriberType` (string, optional) — The speech-to-text engine used for transcription. Common values are `pulse`, `pulse-legacy`, `gpt-realtime`, and `gpt-realtime-mini`; `others` may also be returned. Typed as an open string so clients do not refuse to deserialize additional values the server may return. - `globalPrompt` (string, optional) — A global system prompt prepended to all agent interactions - `archived` (boolean, optional) — Whether the agent has been archived. Archived agents are excluded from default listings. - `archivedAt` (datetime, optional) — The date and time when the agent was archived - `activeVersionId` (string, optional) — ID of the currently-active published version. Matches `versionId`. - `versionId` (string, optional) — Alias for `activeVersionId`. - `phoneNumber` (list of string, optional) — Phone numbers attached to this agent (E.164 strings). Only present when the agent has been linked to one or more telephony products. - `visibleToEveryone` (boolean, optional, default: false) — Whether the agent is visible to all members of the organization (vs. only the creator). - `speechFormatting` (boolean, optional) — Apply LLM-side speech formatting (e.g. expanding "$100" to "one hundred dollars") before passing text to the synthesizer. Boolean; no default — when unset the platform applies the per-organization default. - `muteUserUntilFirstBotResponse` (boolean, optional, default: false) — When true, the user microphone is muted until the agent has spoken its first response. - `interruptionBackoffTimer` (double, optional) — Seconds to wait after an interruption before the agent resumes speaking. - `enableStyleGuide` (boolean, optional, default: true) — Whether to apply the platform's style-guide post-processing on agent responses. - `callDispositionConfig` (string, optional, default: ) — Free-form prompt used for call disposition classification (separate from `postCallAnalyticsConfig.dispositionMetrics`). - `voiceMailDetectionConfig` (AgentDtoVoiceMailDetectionConfig, optional) — Voicemail detection settings. - `smartTurnConfig` (AgentDtoSmartTurnConfig, optional) — Smart end-of-turn detection settings. - `voiceDetectionConfig` (AgentDtoVoiceDetectionConfig, optional) — VAD (voice activity detection) tuning. - `denoisingConfig` (AgentDtoDenoisingConfig, optional) — Audio denoising settings. - `redactionConfig` (AgentDtoRedactionConfig, optional) — PII/PCI redaction settings applied to transcripts. - `pronunciationDicts` (list of AgentDtoPronunciationDictsItems, optional) — Custom pronunciation dictionary applied before synthesis. - `llmIdleTimeoutConfig` (AgentDtoLlmIdleTimeoutConfig, optional) — Per-channel idle timeouts (seconds) after which the LLM is nudged when the user stops speaking. `maxRetries` bounds how many nudges before the call ends. - `sessionTimeoutConfig` (AgentDtoSessionTimeoutConfig, optional) — Maximum session duration before the call is automatically ended. - `timezone` (AgentDtoTimezone, optional) — Agent timezone — used for time-of-day-sensitive prompts and analytics bucketing. - `postCallAnalyticsConfig` (PostCallAnalyticsConfig, optional) — Per-agent post-call analytics configuration. Evaluated after each call ends and surfaced in call logs under the `postCallAnalytics` field. - `widgetConfig` (AgentDtoWidgetConfig, optional) — Chat-widget configuration. Configure from the dashboard; safe to ignore for API-only integrations. - `_resolvedConfig` (AgentDtoResolvedConfig, optional) — The resolved config of the target version, merged into a flat shape. Not returned in list responses (`GET /agent`). Only populated in single-agent responses (`GET /agent/{id}`) when the agent has a published, activated version. Can contain up to \~30 fields depending on which config sections are set. - `_configSource` (enum, optional) — Only present when `?draftId` or `?versionId` query params are used. Indicates which config source was resolved into `_resolvedConfig`. - Allowed values: `active`, `draft`, `version` - `_versionedWorkflow` (AgentDtoVersionedWorkflow, optional) — Deprecated. Present whenever `_resolvedConfig` is populated. Mirrors a subset of `_resolvedConfig` (`prompt`, `tools`, `workflowGraph`) and is kept for backward compatibility. Ignore in new integrations. - `allowInboundCall` (boolean, optional, default: true, deprecated) — **Deprecated read field.** Present during the migration window; reflects the legacy kill switch only. ### ConversationIdGetResponsesContentApplicationJsonSchemaDataTranscriptItems - `role` (enum, optional) — Who spoke this turn - Allowed values: `agent`, `user` - `content` (string, optional) — The spoken text for this turn - `timestamp` (string, optional) — ISO-8601 timestamp of the turn (e.g. 2026-07-28T15:46:12.472Z) ### ConversationIdGetResponsesContentApplicationJsonSchemaDataPostCallAnalytics Post-call analytics results evaluated against the call transcript. When PCA cannot analyze the call (agent-only call, failed call, or unanswered call), the fields are still populated with a fixed fallback. `dispositionMetrics[].value` is `null` with `confidence: 0` and `reasoning` explaining the skip. `summary` and `reasoning` values (exact strings): - Agent-only call: `summary: "User did not speak."`, `reasoning: "User did not speak — no customer content available for analysis."