--- title: "List" method: GET path: "/conversations" tags: ["conversations"] --- # List `GET /conversations` Returns conversations with optional filtering. ## Query parameters - `project` string - `external_id` string - `duration_min` integer - `duration_max` integer - `started_at_min` string - `started_at_max` string - `before` string - `after` string - `limit` integer - `audio_container` 'wav.gz' | 'wav' ## Headers - `Authorization` string, required ## Response `200` Paginated list (`conversations`, `pagination`) when listing, or a single `conversation` when the `external_id` query parameter matches exactly one conversation. - union - ListConversationsResponse - `conversations` Conversation[], required - `id` string, required — The conversation ID. - `agent` ConversationAgent, required — The agent associated with the conversation. - `id` string, required — The ID of the agent. - `name` string, required — The name of the agent. - `is_deleted` boolean, required — Whether the agent has been deleted. - `workspace` string, required — The organization/workspace name. - `project` ConversationProject, required — The project associated with the conversation. - `id` string, required — The ID of the project. - `name` string, required — The name of the project. - `external_id` string, nullable, required — External ID for conversation tracking. - `origin` 'web' | 'web-playground' | 'web-demo' | 'direct' | 'livekit-agents-py' | 'livekit-agents-js' | 'sdk-py' | 'sdk-js' | 'inbound' | 'telephony-inbound' | 'outbound' | 'telephony-outbound' | 'replay', required — The origin of the conversation. - `model` string, required — The STS model used. - `generate_welcome_message` boolean, required — Will be `true` if welcome message was automatically generated. - `is_welcome_message_interruptible` boolean, required — When `false`, the welcome message will not be interruptible by the user. - `welcome_message` string, nullable, required — Welcome message played at start. Will be `null` when `generate_welcome_message` is `true`. - `template_variables` object, required — Template variables used in the conversation. - `system_prompt` string, nullable — System prompt used in the conversation. - `input_format` string, required — Audio input format. - `output_format` string, required — Audio output format. - `background_noise_level` number, double, required — Background noise level used in the conversation. - `background_noise` 'office' | 'call-center' | 'coffee-shop', required — The background noise type used in the conversation. - `live_transcript` string, nullable, required — Live transcript of the conversation. - `post_call_transcript` string, nullable, required — Post-call processed transcript. - `duration_ms` number, double, required — Duration of the conversation in milliseconds. - `audio_url` string, uri, nullable, required — Presigned URL to the conversation audio file. Expires in 1 day. - `started_at` string, date-time, nullable, required — When the conversation started. - `ended_at` string, date-time, nullable, required — When the conversation ended. - `ended_by` 'user' | 'user_canceled' | 'user_validation_failed' | 'assistant' | 'assistant_silence_limit_reached' | 'configuration_endpoint_timed_out' | 'configuration_endpoint_error' | 'configuration_endpoint_invalid_response' | 'error', required — Who or what ended the conversation. - `boosted_keywords` string[], nullable, required — These words, or short phrases, are more accurately recognized by the model. - `pronunciation_dictionary` ConversationPronunciationDictionaryItems[], required — Array of `{ word, pronunciation }` entries. Words must be unique. - `word` string, required - `pronunciation` string, required - `min_words_to_interrupt` integer, required — Minimum number of words required to interrupt the assistant. - `default_language` 'ar' | 'az' | 'bg' | 'bn' | 'cs' | 'da' | 'de' | 'el' | 'en' | 'es' | 'fa' | 'fi' | 'fil' | 'fr' | 'gu' | 'he' | 'hi' | 'hu' | 'id' | 'it' | 'ja' | 'ka' | 'km' | 'kn' | 'ko' | 'lt' | 'lv' | 'ml' | 'mr' | 'ms' | 'ne' | 'nl' | 'no' | 'pa' | 'pl' | 'pt' | 'ro' | 'ru' | 'si' | 'sk' | 'sq' | 'sv' | 'sw' | 'ta' | 'te' | 'th' | 'tr' | 'uk' | 'ur' | 'vi' | 'yue' | 'zh', required — ISO 639-1 language codes supported by the agent - `additional_languages` LanguageCode[], nullable, required — Array of additional ISO 639-1 language codes that the agent should be able to recognize and speak. Should not include `default_language`. When `multilingual_mode` is `"auto"`, a maximum of 2 additional languages is allowed. - `multilingual_mode` 'auto' | 'request' | 'initial', required — If `"auto"`, each user audio is automatically identified for the language to respond in. If `"request"`, user must