text_search_conversation_messages_route
Read-onlyIdempotent
Search across ElevenLabs conversation transcripts to find messages matching keywords. Filter results by agent, user, rating, language, topic, or call outcome.
Instructions
Text Search Conversation Messages
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| cursor | No | Used for fetching next page. Cursor is returned in the response. | |
| sort_by | No | Sort order for search results. 'search_score' sorts by search score, 'created_at' sorts by conversation start time. | |
| user_id | No | Filter conversations by the user ID who initiated them. | |
| agent_id | No | Agent id (agent_…) or speech engine external id (seng_), resolved to the same underlying resource. | |
| branch_id | No | Filter conversations by branch ID. | |
| page_size | No | Number of results per page. Max 50. | |
| text_only | No | ||
| topic_ids | No | Filter conversations by topic IDs assigned during topic discovery. | |
| rating_max | No | Maximum overall rating (1-5). | |
| rating_min | No | Minimum overall rating (1-5). | |
| text_query | Yes | The search query text for full-text and fuzzy matching | |
| tool_names | No | Filter conversations by tool names used during the call. | |
| version_id | No | Filter conversations by version ID. | |
| summary_mode | No | Whether to include transcript summaries in the response. | |
| main_languages | No | Filter conversations by detected main language (language code). | |
| call_successful | No | The result of the success evaluation | |
| exclude_statuses | No | Exclude conversations with the given statuses. Useful for hiding in-progress / processing conversations from list views. | |
| evaluation_params | No | Evaluation filters. Repeat param. Format: criteria_id:result. Example: eval=value_framing:success | |
| visited_agent_ids | No | Filter conversations where any of these agents participated. Can not exceed 50 values. | |
| tool_names_errored | No | Filter conversations by tool names that had errored calls. | |
| termination_reasons | No | Filter conversations by their stored termination_reason (metadata.termination_reason). Repeat param to match any of several. | |
| has_feedback_comment | No | Filter conversations with user feedback comments. | |
| call_start_after_unix | No | Unix timestamp (in seconds) to filter conversations after to this start date. | |
| tool_names_successful | No | Filter conversations by tool names that had successful calls. | |
| call_duration_max_secs | No | Maximum call duration in seconds. | |
| call_duration_min_secs | No | Minimum call duration in seconds. | |
| call_start_before_unix | No | Unix timestamp (in seconds) to filter conversations up to this start date. | |
| data_collection_params | No | Data collection filters. Repeat param. Format: id:op:value where op is one of eq|gt|gte|lt|lte|missing. | |
| dynamic_variable_params | No | Dynamic variable filters. Repeat param. Format: name:op:value where op is one of eq|gt|gte|lt|lte. Comparison operators require a numeric value. Names containing ':' cannot be expressed. | |
| triggered_procedure_ids | No | Filter conversations where any of these procedures were triggered. Can not exceed 50 values. | |
| visited_agent_branch_ids | No | Filter conversations where any of these agent branches participated. Can not exceed 50 values. | |
| conversation_product_type | No | Restrict results to a single conversation product surface. | |
| include_invalid_tool_calls | No | Also match tool calls that never ran. | |
| conversation_initiation_source | No |