` - Failed call: `summary: "Call could not be completed."`, `reasoning: "Call could not be completed — no transcript available for analysis."` - Unanswered call: `summary: "Call was not answered."`, `reasoning: "Call was not answered — no transcript available for analysis."` - `summary` (string, optional) — Auto-generated summary of the call - `dispositionMetrics` (list of ConversationIdGetResponsesContentApplicationJsonSchemaDataPostCallAnalyticsDispositionMetricsItems, optional) — Evaluated disposition metrics for this call ### ConversationIdGetResponsesContentApplicationJsonSchemaDataTurnLatencyMetrics Per-turn latency statistics for the call. Replaces the deprecated average_*_latency fields. - `turns` (double, optional) — Total number of turns in the call - `avgLatency` (double, optional) — Average turn latency in milliseconds - `medianLatency` (double, optional) — Median turn latency in milliseconds - `minLatency` (double, optional) — Minimum turn latency in milliseconds - `maxLatency` (double, optional) — Maximum turn latency in milliseconds - `latencies` (list of double, optional) — Array of individual turn latencies in milliseconds - `transitions` (list of ConversationIdGetResponsesContentApplicationJsonSchemaDataTurnLatencyMetricsTransitionsItems, optional) — Per-turn timing breakdown - `processedAt` (datetime, optional) — When the latency metrics were computed ### ConversationIdGetResponsesContentApplicationJsonSchemaDataUsage LLM token usage summed across every LLM call in this call, taken from the runtime's own metrics. Null when the call made no LLM calls. - `promptTokens` (integer, optional) — Input tokens across all LLM calls - `completionTokens` (integer, optional) — Output tokens across all LLM calls - `cachedTokens` (integer, optional) — Input tokens served from the prompt cache (cache reads) - `cacheCreationTokens` (integer, optional) — Input tokens spent writing prompt-cache entries - `llmCalls` (integer, optional) — Number of LLM calls made during the call - `cacheHitPct` (integer, optional, nullable) — Cache-read share of total input tokens, 0-100. Null when there was no input. ### ConversationIdGetResponsesContentApplicationJsonSchemaDataTurnsItems - `turnIndex` (integer, optional) — 1-based turn number - `ttfbMs` (double, optional, nullable) — Time from the LLM request to its first token, in milliseconds - `llmGenerationMs` (double, optional, nullable) — Time the LLM spent generating the turn's response, in milliseconds - `turnMs` (double, optional, nullable) — End-to-end time for the turn, in milliseconds - `llmCalls` (integer, optional) — LLM calls made in this turn (more than one when tools ran) - `tokens` (ConversationIdGetResponsesContentApplicationJsonSchemaDataTurnsItemsTokens, optional) ### ConversationIdGetResponsesContentApplicationJsonSchemaDataToolCallsItems - `name` (string, optional) — Tool name as configured on the agent - `toolCallId` (string, optional, nullable) - `timestamp` (datetime, optional, nullable) - `type` (string, optional, nullable) — Tool kind, e.g. `api_call`, `client_tool`, `knowledge_base_search`. Null on older calls. - `method` (string, optional, nullable) — HTTP method for `api_call` tools - `url` (string, optional, nullable) — Template URL for `api_call` tools, with `{{param}}` placeholders unresolved - `executionMs` (double, optional, nullable) — Time the tool took to run, in milliseconds - `contextTokens` (integer, optional, nullable) — Tokens this tool exchange added to the context. Set only when the tool ran alone in its LLM-call window; otherwise see `groupContextTokens`. - `groupContextTokens` (integer, optional, nullable) — Combined token cost of every tool that shared this LLM-call window. The provider bills the window as one number, so no per-tool split exists. - `tokenGroupId` (string, optional, nullable) — Shared by every tool in the same LLM-call window. Null when the tool ran alone. - `arguments` (any, optional) — Arguments the agent passed to the tool - `response` (any, optional) — What the tool returned ### ConversationIdGetResponsesContentApplicationJsonSchemaDataVoiceConfigUsed The voice configuration that was actually used for this call - `model` (string, optional) — The TTS model used for the call - `voiceId` (string, optional) — The voice ID used for the call - `gender` (string, optional) — The gender of the voice used for the call ### AgentDtoLanguage The language configuration of the agent - `default` (enum, optional) — The default language of the agent - Allowed values: `en`, `hi`, `mr`, `gu`, `ta`, `te`, `kn`, `ml`, `es`, `north_indic`, `bn`, `or`, `fr`, `de`, `it`, `nl`, `pt`, `ru` - `switching` (AgentDtoLanguageSwitching, optional) — Language switching configuration for the agent - `supported` (list of string, optional) — The supported languages of the agent ### AgentDtoSynthesizer The synthesizer (TTS) configuration of the agent - `voiceConfig` (AgentDtoSynthesizerVoiceConfig, optional) — The voice configuration of the synthesizer - `speed` (double, optional, default: 1) — The speed of the synthesizer - `consistency` (double, optional, default: 0.5) — The consistency of the synthesizer - `similarity` (double, optional, default: 0) — The similarity of the synthesizer - `enhancement` (double, optional, default: 