Silence beat in an avatar video plan: 2 seconds with no words
Sume Avatar 1.0 multi-scene plans can include a silence beat. How to place a 2-second pause in a product reveal and what it adds at $0.258 a second.
A multi-scene Sume Avatar 1.0 plan can include a silence beat, so the avatar pauses while the product sits on screen. A 2-second pause costs the same as 2 seconds of speech: $0.388 on standard, $0.516 on plus and $1.16 on max with a product image.
The video_inputs plan and its scene types are described in the Avatar Video docs (read 2026-10-06). The duration estimate counts words at 2.8 a second, so a silence beat is counted by its seconds, not by words.
Where a pause helps
A pause helps at the reveal. Say the product name, stop for two seconds, then give the benefit. A voice that never stops makes every line the same weight.
| Tier | Per second | 2 seconds |
|---|---|---|
| standard | $0.194 | $0.39 |
| plus (default) | $0.258 | $0.52 |
| max | $0.58 | $1.16 |
Check it in the preview
Multi-scene previews return one still per scene, and later stills continue from the first. Look at the still for the silent scene: if the avatar is shown mid-word, change the scene description.
A worked example
Take a 15-second plan with three scenes: a 5-second hook, a 2-second silent reveal and an 8-second benefit and call to action. On plus with a product image the full plan is 15 seconds at $0.258, or $3.87. The silent scene is $0.52 of that.
The reveal scene should show the product clearly. Send the product image, preview the stills and check that the product is visible in the second scene before you pay for the video.
Before you render
Write the silent scene's description so that the avatar's expression suits a pause: a small smile or a steady look, not an open mouth. Then check the preview still for that scene.
If you plan to add music over the silent beat in a timeline, make sure the soundtrack is quiet enough there and ducks under the voice elsewhere. The timeline's soundtrack options include a duck level for exactly that.
Tradeoffs
Silence is paid time, and a 15-second ad with a 2-second pause leaves 13 seconds for the pitch. Use it once, at the moment that matters.
Keep the pause short. Two seconds feels deliberate on a phone; four feels like a mistake. If the preview suggests the product is already clear at one second, shorten it and save the seconds for the offer.
Sources
Related posts
More in Sume Avatar 1.0
- Swap two people in one clip: H3 Max Recast takes 1 to 4 photos
To change two people in one video, send one reference photo for each. Sume's H3 Max Recast takes 1 to 4 person photos and a 5 to 30 second source video.
- Tavus Griffin-Lite is invite-only: what can you build today?
Griffin-Lite is a closed Tavus preview. Until you get in, Sume ships rendered avatar clips, lip sync and motion control for talking-head video.
- 12 six-second UGC hooks: Standard, Plus or Max rate math
Twelve 6-second avatar hooks come to 72 seconds: about $13.25 on Standard, $17.64 on Plus and $39.60 on Max at Sume's listed per-second rates, before rounding.
- Wedding save-the-date: a 20-second avatar clip, cost by tier
A 20-second save-the-date spoken by an AI avatar costs about $3.68 on Standard, $4.90 on Plus or $11.00 on Max at Sume's listed per-second rates.
Written by Sume