Align Shots to Audio

Build with Align Shots to Audio.

Re-computes each scene start_time and duration from whisper word_timestamps so shots stay in sync with whatever voiceover is actually playing.

Read the Align Shots to Audio docs

Best for

Re-computes each scene start_time and duration from whisper word_timestamps so shots stay in sync with whatever voiceover is actually playing. Use the playground to set up a single step, then open a workflow when you want to connect more tools.

Inputs explained

Scenes (JSON) (optional)

Array of scene definitions with narration text. Can come from an upstream JSON source or from this node's Scenes JSON config field. Type: json.

Word Timestamps (required)

Array of {word, start, end} timestamps from a Whisper STT node. Required. without this, alignment falls back to a linear estimate. Type: json.

Hook Duration (sec) (optional)

Fixed offset for any pre-made hook scene with baked audio. Non-hook scenes are offset by this amount so the voiceover plays after the hook video ends. Type: number. Minimum: 0. Maximum: 60. Default: 0.

Fuzzy Match Window (optional)

How far forward (in words) to search for each scene's first narration word. Higher = more forgiving when transcription differs from script. Type: number. Minimum: 1. Maximum: 100. Default: 20.

Scenes JSON (fallback) (optional)

Paste scene definitions JSON here if not wired via the scenes port. Parsed as the fallback scenes array. Type: text.

Tips before you run

Start with the default settings and change one input at a time. Keep the result you like on your board so the next step can use it.

If you add a reference file, use a link the workflow can read. Check the inputs and credit estimate on the board before starting a run.

Common questions