Endpoint Playground
Returns a frequency-ranked word cloud for US television coverage. `channel` is required and picks what is counted: `transcript`, `caption`, `concept`, `onscreen_text` or `visual`; `station` is also required. Match with the same channel options (with `exclude_` counterparts) and limit by `show`, `day_of_week`, `timespan` or `from` and `to`. Each word has a `label` and `count`.
14 Oct 2026: 262 words; 2 fields had a value in every checked item.
Sample value profiles: count: 0.44 to 100, median 0.44; label: “Trump” and 261 other values.
curl 'https://api.crawlora.net/api/v1/gdelt/tv-wordcloud?channel=caption&station=CNN' \
-H "x-api-key: $CRAWLORA_API_KEY"| Parameter | Type | Required | Prefilled value | Description |
|---|---|---|---|---|
| channel | string | Yes | caption | Required. Which match channel to build a word cloud from. |
| transcript | array | No | Search machine-generated speech-to-text transcripts (GDELT's asr: operator). Repeatable; multiple values are OR'd together. Short phrases only (GDELT caps each at 5 words). | |
| caption | array | No | Search human-provided closed captioning (GDELT's cap: operator). Repeatable; multiple values are OR'd together. | |
| concept | array | No | Search Google Knowledge Graph concepts extracted from captioning, by MID code (GDELT's capnlp: operator). Repeatable; multiple values are OR'd together. | |
| onscreen_text | array | No | Search OCR'd onscreen text/chyrons (GDELT's ocr: operator). Repeatable; multiple values are OR'd together. Short phrases only (GDELT caps each at 5 words). | |
| visual | array | No | Search visual object/activity labels from computer vision (GDELT's visual: operator). Repeatable; multiple values are OR'd together. | |
| exclude_transcript | array | No | Exclude clips whose speech-to-text transcript matches this value (GDELT's -asr: operator). Repeatable; every value must be absent. | |
| exclude_caption | array | No | Exclude clips whose closed captioning matches this value (GDELT's -cap: operator). Repeatable; every value must be absent. | |
| exclude_concept | array | No | Exclude clips whose extracted concepts match this MID code (GDELT's -capnlp: operator). Repeatable; every value must be absent. | |
| exclude_onscreen_text | array | No | Exclude clips whose OCR'd onscreen text matches this value (GDELT's -ocr: operator). Repeatable; every value must be absent. | |
| exclude_visual | array | No | Exclude clips whose visual labels match this value (GDELT's -visual: operator). Repeatable; every value must be absent. | |
| station | string | Yes | CNN | Required. Station to search. |
| show | string | No | Limit to an exact show name. | |
| day_of_week | string | No | Limit to a day of week, 0 (Sunday) through 7 (Saturday), PST. | |
| timespan | string | No | Relative time window ending now, e.g. 1h, 7d, 3m, 1y. Cannot be combined with from/to. GDELT's TV archive starts July 6, 2010. | |
| from | string | No | Start of an absolute time window. Accepts YYYY-MM-DD, RFC3339, or GDELT's raw YYYYMMDDHHMMSS. Cannot be combined with timespan. | |
| to | string | No | End of an absolute time window. Same formats as from. |
{
"code": 200,
"msg": "OK",
"data": {
"query": "cap:\"trump\" station:CNN",
"channel": "caption",
"source_url": "https://api.gdeltproject.org/api/v2/tvai/tvai?format=json&mode=wordcloudcap&query=cap%3A%22trump%22+station%3ACNN",
"fetched_at": "2026-08-20T10:00:00Z",
"words": [
{
"label": "Trump",
"count": 100
},
{
"label": "Donald",
"count": 22.1239
},
{
"label": "President",
"count": 2.2124
}
]
}
}The sample response, schema and code snippets below work without an account. Sending a live request needs an API key.