request to change language (recommended). If `"initial"` the first turn user audio determines the language for the rest of the conversation. - `push_to_talk` boolean, required — Push to talk mode. User must send mute/unmute messages to turn on/off listening to audio. Defaults to false. - `languages` string[] — Array of ISO 639-1 language codes recognized by the model. This field is deprecated. Use `default_language` and `additional_languages` instead. - `generate_no_input_poke_text` boolean, nullable — Whether the no-input poke text was generated by AI. - `no_input_poke_sec` integer, nullable, required — Number of seconds of silence before a poke message is sent. `null` means the poke message is disabled. - `no_input_poke_text` string, nullable, required — The message to send after the specified silence. Relevant only if `no_input_poke_sec` is not `null`. Ignored when generate_no_input_poke_text is true. - `no_input_end_conversation_sec` integer, nullable, required — Seconds of silence before the conversation is ended. - `websocket_timeout_sec` number, double — The WebSocket idle timeout in seconds. - `vad_prebuffer_duration_ms` integer, nullable — Voice activity detection prebuffer duration in milliseconds. `null` when not applicable or unknown (e.g. push-to-talk, or legacy stored conversations). - `vad_min_speech_duration_ms` integer, nullable — Minimum speech duration for voice activity detection in milliseconds. `null` when not applicable or unknown. - `vad_min_silence_duration_ms` integer, nullable — Minimum silence duration for voice activity detection in milliseconds. `null` when not applicable or unknown. - `vad_threshold` number, double, nullable — Voice activity detection threshold. `null` when not applicable or unknown. - `task_results` object, required — Results from conversation evaluations and extractions. - `items` ConversationItem[], required — Array of conversation items (turns). - `id` string, required — The conversation item ID. - `item_idx` integer, required — Index of the item in the conversation. - `role` 'user' | 'assistant', required — Who spoke in this turn. - `live_transcript` string, nullable, required — Live transcript of this turn. `null` when the turn has been redacted. - `post_call_transcript` string, nullable, required — Post-call processed transcript. - `redacted_transcript` string, nullable — The redacted transcript of this turn. `null` when the turn is not redacted. - `duration_ms` number, double, required — Duration of this turn in milliseconds. - `started_at` string, date-time, required — When this turn started. - `voice_id` string — Voice ID used (assistant only). - `audio_speed` number, double — Audio speed used (assistant only). - `system_prompt` string — System prompt used for this assistant turn. - `tool_calls` ConversationItemToolCallsItems[] — Tool calls made by the assistant. - `id` string, required — The tool call ID. - `tool` ConversationItemToolCallsItemsTool, required - `id` string, required — The tool ID. - `name` string, required — The tool name. - `integration` string, nullable — The integration associated with the tool, if any. - `endpoint_method` string, nullable — HTTP method for webhook tool calls. - `endpoint_url` string, nullable — URL for webhook tool calls. - `endpoint_headers` object, nullable — Headers for webhook tool calls. - `endpoint_timeout_ms` number, double, nullable — Timeout in milliseconds for webhook tool calls. - `endpoint_called_at` string, date-time, nullable — When the webhook endpoint was called (null on error). - `query_params` object, nullable — Query parameters for webhook tool calls (null on error or when no params). - `response_status_code` number, double, nullable — HTTP response status code for webhook tool calls (null on error). - `tool_call_output_timeout_ms` number, double, nullable — Timeout in milliseconds for websocket tool calls. - `request_body` union, required — The request body sent to the tool. Can be any JSON-serializable value. - object - unknown[] - … - string - number, double - boolean - `response_body` object, nullable, required — The response body received from the tool. - `timed_out` boolean, nullable, required — Whether the tool call timed out. - `error_message` string, nullable, required — Error message if the tool call failed. - `call_info` ConversationCallInfo, required — Phone call metadata. `null` for non-phone call conversations. - `from_phone_number` string, required — Caller phone number in E.164 format. - `to_phone_number` string, required — Callee phone number in E.164 format. - `twilio_call_sid` string — Twilio Call SID. Only present for user SIP trunking calls. - `analysis` ConversationAnalysis, required - `id` string, required — The ID of the conversation analysis. - `latencies_ms` number[], required — Latencies between turns in milliseconds. - `interruptions_count` integer, required — Number of interruptions in the conversation. - `is_redacted` boolean — Whether PII and PHI have been redacted from the conversation. - `redacted_transcript` string, nullable — The redacted transcript of the conversation. `null` when the conversation is not redacted. - `metadata` object, nullable — Arbitrary metadata associated with the conversation. - `data_retention_policy` union — Controls how long transcripts and audio recordings are retained before deletion. When `zero_data_retention` is `true`, nothing is retained and `transcripts`/`audio_recordings` are omitted. - DataRetentionPolicy0 — Zero data retention mode. No transcripts or audio recordings are retained. - `zero_data_retention` boolean, required — When `true`, no transcripts or audio recordings are retained. - DataRetentionPolicy1 — Standard data retention with configurable deletion windows. - `zero_data_retention` boolean, required — Must be `false` for standard data retention. - `transcripts` DataRetentionPolicyOneOf1Transcripts, required - `delete_after_hours` integer, nullable, required — Number of hours after which transcripts are deleted. Null means transcripts are retained indefinitely. - `audio_recordings` DataRetentionPolicyOneOf1AudioRecordings, required - `delete_after_hours` integer, nullable, required — Number of hours after which audio recordings are deleted. Null means audio recordings are retained indefinitely. - `deletion_info` ConversationDeletionInfo — Information about when transcripts and audio recordings are or were scheduled to be deleted. - `transcripts_deleted_at` string, date-time, nullable, required — When the transcripts were deleted. `null` if not deleted. - `audio_recordings_deleted_at` string, date-time, nullable, required — When the audio recordings were deleted. `null` if not deleted. - `enable_assistant_backchannel` boolean — Whether the assistant produced backchannel responses during the conversation. - `assistant_backchannel_aggressiveness` number, double, nullable — How aggressively the assistant produced backchannel responses during the conversation. - `pagination` ConversationsListResponseConversationsPagination, required - `prev_cursor` string, nullable, required — Cursor to fetch the previous page of conversations (newer). Use this value in the `before` query parameter. `null` if there is no previous page. - `next_cursor` string, nullable, required — Cursor to fetch the next page of conversations (older). Use this value in the `after` query parameter. `null` if there is no next page. - GetConversationByExternalIdResponse - `conversation` Conversation, required - `id` string, required — The conversation ID. - `agent` ConversationAgent, required — The agent associated with the conversation. - `id` string, required — The ID of the agent. - `name` string, required — The name of the agent. - `is_deleted` boolean, required — Whether the agent has been deleted. - `workspace` string, required — The organization/workspace name. - `project` ConversationProject, required — The project associated with the conversation. - `id` string, required — The ID of the project. - `name` string, required — The name of the project. - `external_id` string, nullable, required — External ID for conversation tracking. - `origin` 'web' | 'web-playground' | 'web-demo' | 'direct' | 'livekit-agents-py' | 'livekit-agents-js' | 'sdk-py' | 'sdk-js' | 'inbound' | 'telephony-inbound' | 'outbound' | 'telephony-outbound' | 'replay', required — The origin of the conversation. - `model` string, required — The STS model used. - `generate_welcome_message` boolean, required — Will be `true` if welcome message was automatically generated. - `is_welcome_message_interruptible` boolean, required — When `false`, the welcome message will not be interruptible by the user. - `welcome_message` string, nullable, required — Welcome message played at start. Will be `null` when `generate_welcome_message` is `true`. - `template_variables` object, required — Template variables used in the conversation. - `system_prompt` string, nullable — System prompt used in the conversation. - `input_format` string, required — Audio input format. - `output_format` string, required — Audio output format. - `background_noise_level` number, double, required — Background noise level used in the conversation. - `background_noise` 'office' | 'call-center' | 'coffee-shop', required — The background noise type used in the conversation. - `live_transcript` string, nullable, required — Live transcript of the conversation. - `post_call_transcript` string, nullable, required — Post-call processed transcript. - `duration_ms` number, double, required — Duration of the conversation in milliseconds. - `audio_url` string, uri, nullable, required — Presigned URL to the conversation audio file. Expires in 1 day. - `started_at` string, date-time, nullable, required — When the conversation started. - `ended_at` string, date-time, nullable, required — When the conversation ended. - `ended_by` 'user' | 'user_canceled' | 'user_validation_failed' | 'assistant' | 'assistant_silence_limit_reached' | 'configuration_endpoint_timed_out' | 'configuration_endpoint_error' | 'configuration_endpoint_invalid_response' | 'error', required — Who or what ended the conversation. - `boosted_keywords` string[], nullable, required — These words, or short phrases, are more accurately recognized by the model. - `pronunciation_dictionary` ConversationPronunciationDictionaryItems[], required — Array of `{ word, pronunciation }` entries. Words must be unique. - `word` string, required - `pronunciation` string, required - `min_words_to_interrupt` integer, required — Minimum number of words required to interrupt the assistant. - `default_language` 'ar' | 'az' | 'bg' | 'bn' | 'cs' | 'da' | 'de' | 'el' | 'en' | 'es' | 'fa' | 'fi' | 'fil' | 'fr' | 'gu' | 'he' | 'hi' | 'hu' | 'id' | 'it' | 'ja' | 'ka' | 'km' | 'kn' | 'ko' | 'lt' | 'lv' | 'ml' | 'mr' | 'ms' | 'ne' | 'nl' | 'no' | 'pa' | 'pl' | 'pt' | 'ro' | 'ru' | 'si' | 'sk' | 'sq' | 'sv' | 'sw' | 'ta' | 'te' | 'th' | 'tr' | 'uk' | 'ur' | 'vi' | 'yue' | 'zh', required — ISO 639-1 language codes supported by the agent - `additional_languages` LanguageCode[], nullable, required — Array of additional ISO 639-1 language codes that the agent should be able to recognize and speak. Should not include `default_language`. When `multilingual_mode` is `"auto"`, a maximum of 2 additional languages is allowed. - `multilingual_mode` 'auto' | 'request' | 'initial', required — If `"auto"`, each user audio is automatically identified for the language to respond in. If `"request"`, user must request to change language (recommended). If `"initial"` the first turn user audio determines the language for the rest of the conversation. - `push_to_talk` boolean, required — Push to talk mode. User must send mute/unmute messages to turn on/off listening to audio. Defaults to false. - `languages` string[] — Array of ISO 639-1 language codes recognized by the model. This field is deprecated. Use `default_language` and `additional_languages` instead. - `generate_no_input_poke_text` boolean, nullable — Whether the no-input poke text was generated by AI. - `no_input_poke_sec` integer, nullable, required — Number of seconds of silence before a poke message is sent. `null` means the poke message is disabled. - `no_input_poke_text` string, nullable, required — The message to send after the specified silence. Relevant only if `no_input_poke_sec` is not `null`. Ignored when generate_no_input_poke_text is true. - `no_input_end_conversation_sec` integer, nullable, required — Seconds of silence before the conversation is ended. - `websocket_timeout_sec` number, double — The WebSocket idle timeout in seconds. - `vad_prebuffer_duration_ms` integer, nullable — Voice activity detection prebuffer duration in milliseconds. `null` when not applicable or unknown (e.g. push-to-talk, or legacy stored conversations). - `vad_min_speech_duration_ms` integer, nullable — Minimum speech duration for voice activity detection in milliseconds. `null` when not applicable or unknown. - `vad_min_silence_duration_ms` integer, nullable — Minimum silence duration for voice activity detection in milliseconds. `null` when not applicable or unknown. - `vad_threshold` number, double, nullable — Voice activity detection threshold. `null` when not applicable or unknown. - `task_results` object, required — Results from conversation evaluations and extractions. - `items` ConversationItem[], required — Array of conversation items (turns). - `id` string, required — The conversation item ID. - `item_idx` integer, required — Index of the item in the conversation. - `role` 'user' | 'assistant', required — Who spoke in this turn. - `live_transcript` string, nullable, required — Live transcript of this turn. `null` when the turn has been redacted. - `post_call_transcript` string, nullable, required — Post-call processed transcript. - `redacted_transcript` string, nullable — The redacted transcript of this turn. `null` when the turn is not redacted. - `duration_ms` number, double, required — Duration of this turn in milliseconds. - `started_at` string, date-time, required — When this turn started. - `voice_id` string — Voice ID used (assistant only). - `audio_speed` number, double — Audio speed used (assistant only). - `system_prompt` string — System prompt used for this assistant turn. - `tool_calls` ConversationItemToolCallsItems[] — Tool calls made by the assistant. - `id` string, required — The tool call ID. - `tool` ConversationItemToolCallsItemsTool, required - `id` string, required — The tool ID. - `name` string, required — The tool name. - `integration` string, nullable — The integration associated with the tool, if any. - `endpoint_method` string, nullable — HTTP method for webhook tool calls. - `endpoint_url` string, nullable — URL for webhook tool calls. - `endpoint_headers` object, nullable — Headers for webhook tool calls. - `endpoint_timeout_ms` number, double, nullable — Timeout in milliseconds for webhook tool calls. - `endpoint_called_at` string, date-time, nullable — When the webhook endpoint was called (null on error). - `query_params` object, nullable — Query parameters for webhook tool calls (null on error or when no params). - `response_status_code` number, double, nullable — HTTP response status code for webhook tool calls (null on error). - `tool_call_output_timeout_ms` number, double, nullable — Timeout in milliseconds for websocket tool calls. - `request_body` union, required — The request body sent to the tool. Can be any JSON-serializable value. - object - unknown[] - … - string - number, double - boolean - `response_body` object, nullable, required — The response body received from the tool. - `timed_out` boolean, nullable, required — Whether the tool call timed out. - `error_message` string, nullable, required — Error message if the tool call failed. - `call_info` ConversationCallInfo, required — Phone call metadata. `null` for non-phone call conversations. - `from_phone_number` string, required — Caller phone number in E.164 format. - `to_phone_number` string, required — Callee phone number in E.164 format. - `twilio_call_sid` string — Twilio Call SID. Only present for user SIP trunking calls. - `analysis` ConversationAnalysis, required - `id` string, required — The ID of the conversation analysis. - `latencies_ms` number[], required — Latencies between turns in milliseconds. - `interruptions_count` integer, required — Number of interruptions in the conversation. - `is_redacted` boolean — Whether PII and PHI have been redacted from the conversation. - `redacted_transcript` string, nullable — The redacted transcript of the conversation. `null` when the conversation is not redacted. - `metadata` object, nullable — Arbitrary metadata associated with the conversation. - `data_retention_policy` union — Controls how long transcripts and audio recordings are retained before deletion. When `zero_data_retention` is `true`, nothing is retained and `transcripts`/`audio_recordings` are omitted. - DataRetentionPolicy0 — Zero data retention mode. No transcripts or audio recordings are retained. - `zero_data_retention` boolean, required — When `true`, no transcripts or audio recordings are retained. - DataRetentionPolicy1 — Standard data retention with configurable deletion windows. - `zero_data_retention` boolean, required — Must be `false` for standard data retention. - `transcripts` DataRetentionPolicyOneOf1Transcripts, required - `delete_after_hours` integer, nullable, required — Number of hours after which transcripts are deleted. Null means transcripts are retained indefinitely. - `audio_recordings` DataRetentionPolicyOneOf1AudioRecordings, required - `delete_after_hours` integer, nullable, required — Number of hours after which audio recordings are deleted. Null means audio recordings are retained indefinitely. - `deletion_info` ConversationDeletionInfo — Information about when transcripts and audio recordings are or were scheduled to be deleted. - `transcripts_deleted_at` string, date-time, nullable, required — When the transcripts were deleted. `null` if not deleted. - `audio_recordings_deleted_at` string, date-time, nullable, required — When the audio recordings were deleted. `null` if not deleted. - `enable_assistant_backchannel` boolean — Whether the assistant produced backchannel responses during the conversation. - `assistant_backchannel_aggressiveness` number, double, nullable — How aggressively the assistant produced backchannel responses during the conversation. ## Other responses - `400` — Invalid parameters - `401` — Unauthorized (authentication missing or invalid) - `403` — Forbidden - `404` — Project or conversation not found - `500` — Internal server error --- [API](https://skmtc.net/phonic/apis/api-reference.md) · [All operations](https://skmtc.net/phonic/apis/api-reference/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/phonic/api-reference/revisions/7f8c81a5a990/schema)