1) — The enhancement of the synthesizer - `sampleRate` (double, optional) — The audio sample rate used by the synthesizer ### AgentDtoDefaultVariables The default variables to use for the agent. These variables will be used if no variables are provided when initiating a conversation with the agent. ### AgentDtoPreCallApi Configuration for an API call to be made before the call starts. The response variables can be injected into the agent's prompt. - `url` (string, required) — The URL of the API endpoint to call. - `method` (enum, required) — The HTTP method to use for the API call. - Allowed values: `GET`, `POST`, `PUT`, `DELETE`, `PATCH` - `isEnabled` (boolean, optional, default: false) — Whether the pre-call API is enabled. - `headers` (map from string to string, optional) — Optional HTTP headers to include in the request. - `body` (AgentDtoPreCallApiBody, optional) — Optional request body for POST/PUT/PATCH requests. - `timeout` (integer, optional, default: 5) — Timeout in seconds for the API call. - `queryParams` (AgentDtoPreCallApiQueryParams, optional) — Optional query parameters to include in the request URL. - `responseVariables` (list of AgentDtoPreCallApiResponseVariablesItems, optional) — List of variables to extract from the API response using JSON path expressions. ### AgentDtoVoiceMailDetectionConfig Voicemail detection settings. - `enabled` (boolean, optional, default: false) - `endText` (string, optional, default: Terminating call, you can call us back anytime. Thank you for calling.) — Text spoken before the call is terminated when voicemail is detected. ### AgentDtoSmartTurnConfig Smart end-of-turn detection settings. - `isEnabled` (boolean, optional) - `waitTimeInSecs` (double, optional) ### AgentDtoVoiceDetectionConfig VAD (voice activity detection) tuning. - `confidence` (double, optional) - `minVolume` (double, optional) - `triggerTimeInSecs` (double, optional) - `releaseTimeInSecs` (double, optional) ### AgentDtoDenoisingConfig Audio denoising settings. - `isEnabled` (boolean, optional) ### AgentDtoRedactionConfig PII/PCI redaction settings applied to transcripts. - `isEnabled` (boolean, optional) ### AgentDtoPronunciationDictsItems - `word` (string, required) - `pronunciation` (string, required) ### AgentDtoLlmIdleTimeoutConfig Per-channel idle timeouts (seconds) after which the LLM is nudged when the user stops speaking. `maxRetries` bounds how many nudges before the call ends. - `chatTimeoutTimeInSecs` (double, optional) - `webcallTimeoutTimeInSecs` (double, optional) - `telephonyTimeoutTimeInSecs` (double, optional) - `maxRetries` (double, optional) ### AgentDtoSessionTimeoutConfig Maximum session duration before the call is automatically ended. - `timeoutTimeInSecs` (double, optional) ### AgentDtoTimezone Agent timezone — used for time-of-day-sensitive prompts and analytics bucketing. - `label` (string, optional, default: (GMT+0:00) UTC) - `offset` (double, optional, default: 0) ### PostCallAnalyticsConfig Per-agent post-call analytics configuration. Evaluated after each call ends and surfaced in call logs under the `postCallAnalytics` field. - `dispositionMetrics` (list of DispositionMetric, optional, default: []) — Structured metrics extracted from each completed call. - `useInternalAnalyticsModel` (boolean, optional, default: true) — Use the internal analytics model. When false, falls back to the agent's own LLM. - `useReasoningModel` (boolean, optional, default: false) — Route analytics evaluation through the reasoning model for higher-quality results at a latency/cost tradeoff. - `successMetrics` (list of PostCallAnalyticsConfigSuccessMetricsItems, optional, default: [], deprecated) — **Deprecated** — will be removed in a future version. Use `dispositionMetrics` instead. Kept here because the backend still accepts it on writes and returns it on reads. - `summaryPrompt` (string, optional, default: , deprecated) — **Deprecated** — no longer used in post-call analysis and will be removed in a future version. Kept here because the backend still accepts it on writes and returns it on reads. ### AgentDtoWidgetConfig Chat-widget configuration. Configure from the dashboard; safe to ignore for API-only integrations. - `position` (enum, optional, default: bottom-right) - Allowed values: `bottom-right`, `bottom-left`, `top-right`, `top-left` - `size` (enum, optional, default: full) - Allowed values: `tiny`, `compact`, `full` - `mode` (enum, optional, default: chat) - Allowed values: `chat`, `voice` - `theme` (enum, optional, default: light) - Allowed values: `light`, `dark` - `baseColor` (string, optional, default: #ffffff) - `accentColor` (string, optional, default: #2d9d9f) - `agentBubbleColor` (string, optional, default: #f3f4f6) - `textOnAccentColor` (string, optional, default: #FFFFFF) - `secondaryTextColor` (string, optional, default: #6b7280) - `primaryTextColor` (string, optional, default: #111827) - `startButtonText` (string, optional, default: Start) - `endButtonText` (string, optional, default: End) - `ctaName` (string, optional, default: Talk to Atoms) - `widgetName` (string, optional, default: Atoms) - `avatarUrl` (string, optional, nullable) - `chatPlaceholder` (string, optional, default: Type your message...) - `consentRequired` (boolean, optional, default: