List conversations

GET

/v1/convai/conversations

GET

/v1/convai/conversations

curl -G https://api.elevenlabs.io/v1/convai/conversations \
     -d agent_id=agent_id \
     -d branch_id=branch_id \
     -d call_duration_max_secs=1 \
     -d call_duration_min_secs=1 \
     -d call_start_after_unix=1 \
     -d call_start_before_unix=1 \
     -d call_successful=success \
     -d conversation_initiation_source=unknown \
     -d conversation_product_type=agents \
     -d cursor=cursor \
     -d custom_guardrail_names=custom_guardrail_names \
     -d data_collection_ids=data_collection_ids \
     -d data_collection_params=data_collection_params \
     -d dynamic_variable_params=dynamic_variable_params \
     -d evaluation_criteria_ids=evaluation_criteria_ids \
     -d evaluation_params=evaluation_params \
     -d exclude_statuses=initiated \
     -d guardrail_types=custom \
     -d has_feedback_comment=true \
     -d include_invalid_tool_calls=true \
     -d main_languages=main_languages \
     -d page_size=1 \
     -d parent_conversation_id=parent_conversation_id \
     -d rating_max=1 \
     -d rating_min=1 \
     -d search=search \
     -d sort_direction=asc \
     -d summary_mode=exclude \
     -d tag_ids=tag_ids \
     -d termination_reasons=termination_reasons \
     -d text_only=true \
     -d tool_names=tool_names \
     -d tool_names_errored=tool_names_errored \
     -d tool_names_successful=tool_names_successful \
     -d topic_ids=topic_ids \
     -d triggered_procedure_ids=triggered_procedure_ids \
     -d user_id=user_id \
     -d version_id=version_id \
     -d visited_agent_branch_ids=visited_agent_branch_ids \
     -d visited_agent_ids=visited_agent_ids \
     -d workflow_node_entered_id=workflow_node_entered_id

{
  "conversations": [
    {
      "agent_id": "agent_id",
      "conversation_id": "conversation_id",
      "start_time_unix_secs": 1,
      "call_duration_secs": 1,
      "message_count": 1,
      "status": "initiated",
      "call_successful": "success",
      "branch_id": "branch_id",
      "version_id": "version_id",
      "agent_name": "agent_name",
      "termination_reason": "termination_reason",
      "call_success_score": 1.1,
      "transcript_summary": "transcript_summary",
      "call_summary_title": "call_summary_title",
      "main_language": "main_language",
      "conversation_initiation_source": "unknown",
      "tool_names": [
        "tool_names"
      ],
      "direction": "inbound",
      "rating": 1.1,
      "sentiment_analysis": {
        "overall_label": "positive",
        "overall_sentiment_score": 1.1,
        "overall_frustration_score": 1.1,
        "min_user_sentiment_score": 1.1,
        "max_user_frustration_score": 1.1,
        "num_scored_user_turns": 1
      },
      "data_collection_results": {
        "key": "value"
      },
      "tag_ids": [
        "tag_ids"
      ]
    }
  ],
  "has_more": true,
  "next_cursor": "next_cursor"
}

Get all conversations of agents that user owns. With option to restrict to a specific agent.

Paramètres de requête

cursorstringOptionnel

Used for fetching next page. Cursor is returned in the response.

agent_idstringOptionnel

Agent id (agent_…) or speech engine external id (seng_), resolved to the same underlying resource.

visited_agent_idsstringOptionnel

Filter conversations where any of these agents participated. Can not exceed 50 values.

visited_agent_branch_idsstringOptionnel

Filter conversations where any of these agent branches participated. Can not exceed 50 values.

triggered_procedure_idsstringOptionnel

Filter conversations where any of these procedures were triggered. Can not exceed 50 values.

call_successfulenumOptionnel

The result of the success evaluation

Valeurs autorisées:

call_start_before_unixintegerOptionnel

Unix timestamp (in seconds) to filter conversations up to this start date.

call_start_after_unixintegerOptionnel

Unix timestamp (in seconds) to filter conversations after to this start date.

call_duration_min_secsintegerOptionnel

Minimum call duration in seconds.

call_duration_max_secsintegerOptionnel

Maximum call duration in seconds.

