YouTube Transcript

Fetch a YouTube video transcript as plain text for summarizing, rewriting, or analysis.

Audience

Creators building and publishing workflows.

Overview#

YouTube Transcript asks for a video link in the run modal, fetches captions, and passes transcript text to the next block. If automatic fetch is unavailable, customers can paste a transcript manually as fallback.

Use it for video-to-text products, summaries, study guides, quote extraction, or any workflow that starts from spoken content.

Ports#

Output: Transcript: Plain text or timestamped lines, depending on your format setting. No inputs; this block starts the flow.

Inspector#

Run Modal Question: What customers see when asked for the YouTube link.
Run Modal Description: Optional help under the question, such as examples or guardrails.
Caption Language (optional): ISO code such as en or es; leave blank for auto-detection.
Output Format: Plain text (best for most AI steps) or timestamped lines.
Plain Text Separator: How segments join: spaces, new lines, or paragraph breaks.

Tips#

Plain text output works best when the next block is LLM Chat or similar.
Add a clear description with an example URL format customers recognize.
Set caption language only when you need a specific track; auto usually suffices.
Test with both short clips and long videos to confirm downstream token limits.

Workflow Studio

Was this useful?

Your response helps us improve the documentation.

More blocks

Workflow Input

Ask the customer one clear question and turn their answer into data your workflow can use.

Workflow Form

Collect several run-modal fields in one grouped form, each with a stable key for downstream steps.

Workflow Output

Define what the customer receives when the workflow finishes.

Block reference