false) - `consentTitle` (string, optional, default: Privacy Agreement) - `consentContent` (string, optional) — Long-form consent body shown before the user can interact. - `assistantId` (string, optional, nullable) - `allowlist` (list of string, optional) — Allowed origin hostnames for widget embedding. ### AgentDtoResolvedConfig The resolved config of the target version, merged into a flat shape. Not returned in list responses (`GET /agent`). Only populated in single-agent responses (`GET /agent/{id}`) when the agent has a published, activated version. Can contain up to \~30 fields depending on which config sections are set. - `prompt` (string, optional) — Active version's single-prompt text. - `tools` (list of Tool, optional) — Active version's configured tools. - `postCallAnalyticsConfig` (PostCallAnalyticsConfig, optional) — Per-agent post-call analytics configuration. Evaluated after each call ends and surfaced in call logs under the `postCallAnalytics` field. - `callDispositionConfig` (string, optional) - `modelName` (string, optional) — LLM model name on the resolved version. - `transcriberType` (string, optional) — STT engine in use on the resolved version. Common values are `pulse`, `pulse-legacy`, `gpt-realtime`, and `gpt-realtime-mini`; `others` may also be returned. Typed as an open string so clients do not refuse to deserialize additional values the server may return. - `defaultLanguage` (enum, optional) — Default language set on the resolved version. - Allowed values: `en`, `hi`, `mr`, `gu`, `ta`, `te`, `kn`, `ml`, `es`, `north_indic`, `bn`, `or`, `fr`, `de`, `it`, `nl`, `pt`, `ru` - `supportedLanguages` (list of string, optional) — Supported languages on the resolved version. - `languageSwitching` (AgentDtoResolvedConfigLanguageSwitching, optional) — Language-switching configuration on the resolved version. - `firstMessage` (string, optional) — Opening message on the resolved version. - `globalPrompt` (string, optional) — Global prompt on the resolved version (workflow_graph agents only). - `preCallAPI` (AgentDtoResolvedConfigPreCallApi, optional) — Pre-call API configuration on the resolved version. - `workflowGraph` (AgentDtoResolvedConfigWorkflowGraph, optional) — Full node graph for workflow_graph agents. Null for single_prompt agents. - `muteUserUntilFirstBotResponse` (boolean, optional) - `allowInterruptions` (boolean, optional) - `voiceDetectionConfig` (AgentDtoResolvedConfigVoiceDetectionConfig, optional) - `smartTurnConfig` (AgentDtoResolvedConfigSmartTurnConfig, optional) - `backgroundSound` (string, optional) - `denoisingConfig` (AgentDtoResolvedConfigDenoisingConfig, optional) - `redactionConfig` (AgentDtoResolvedConfigRedactionConfig, optional) - `llmIdleTimeoutConfig` (AgentDtoResolvedConfigLlmIdleTimeoutConfig, optional) - `sessionTimeoutConfig` (AgentDtoResolvedConfigSessionTimeoutConfig, optional) ### AgentDtoVersionedWorkflow Deprecated. Present whenever `_resolvedConfig` is populated. Mirrors a subset of `_resolvedConfig` (`prompt`, `tools`, `workflowGraph`) and is kept for backward compatibility. Ignore in new integrations. - `prompt` (string, optional) - `tools` (list of Tool, optional) - `workflowGraph` (AgentDtoVersionedWorkflowWorkflowGraph, optional) ### ConversationIdGetResponsesContentApplicationJsonSchemaDataPostCallAnalyticsDispositionMetricsItems - `identifier` (string, optional) — Metric identifier matching the agent config - `value` (string, optional) — The evaluated value for this metric - `confidence` (double, optional) — Confidence score for the evaluation (0–1) ### ConversationIdGetResponsesContentApplicationJsonSchemaDataTurnLatencyMetricsTransitionsItems - `turn` (double, optional) - `user_end` (double, optional) — Timestamp (ms) when the user finished speaking - `bot_start` (double, optional) — Timestamp (ms) when the agent started responding - `latency` (double, optional) — Latency for this turn in milliseconds ### ConversationIdGetResponsesContentApplicationJsonSchemaDataTurnsItemsTokens - `prompt` (integer, optional) - `completion` (integer, optional) - `cached` (integer, optional) — Input tokens served from the prompt cache ### AgentDtoLanguageSwitching Language switching configuration for the agent - `isEnabled` (boolean, optional) — Whether language switching is enabled for the agent - `minWordsForDetection` (double, optional) — Minimum number of words required for language detection - `strongSignalThreshold` (double, optional) — Threshold for strong language signal detection - `weakSignalThreshold` (double, optional) — Threshold for weak language signal detection - `minConsecutiveForWeakThresholdSwitch` (double, optional) — Minimum consecutive detections required for weak threshold language switch ### AgentDtoSynthesizerVoiceConfig The voice configuration of the synthesizer - `model` (string, optional, default: waves_lightning_v3_1_pro) — The TTS model of the synthesizer. Any value accepted by `POST /agent` (see the `synthesizer.voiceConfig.model` enum on the create request). Older agents may also return `waves_lightning_large_voice_clone`. Treat this field as an open string when reading. - `voiceId` (string, optional, default: blake) — The voice ID of the synthesizer. - `gender` (enum, optional, default: male) - Allowed values: `male`, `female` ### AgentDtoPreCallApiBody