rating_maxintegerOptionnel1-5

Maximum overall rating (1-5).

rating_minintegerOptionnel1-5

Minimum overall rating (1-5).

has_feedback_commentbooleanOptionnel

Filter conversations with user feedback comments.

user_idstringOptionnel

Filter conversations by the user ID who initiated them.

evaluation_paramsstringOptionnel

Evaluation filters. Repeat param. Format: criteria_id:result where result is one of success|failure|unknown. Example: eval=value_framing:success

data_collection_paramsstringOptionnel

Data collection filters. Repeat param. Format: id:op:value where op is one of eq|neq|gt|gte|lt|lte|in. For in, pipe-delimit values. An empty value matches conversations where the field was not collected (id:eq:), and neq with an empty value matches where it was (id:neq:). eq is exact equality. gt|gte|lt|lte require a numeric value.

dynamic_variable_paramsstringOptionnel

Dynamic variable filters. Repeat param. Format: name:op:value where op is one of eq|neq|gt|gte|lt|lte|in. For in, pipe-delimit values. An empty value matches conversations where the variable was not set (name:eq:), and neq with an empty value matches where it was (name:neq:). eq is exact equality. gt|gte|lt|lte require a numeric value. Names containing ’:’ cannot be expressed.

data_collection_idsstringOptionnel

Data collection field IDs to include in each conversation summary. Repeat param. When omitted, data_collection_results is not returned.

evaluation_criteria_idsstringOptionnel

Evaluation criteria IDs to include in each conversation summary. Repeat param. When omitted, evaluation_criteria_results is not returned.

tool_namesstringOptionnel

Filter conversations by tool names used during the call.

tool_names_successfulstringOptionnel

Filter conversations by tool names that had successful calls.

tool_names_erroredstringOptionnel

Filter conversations by tool names that had errored calls.

include_invalid_tool_callsbooleanOptionnelPar défaut false

Also match tool calls that never ran.

main_languagesstringOptionnel

Filter conversations by detected main language (language code).

page_sizeintegerOptionnel1-100Par défaut 30

How many conversations to return at maximum. Can not exceed 100, defaults to 30.

summary_modeenumOptionnelPar défaut exclude

Whether to include transcript summaries in the response.

Valeurs autorisées:

searchstringOptionnelDeprecated

Full-text or fuzzy search over transcript messages

conversation_initiation_sourceenumOptionnelPar défaut unknown

Enum representing the possible sources for conversation initiation.

text_onlybooleanOptionnel

conversation_product_typeenumOptionnel

Restrict results to a single conversation product surface.

Valeurs autorisées:

branch_idstringOptionnel

Filter conversations by branch ID.

version_idstringOptionnel

Filter conversations by version ID.

parent_conversation_idstringOptionnel

Filter conversations by parent conversation ID for subagent conversations.

topic_idsstringOptionnel

Filter conversations by topic IDs assigned during topic discovery.

exclude_statusesenumOptionnel

Exclude conversations with the given statuses. Useful for hiding in-progress / processing conversations from list views.

Valeurs autorisées:

tag_idsstringOptionnel

Filter conversations by conversation tag IDs assigned via the conversation-tags endpoints.

workflow_node_entered_idstringOptionnel

Filter conversations to only those that entered the given node.

termination_reasonsstringOptionnel

Filter conversations by their stored termination_reason (metadata.termination_reason). Repeat param to match any of several.

guardrail_typesenumOptionnel

Filter to conversations where a guardrail of any of these types triggered (metadata.triggered_guardrails.guardrail_type). Repeat param to match any of several.

custom_guardrail_namesstringOptionnel

Filter to conversations where a custom guardrail with any of these names triggered (metadata.triggered_guardrails.guardrail_name). Only custom guardrails carry a name. Repeat param to match any of several.

sort_directionenumOptionnel

The direction to sort conversations by call start time. Defaults to descending (newest first).

Valeurs autorisées:

Réponse

Successful Response

conversationslist of objects

has_moreboolean

next_cursorstringOptionnel

Erreurs

422

Conversations List Request Unprocessable Entity Error

En-têtes

Paramètres de requête

Réponse

Erreurs