For the complete documentation index, see llms.txt. This page is also available as Markdown.

Video to Text

Transcribe the speech in a video without first converting it to a separate audio file. Use it to prepare spoken content for a summary or other text task.

Use this tool

  1. Supply Video URL for a directly downloadable video.

  2. Select Model and enable Include Timestamps if timed segments are needed.

  3. Run the tool.

  4. Review Transcription and, when enabled, Segments against the recording.

Behavior and limits

The tool transcribes the audio track. It does not describe silent visual content. A page address that requires an interactive login is not a downloadable video URL; use an accessible or signed file link.

Inputs

Field
Parameter
Description

Video URL (required)

video_url

URL of the video file to transcribe. Must be reachable without a login — a pre-authenticated or signed download URL works.

Model

model

Transcription model to use.

Include Timestamps

include_timestamps

Include timestamped transcript segments in the output. Default: false.

Outputs

Field
Parameter
Description

Transcription

transcription

The text transcribed from the video's audio track.

Segments

segments

Timestamped transcript segments. Empty unless 'Include Timestamps' is enabled.

Was this helpful?