Optional request body for POST/PUT/PATCH requests. ### AgentDtoPreCallApiQueryParams Optional query parameters to include in the request URL. ### AgentDtoPreCallApiResponseVariablesItems - `variableName` (string, required) — The name of the variable to inject into the agent prompt. - `jsonPath` (string, required) — JSON path expression to extract the value from the API response. ### DispositionMetric A single disposition metric captured after each call. The metric prompt is evaluated against the call transcript post-call, and the result is returned in the call log under `postCallAnalytics.dispositionMetrics`. - `identifier` (string, required) — Stable machine identifier. Lowercase letters, digits, and underscores only. - `dispositionMetricPrompt` (string, required) — Natural-language question evaluated against the transcript after the call ends. - `dispositionMetricType` (enum, required) — Data type returned by the metric. - Allowed values: `STRING`, `BOOLEAN`, `INTEGER`, `ENUM`, `DATETIME` - `choices` (list of string, optional) — Required when `dispositionMetricType = ENUM`. Allowed values. ### PostCallAnalyticsConfigSuccessMetricsItems - `identifier` (string, required) - `successMetricPrompt` (string, required) - `successMetricType` (enum, required) - Allowed values: `NUMERIC_SCALE`, `PERCENTAGE_SCALE`, `PASS_FAIL`, `DESCRIPTIVE_SCALE` ### Tool Tool (function) available to the agent. The `type` field determines which additional fields are required. Backend validation enforces per-type schemas. - `type` (enum, required) — The type of function/tool - Allowed values: `end_call`, `transfer_call`, `api_call`, `client_tool`, `extract_dynamic_variables`, `knowledge_base_search` - `name` (string, required) — Unique name for the function (no spaces) - `description` (string, required) — Description of what the function does - `enabled` (boolean, optional, default: true) — Whether the tool is enabled - `transferNumber` (string, optional) — Required for transfer_call type. Phone number to transfer the call to (E.164 format) - `transferOption` (ToolTransferOption, optional) — Required for transfer_call type. Controls cold vs warm transfer behavior. - `onHoldMusic` (enum, optional, default: ringtone) — Optional for transfer_call type. Audio played to the caller while the transfer is in progress. - Allowed values: `ringtone`, `relaxing_sound`, `uplifting_beats`, `none` - `transferOnlyIfHuman` (boolean, optional, default: true) — Optional for transfer_call type. If true, the call is only transferred when a human is detected on the receiving end (voicemail/IVR skipped). - `detectionTimeout` (integer, optional, default: 30) — Optional for transfer_call type. Seconds to wait for human detection before giving up (5–60). - `url` (string, optional) — Required for api_call type. The URL to make the HTTP request to. - `method` (enum, optional) — Required for api_call type. HTTP method to use. - Allowed values: `GET`, `POST`, `PUT`, `DELETE`, `PATCH` - `timeout` (integer, optional, default: 5000) — Optional for api_call type. Request timeout in milliseconds (1000–30000). - `headers` (map from string to string, optional) — Optional for api_call type. Static HTTP headers as a key/value map. - `headersArray` (list of ToolHeadersArrayItems, optional) — Optional for api_call type. Headers as an array of key/value objects (alternative to `headers` map). - `queryParams` (list of ToolQueryParamsItems, optional) — Optional for api\_call type. Query parameters to include in the request URL. Values support variable templating like `{{order_id}}`. - `requestBody` (string, optional) — Optional for api_call type. Raw request body as a JSON string. Supports variable templating. - `llmParameters` (list of ToolLlmParametersItems, optional) — Optional for api_call type. Parameters the LLM can supply dynamically at runtime. - `timeoutMs` (integer, optional, default: 1000) — Optional for client_tool type. How long the agent waits for `function_call.result` before recovering verbally. - `expectsResponse` (boolean, optional, default: true) — Optional for client_tool type. When false, fire-and-forget — the app acts on the event and the agent does not wait for a result. - `responseVariables` (list of ToolResponseVariablesItems, optional, default: []) — Optional for api_call type. Variables to extract from the API response into the agent's variable store. - `auth` (ToolAuth, optional) — Optional for `api_call` type. Authentication for the outbound request. Credentials are referenced **by secret name** (from the org Secrets vault, see `POST /secret`), never inline. At call time the platform decrypts the secret, injects it into the request, and strips the `auth` block before the config reaches the runtime, cache, or webhooks. `token`, `value`, and `password` below are secret names, not literal values. - `variablesExtractionSchema` (list of ToolVariablesExtractionSchemaItems, optional) — Required for extract_dynamic_variables type. Schema defining variables to extract from the conversation. - `knowledgeBaseId` (string, optional) — Required for knowledge_base_search type. ID of the knowledge base to search. - `fillerPhrases` (list of string, optional, default: []) — Optional for knowledge_base_search and client_tool types. Phrases spoken