get_transcript
Retrieve the full transcript of any YouTube video to analyze content without watching. Supports chunking, plain text, and sponsor filtering.
Instructions
Retrieves the full transcript of a specified YouTube video. This tool is useful for understanding video content without watching it, or for extracting textual information from videos. FORMATTING GUIDANCE (optional - user instructions override): When creating summaries, consider using: Key Points with Timestamps: Use [MM:SS] or [HH:MM:SS] inline references. Structure: Break into logical sections. Context: Include video title and channel. Example: 'The speaker explains TypeScript generics [05:30] and shows practical examples [08:15].' This formatting is optional - always follow any specific user instructions instead.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| videoUrl | Yes | The full URL of the YouTube video from which to retrieve the transcript. This is the standard URL you would use to watch the video in a browser (e.g., 'https://www.youtube.com/watch?v=dQw4w9WgXcQ'). | |
| chunkSize | No | Optional: The maximum number of characters for each transcript chunk. If provided, the transcript will be split into chunks of this size. Useful for processing very long transcripts in smaller, manageable parts. | |
| plainText | No | Optional: If true, returns the full transcript as a single plain text string without timestamp data. This uses less context than the default timestamped format and is better for summarization. If you later need timestamps, subsequent calls are cached. | |
| skipSponsor | No | Optional: If true, removes sponsor/ad segments from the transcript using the SponsorBlock API. Fetches sponsor timestamps and filters out transcript text that falls within sponsored sections. | |
| chunkBySilence | No | Optional: If true, the transcript will be chunked based on periods of silence in the audio. This can help in segmenting the transcript into more natural conversational or thematic breaks. | |
| silenceThreshold | No | Optional: When chunkBySilence is true, this specifies the minimum duration of silence (in milliseconds) to consider as a chunk break. A higher value means longer pauses are required to create a new chunk. |