Voiceover & clips · optional AI narration
Clips are cut from your real source footage (podcast / webinar). Voiceover is the optional AI narration that overlays the clip — one tap per clip to draft, regenerate, or leave unvoiced.
Voiceover is additive over your source clip — captions and audio output are separate slices further down the pipeline.
Generate
One short AI voiceover script per clip, sized to the clip's runtime and shaped by the tone you pick. Saved per clip — regenerate with a different angle any time, or leave the clip unvoiced if the speaker's audio carries it.
Step 1 · Add a clip
Headline, what the speaker covers, and the clip's length. The AI voiceover is optional — opt in per clip after the clip is on file.
Loading saved clips…
How it works here
Capture the moment your editor cut: a short headline, what the speaker covers, and the clip length. Persist once — voiceover is added on top later.
Pick a tone and tap Generate on the clip you want overlaid. The AI drafts a short narration sized to the clip's runtime — additive, not a rewrite of the speaker's audio.
Each clip keeps its own voiceover lane. Regenerate with a different tone, swap the narration for a new take, or leave the clip without a voiceover entirely.
Next step
See your delivered clips and decide per-clip whether they want an AI voiceover overlay. Captions and audio output come next — this one is just the voiceover layer.
Submit the first clip you want on file.
Voiceover runs in 10–25 seconds when you opt in. Each clip keeps its own story — nothing is shared or merged across clips.
Open the clip intake