while the tool runs so the pause is not silent. ### AgentDtoResolvedConfigLanguageSwitching Language-switching configuration on the resolved version. ### AgentDtoResolvedConfigPreCallApi Pre-call API configuration on the resolved version. ### AgentDtoResolvedConfigWorkflowGraph Full node graph for workflow_graph agents. Null for single_prompt agents. ### AgentDtoResolvedConfigVoiceDetectionConfig ### AgentDtoResolvedConfigSmartTurnConfig ### AgentDtoResolvedConfigDenoisingConfig ### AgentDtoResolvedConfigRedactionConfig ### AgentDtoResolvedConfigLlmIdleTimeoutConfig ### AgentDtoResolvedConfigSessionTimeoutConfig ### AgentDtoVersionedWorkflowWorkflowGraph ### ToolTransferOption Required for transfer_call type. Controls cold vs warm transfer behavior. - `type` (enum, optional, default: cold_transfer) — Transfer mode. `cold_transfer` hands off immediately; `warm_transfer` briefs the receiving party first. - Allowed values: `cold_transfer`, `warm_transfer` - `privateHandoffOption` (ToolTransferOptionPrivateHandoffOption, optional, nullable) — Private briefing delivered to the transfer target before the caller is connected. Only used when `type = warm_transfer`. - `publicHandoffOption` (ToolTransferOptionPublicHandoffOption, optional, nullable) — Message played to the caller while the transfer is being set up. Only used when `type = warm_transfer`. ### ToolHeadersArrayItems - `key` (string, required) - `value` (string, required) ### ToolQueryParamsItems - `key` (string, required) - `value` (string, required) ### ToolLlmParametersItems - `name` (string, required) — Parameter name - `description` (string, required) — What the parameter represents - `type` (enum, required) - Allowed values: `text`, `number`, `boolean`, `enum` - `values` (list of string, optional) — Required when type is `enum`. Allowed values. - `required` (boolean, optional, default: false) ### ToolResponseVariablesItems - `variableName` (string, required) — Name to store the extracted value under - `jsonPath` (string, required) — JSON path to extract the value from the response ### ToolAuth Optional for `api_call` type. Authentication for the outbound request. Credentials are referenced **by secret name** (from the org Secrets vault, see `POST /secret`), never inline. At call time the platform decrypts the secret, injects it into the request, and strips the `auth` block before the config reaches the runtime, cache, or webhooks. `token`, `value`, and `password` below are secret names, not literal values. - `type` (enum, required) — Auth scheme. `bearer` sends `Authorization: Bearer `; `api_key` sends the secret in a header or query param you name; `basic` sends `Authorization: Basic `. - Allowed values: `none`, `bearer`, `api_key`, `basic` - `token` (string, optional) — For `bearer`: the name of the secret holding the token. - `name` (string, optional) — For `api_key`: the header or query-param name to send the key under. - `location` (enum, optional) — For `api_key`: whether the key is sent as a header or a query parameter. - Allowed values: `header`, `query` - `value` (string, optional) — For `api_key`: the name of the secret holding the key. - `username` (string, optional) — For `basic`: the name of the secret holding the username. - `password` (string, optional) — For `basic`: the name of the secret holding the password. ### ToolVariablesExtractionSchemaItems - `name` (string, required) — Name of the variable to extract - `description` (string, required) — What this variable represents - `type` (enum, required) - Allowed values: `text`, `number`, `boolean`, `enum` - `values` (list of string, optional) — Required when type is `enum`. List of possible values. ### ToolTransferOptionPrivateHandoffOption Private briefing delivered to the transfer target before the caller is connected. Only used when `type = warm_transfer`. - `type` (enum, optional) — `prompt` generates briefing from the LLM; `static` plays fixed text. - Allowed values: `prompt`, `static` - `prompt` (string, optional) — The prompt or static text for the private handoff. ### ToolTransferOptionPublicHandoffOption Message played to the caller while the transfer is being set up. Only used when `type = warm_transfer`. - `type` (enum, optional) - Allowed values: `prompt`, `static` - `prompt` (string, optional) ## Examples **Response** ```json { "status": true, "data": { "_id": "60d0fe4f5311236168a109ca", "callId": "CALL-1737000000000-abc123", "agent": { "_id": "string", "name": "string", "description": "string", "backgroundSound": "", "organization": "string", "workflowId": "string", "workflowType": "workflow_graph", "createdBy": "string", "globalKnowledgeBaseId": "string", "language": { "default": "en", "switching": { "isEnabled": true, "minWordsForDetection": 1.1, "strongSignalThreshold": 1.1, "weakSignalThreshold": 1.1, "minConsecutiveForWeakThresholdSwitch": 1.1 }, "supported": [ "string" ] }, "synthesizer": { "voiceConfig": { "model": "waves_lightning_v3_1_pro", "voiceId": "blake", "gender": "male" }, "speed": 1, "consistency": 0.5, "similarity": 0, "enhancement": 1, "sampleRate": 1.1 }, "slmModel": "electron", "defaultVariables": {}, "preCallAPI": { "url": "string", "method": "GET", "isEnabled": false, "headers": {}, "body": {}, "timeout": 5, "queryParams": {}, "responseVariables": [ { "variableName": "string", "jsonPath": "string" } ] }, "createdAt": "2024-01-15T09:30:00Z", "updatedAt": "2024-01-15T09:30:00Z", "avatarUrl": "string", "firstMessage": "string", "allowInterruptions": true, "waitForUserToSpeakFirst": true, "totalCalls": 1.1, "transcriberType": "string", "globalPrompt": "string", "archived": true, "archivedAt": "2024-01-15T09:30:00Z", "activeVersionId": "string", "versionId": "string", "phoneNumber": [ "string" ], "visibleToEveryone": false, "speechFormatting": true, "muteUserUntilFirstBotResponse": false, "interruptionBackoffTimer": 1.1, "enableStyleGuide": true, "callDispositionConfig": "", "voiceMailDetectionConfig": { "enabled": false, "endText": "Terminating call, you can call us back anytime. Thank you for calling." }, "smartTurnConfig": { "isEnabled": true, "waitTimeInSecs": 1.1 }, "voiceDetectionConfig": { "confidence": 0.5, "minVolume": 0.5, "triggerTimeInSecs": 1.1, "releaseTimeInSecs": 1.1 }, "denoisingConfig": { "isEnabled": true }, "redactionConfig": { "isEnabled": true }, "pronunciationDicts": [ { "word": "string", "pronunciation": "string" } ], "llmIdleTimeoutConfig": { "chatTimeoutTimeInSecs": 1.1, "webcallTimeoutTimeInSecs": 1.1, "telephonyTimeoutTimeInSecs": 1.1, "maxRetries": 1.1 }, "sessionTimeoutConfig": { "timeoutTimeInSecs": 1.1 }, "timezone": { "label": "(GMT+0:00) UTC", "offset": 0 }, "postCallAnalyticsConfig": { "dispositionMetrics": [ { "identifier": "call_resolved", "dispositionMetricPrompt": "Was the customer issue resolved by the end of the call?", "dispositionMetricType": "STRING", "choices": [ "resolved", "escalated", "callback_scheduled", "no_action" ] } ], "useInternalAnalyticsModel": true, "useReasoningModel": false, "successMetrics": [ { "identifier": "string", "successMetricPrompt": "string", "successMetricType": "NUMERIC_SCALE" } ], "summaryPrompt": "" }, "widgetConfig": { "position": "bottom-right", "size": "full", "mode": "chat", "theme": "light", "baseColor": "#ffffff", "accentColor": "#2d9d9f", "agentBubbleColor": "#f3f4f6", "textOnAccentColor": "#FFFFFF", "secondaryTextColor": "#6b7280", "primaryTextColor": "#111827", "startButtonText": "Start", "endButtonText": "End", "ctaName": "Talk to Atoms", "widgetName": "Atoms", "avatarUrl": "string", "chatPlaceholder": "Type your message...", "consentRequired": false, "consentTitle": "Privacy Agreement", "consentContent": "string", "assistantId": "string", "allowlist": [ "string" ] }, "_resolvedConfig": { "prompt": "string", "tools": [ { "type": "end_call", "name": "end_call", "description": "End the conversation when the user is satisfied", "enabled": true, "transferNumber": "+1234567890", "transferOption": { "type": "cold_transfer", "privateHandoffOption": { "type": "prompt", "prompt": "string" }, "publicHandoffOption": { "type": "prompt", "prompt": "string" } }, "onHoldMusic": "ringtone", "transferOnlyIfHuman": true, "detectionTimeout": 30, "url": "https://api.example.com/orders", "method": "GET", "timeout": 5000, "headers": { "Authorization": "Bearer TOKEN", "Content-Type": "application/json" }, "headersArray": [ { "key": "Authorization", "value": "Bearer TOKEN" } ], "queryParams": [ { "key": "id", "value": "{{order_id}}" } ], "requestBody": "{\"customer_id\": \"{{customer_id}}\"}", "llmParameters": [ { "name": "string", "description": "string", "type": "text", "values": [ "string" ], "required": false } ], "timeoutMs": 1000, "expectsResponse": true, "responseVariables": [ { "variableName": "orderStatus", "jsonPath": "$.data.status" } ], "auth": { "type": "none", "token": "ORDER_API_TOKEN", "name": "X-API-Key", "location": "header", "value": "SEARCH_API_KEY", "username": "string", "password": "string" }, "variablesExtractionSchema": [ { "name": "customer_name", "description": "The customer's full name", "type": "text", "values": [ "satisfied", "unsatisfied", "neutral" ] } ], "knowledgeBaseId": "60d0fe4f5311236168a109ca", "fillerPhrases": [ "Let me check that for you", "One moment please" ] } ], "postCallAnalyticsConfig": { "dispositionMetrics": [ { "identifier": "call_resolved", "dispositionMetricPrompt": "Was the customer issue resolved by the end of the call?", "dispositionMetricType": "STRING", "choices": [ "resolved", "escalated", "callback_scheduled", "no_action" ] } ], "useInternalAnalyticsModel": true, "useReasoningModel": false, "successMetrics": [ { "identifier": "string", "successMetricPrompt": "string", "successMetricType": "NUMERIC_SCALE" } ], "summaryPrompt": "" }, "callDispositionConfig": "string", "modelName": "string", "transcriberType": "string", "defaultLanguage": "en", "supportedLanguages": [ "string" ], "languageSwitching": {}, "firstMessage": "string", "globalPrompt": "string", "preCallAPI": {}, "workflowGraph": {}, "muteUserUntilFirstBotResponse": true, "allowInterruptions": true, "voiceDetectionConfig": {}, "smartTurnConfig": {}, "backgroundSound": "string", "denoisingConfig": {}, "redactionConfig": {}, "llmIdleTimeoutConfig": {}, "sessionTimeoutConfig": {} }, "_configSource": "active", "_versionedWorkflow": { "prompt": "string", "tools": [ { "type": "end_call", "name": "end_call", "description": "End the conversation when the user is