Appearance
Reels, Shorts and TikTok
A short vertical video is five pieces: the shot, the hook, the voice, the captions and the track. Cinara makes all five; you cut them together in the editor you already post from.
This recipe makes one 10-second clip. Short video is a volume game, so the tips at the end show how to make ten.
1. Make the shot
Open Video.
- Keep From a description selected, or choose From an image to animate a still you already have.
- Describe the shot: the subject, the light and the camera move. "Steam curling off a cup of coffee on a windowsill at sunrise, slow push-in, shallow focus."
- In the settings row, set Shape to 9:16 and Length to 5 s or 10 s.
- Press the send button. The cost is on the button before you press it.
Scene, the default look, is the most affordable and includes sound. A 5-second Scene clip is 320 credits.
A frame you control
If the first frame matters — a product, a face, a logo placement — make it in Images first at 9:16, then choose Animate on it. The video starts exactly there.
2. Write and read the hook
Open Speech.
- Write the hook as you'd say it, then the rest of the voiceover. Keep a 10-second clip to about 25 words.
- Pick a voice. For social, try Confetti (big energy), Breeze (relaxed) or Rise (motivating) — or your own cloned voice.
- Generate it, then try the same line in two more voices. At 1 credit a character, three reads of a 120-character hook cost 360 credits. Keep the one that lands.
3. Time the captions
Open Alignment.
- Add the voiceover you kept.
- Paste the exact words you wrote.
- Download SRT or VTT subtitles. Every word carries its own timing, so captions land on the word instead of near it.
Alignment is 100 credits a minute of audio, so a 10-second read costs 17.
4. Add the track
Open Music, choose Instrumental, describe the energy — "upbeat lo-fi beat, warm keys, 95 bpm, no vocals" — and set the length a little longer than the clip. A Standard instrumental is 300 credits.
For transitions, open Sound Effects and ask for "a quick cinematic whoosh" or "a soft riser", several takes at once.
5. Put it together
Download the shot, the voiceover, the subtitles and the track, and assemble them in your editor. Burn the captions in, or upload the SRT with the post where the platform allows it.
What it costs
| Piece | Credits |
|---|---|
| 5-second shot (Scene, 9:16) | 320 |
| Three reads of the hook (120 characters each) | 360 |
| Captions for a 10-second read | 17 |
| Music bed (Standard instrumental) | 300 |
| About | 1,000 |
Make ten, not one
- Same hook, different voices. Speech is fast and cheap; test four voices on every hook.
- Same shot, different looks. Run one description through Scene and Feature and keep the better one.
- Same clip, another language. Send the finished clip to Dubbing — 2,000 credits a minute for each language — or translate the hook and read it again in Speech.
- A presenter. For a face-to-camera hook, use Talking Avatars with a photo you have permission to use.