Text search | ElevenLabs Documentation

Search through conversation transcript messages by full-text and fuzzy search

Headers

xi-api-keystringRequired

Query parameters

text_querystringRequired

The search query text for full-text and fuzzy matching

agent_idstring or nullOptional

The id of the agent you're taking the action on.

call_successfulenum or nullOptional

The result of the success evaluation

Allowed values:

call_start_before_unixinteger or nullOptional

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

call_start_after_unixinteger or nullOptional

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

call_duration_min_secsinteger or nullOptional

Minimum call duration in seconds.

call_duration_max_secsinteger or nullOptional

Maximum call duration in seconds.

rating_maxinteger or nullOptional1-5

Maximum overall rating (1-5).

rating_mininteger or nullOptional1-5

Minimum overall rating (1-5).

has_feedback_commentboolean or nullOptional

Filter conversations with user feedback comments.

user_idstring or nullOptional

Filter conversations by the user ID who initiated them.

evaluation_paramslist of strings or nullOptional

Evaluation filters. Repeat param. Format: criteria_id:result. Example: eval=value_framing:success

data_collection_paramslist of strings or nullOptional

Data collection filters. Repeat param. Format: id:op:value where op is one of eq|neq|gt|gte|lt|lte|in|exists|missing. For in, pipe-delimit values.

tool_nameslist of strings or nullOptional

Filter conversations by tool names used during the call.

tool_names_successfullist of strings or nullOptional

Filter conversations by tool names that had successful calls.

tool_names_erroredlist of strings or nullOptional

Filter conversations by tool names that had errored calls.

main_languageslist of strings or nullOptional

Filter conversations by detected main language (language code).

page_sizeintegerOptional1-50Defaults to 20

Number of results per page. Max 50.

summary_modeenumOptionalDefaults to exclude

Whether to include transcript summaries in the response.

Allowed values:

conversation_initiation_sourceenum or nullOptionalDefaults to unknown

Enum representing the possible sources for conversation initiation.

branch_idstring or nullOptional

Filter conversations by branch ID.

sort_byenumOptional

Sort order for search results. ‘search_score’ sorts by search score, ‘created_at’ sorts by conversation start time.

Allowed values:

cursorstring or nullOptional

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

Response

Successful Response

resultslist of objects

has_moreboolean

Whether there are more results available

metaobject

next_cursorstring or null

Cursor for the next page of results

Errors

422

Unprocessable Entity Error

1	curl -G https://api.elevenlabs.io/v1/convai/conversations/messages/text-search \
2	-H "xi-api-key: xi-api-key" \
3	-H "Content-Type: application/json" \
4	--data-urlencode "text_query=refund policy" \
5	-d agent_id=21m00Tcm4TlvDq8ikWAM \
6	-d call_successful=success \
7	-d call_start_before_unix=1700000000 \
8	-d call_start_after_unix=1690000000 \
9	-d call_duration_min_secs=60 \
10	-d call_duration_max_secs=1800 \
11	-d rating_max=5 \
12	-d rating_min=3 \
13	-d has_feedback_comment=true \
14	-d user_id=user_12345 \
15	--data-urlencode evaluation_params=value_framing:success \
16	--data-urlencode evaluation_params=tone:failure \
17	--data-urlencode data_collection_params=region:eq:us-west \
18	--data-urlencode data_collection_params=device:in:mobile\|desktop \
19	-d tool_names=crm_integration \
20	-d tool_names=call_recorder \
21	-d tool_names_successful=crm_integration \
22	-d tool_names_errored=call_recorder \
23	-d main_languages=en \
24	-d main_languages=es \
25	-d page_size=20 \
26	-d summary_mode=include \
27	-d conversation_initiation_source=react_sdk \
28	-d branch_id=branch_789 \
29	-d sort_by=search_score \
30	-d cursor=eyJwYWdlIjoxfQ

1	{
2	"results": [
3	{
4	"conversation_id": "conv_987654321",
5	"agent_id": "21m00Tcm4TlvDq8ikWAM",
6	"transcript_index": 5,
7	"chunk_text": "I understand your concern about the refund policy. Let me explain how it works in detail.",
8	"score": 0.95,
9	"conversation_start_time_unix_secs": 1698765432,
10	"agent_name": "Jane Doe"
11	}
12	],
13	"has_more": false,
14	"meta": {
15	"total": 1,
16	"page": 1,
17	"page_size": 1
18	},
19	"next_cursor": "eyJwYWdlIjoyfQ=="
20	}