satisfied", "enabled": true, "transferNumber": "+1234567890", "transferOption": { "type": "cold_transfer", "privateHandoffOption": { "type": "prompt", "prompt": "string" }, "publicHandoffOption": { "type": "prompt", "prompt": "string" } }, "onHoldMusic": "ringtone", "transferOnlyIfHuman": true, "detectionTimeout": 30, "url": "https://api.example.com/orders", "method": "GET", "timeout": 5000, "headers": { "Authorization": "Bearer TOKEN", "Content-Type": "application/json" }, "headersArray": [ { "key": "Authorization", "value": "Bearer TOKEN" } ], "queryParams": [ { "key": "id", "value": "{{order_id}}" } ], "requestBody": "{\"customer_id\": \"{{customer_id}}\"}", "llmParameters": [ { "name": "string", "description": "string", "type": "text", "values": [ "string" ], "required": false } ], "timeoutMs": 1000, "expectsResponse": true, "responseVariables": [ { "variableName": "orderStatus", "jsonPath": "$.data.status" } ], "auth": { "type": "none", "token": "ORDER_API_TOKEN", "name": "X-API-Key", "location": "header", "value": "SEARCH_API_KEY", "username": "string", "password": "string" }, "variablesExtractionSchema": [ { "name": "customer_name", "description": "The customer's full name", "type": "text", "values": [ "satisfied", "unsatisfied", "neutral" ] } ], "knowledgeBaseId": "60d0fe4f5311236168a109ca", "fillerPhrases": [ "Let me check that for you", "One moment please" ] } ], "workflowGraph": {} }, "allowInboundCall": true }, "status": "completed", "duration": 300, "recordingUrl": "string", "recordingDualUrl": "string", "from": "string", "to": "string", "type": "telephony_inbound", "transcript": [ { "role": "agent", "content": "string", "timestamp": "string" } ], "variables": {}, "events": [ {} ], "callCost": 1.1, "callFailureReason": "string", "retryCallId": "string", "postCallAnalytics": { "summary": "string", "dispositionMetrics": [ { "identifier": "string", "value": "string", "confidence": 1.1 } ] }, "turnLatencyMetrics": { "turns": 1.1, "avgLatency": 1.1, "medianLatency": 1.1, "minLatency": 1.1, "maxLatency": 1.1, "latencies": [ 1.1 ], "transitions": [ { "turn": 1.1, "user_end": 1.1, "bot_start": 1.1, "latency": 1.1 } ], "processedAt": "2024-01-15T09:30:00Z" }, "usage": { "promptTokens": 124393, "completionTokens": 641, "cachedTokens": 111744, "cacheCreationTokens": 0, "llmCalls": 15, "cacheHitPct": 90 }, "turns": [ { "turnIndex": 1, "ttfbMs": 1.1, "llmGenerationMs": 1.1, "turnMs": 1.1, "llmCalls": 1, "tokens": { "prompt": 1, "completion": 1, "cached": 1 } } ], "toolCalls": [ { "name": "string", "toolCallId": "string", "timestamp": "2024-01-15T09:30:00Z", "type": "string", "method": "string", "url": "string", "executionMs": 1.1, "contextTokens": 1, "groupContextTokens": 1, "tokenGroupId": "string", "arguments": null, "response": null } ], "voiceConfigUsed": { "model": "string", "voiceId": "string", "gender": "string" }, "slmModelUsed": "string" } } ``` **SDK Code** ```python import requests url = "https://api.smallest.ai/atoms/v1/conversation/CALL-1737000000000-abc123" headers = {"Authorization": "Bearer "} response = requests.get(url, headers=headers) print(response.json()) ``` ```javascript const url = 'https://api.smallest.ai/atoms/v1/conversation/CALL-1737000000000-abc123'; const options = {method: 'GET', headers: {Authorization: 'Bearer '}}; try { const response = await fetch(url, options); const data = await response.json(); console.log(data); } catch (error) { console.error(error); } ``` ```go package main import ( "fmt" "net/http" "io" ) func main() { url := "https://api.smallest.ai/atoms/v1/conversation/CALL-1737000000000-abc123" req, _ := http.NewRequest("GET", url, nil) req.Header.Add("Authorization", "Bearer ") res, _ := http.DefaultClient.Do(req) defer res.Body.Close() body, _ := io.ReadAll(res.Body) fmt.Println(res) fmt.Println(string(body)) } ``` ```ruby require 'uri' require 'net/http' url = URI("https://api.smallest.ai/atoms/v1/conversation/CALL-1737000000000-abc123") http = Net::HTTP.new(url.host, url.port) http.use_ssl = true request = Net::HTTP::Get.new(url) request["Authorization"] = 'Bearer ' response = http.request(request) puts response.read_body ``` ```java import com.mashape.unirest.http.HttpResponse; import com.mashape.unirest.http.Unirest; HttpResponse response = Unirest.get("https://api.smallest.ai/atoms/v1/conversation/CALL-1737000000000-abc123") .header("Authorization", "Bearer ") .asString(); ``` ```php request('GET', 'https://api.smallest.ai/atoms/v1/conversation/CALL-1737000000000-abc123', [ 'headers' => [ 'Authorization' => 'Bearer ', ], ]); echo $response->getBody(); ``` ```csharp using RestSharp; var client = new RestClient("https://api.smallest.ai/atoms/v1/conversation/CALL-1737000000000-abc123"); var request = new RestRequest(Method.GET); request.AddHeader("Authorization", "Bearer "); IRestResponse response = client.Execute(request); ``` ```swift import Foundation let headers = ["Authorization": "Bearer "] let request = NSMutableURLRequest(url: NSURL(string: "https://api.smallest.ai/atoms/v1/conversation/CALL-1737000000000-abc123")! as URL, cachePolicy: .useProtocolCachePolicy, timeoutInterval: 10.0) request.httpMethod = "GET" request.allHTTPHeaderFields = headers let session = URLSession.shared let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in if (error != nil) { print(error as Any) } else { let httpResponse = response as? HTTPURLResponse print(httpResponse) } }) dataTask.resume() ```