Get TikTok video
tiktok_video_getFetches a single TikTok video by URL and returns its details, with options to include the transcript or download media links for analysis or archiving.
Instructions
Get a single TikTok video by URL. Requires url. Author is identity-only (no follower counts) — use tiktok_profile_get for metrics. Credits: 1 (+downloadMedia add-on).
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"url": "<url>",
"context": "<context>",
"llm_model": "<llm_model>"
},
"name": "tiktok_video_get"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Required. Link to the video or photo post. | |
| trim | No | When true, returns a smaller response with fewer fields. | |
| region | No | Optional ISO 3166-1 country code used to route the request when needed. | |
| context | Yes | Describe the user's underlying goal in one sentence, not the tool you are calling. | |
| llm_model | Yes | The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (for example "claude-opus-4-8" or "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" and do not guess. | |
| downloadMedia | No | When true, downloads the media and returns links to the files in `downloads` when available. Adds 10 credits when media is found (11 total including the base lookup); when no media is returned the base lookup credit still applies. | |
| getTranscript | No | When true, includes the video transcript (WEBVTT) in `transcript` when one is available. | |
| conversation_id | No | Echo the conversation_id from the server's previous response. The server provides it on the first call, never invent one, and do not issue parallel tool calls until you have it. |