Get TikTok video transcript
tiktok_video_transcript_getFetch the spoken transcript of a TikTok video using its URL. Convert video speech into readable text for quoting or analysis.
Instructions
Get the spoken transcript for a TikTok video by URL. Requires url.
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_transcript_get"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Required. Link to the TikTok video whose transcript should be returned. | |
| context | Yes | Describe the user's underlying goal in one sentence, not the tool you are calling. | |
| language | No | Optional two-letter language code to request a transcript in a specific language when available. | |
| 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. | |
| useAiFallback | No | When true and the video has no caption track, transcribes the audio with AI (videos up to 2 minutes). Adds 10 credits only when AI produced the transcript (11 total); caption reads and empty results stay at 1 credit. | |
| 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. | |
| allowLongTranscription | No | Requires useAiFallback=true. Lifts the 2-minute AI limit. An AI transcript then costs 10 credits per started minute of video, short clips included (plus the base 1); caption reads and empty results stay at 1 credit. Long videos can take a minute or more. |