From approved shots to a cut you can edit, in every aspect ratio.
Add a voice per line, stage lip-sync, then export the episode or a selection with audio and subtitles. A local API lets your own scripts push jobs in and read status out.
In the app: Video → Dialogue & voice, Project → Export, Tools → Webhook & API
What it does
Every aspect ratio
A finished shot exports at 16:9, 9:16 and 1:1 without prompting the same moment three times.
Dialogue and lip-sync
A voice per line, the take length measured against the shot, and lip-sync as its own stage.
Hand over, not lock in
Export the episode or a selection with audio, subtitles and the codec you choose, then finish it in your own editor.
-
STEP 01
Add the lines
Dialogue comes in with the script sheet; pick a voice for each character.
Video → Dialogue & voice -
STEP 02
Stage lip-sync
Send approved shots that have dialogue to the lip-sync stage; the take length is checked against the shot.
Episode workflow → Lip-sync -
STEP 03
Export
Join the episode or selected shots, with audio and burned-in or separate subtitles.
Project → Export video -
STEP 04
Automate, if you want to
Point your own tool at the local endpoint to queue jobs or read their status.
Tools → Webhook & API
Settings that matter
- Aspect ratios
- 16:9, 9:16 and 1:1 from the same shot.
- Codec and quality
- H.264 or H.265, bitrate and frame rate.
- Subtitles
- Burned in, or as a separate .srt file.
- Webhook
- A URL the app calls when a job finishes, with its status and file path.
Good to know
- Scena Studio is not a video editor: there is no timeline trimming and there are no effects. Export, then edit in the tool you already use.
- Voices and lip-sync run on the services you choose, on your keys.
- The local API listens on your own PC; nothing is exposed to the internet unless you set it up.
24fps Viseme Lip-Sync, 5-Language Dubbing & Dual 16:9 + 9:16 Monetization Export
Finish and multiply the revenue of every episode inside one screen. Lock a permanent voice ID per character, run 24fps phoneme/viseme lip-sync so mouths open and close cleanly on consonants, dub the episode into 5+ languages, verify Trademark/Copyright safety, and export both 16:9 YouTube and 9:16 Meta Reels/TikTok masters simultaneously.
| Production Bottleneck | Standard Web Portal Workflow | How Scena Studio Desktop Solves It |
|---|---|---|
| Dialogue Mouth Accuracy | Flapping cartoon mouths that ignore P/B/M bilabial stops | 24fps phoneme-to-viseme alignment synced to dialogue stems |
| Multilingual Channel Scaling | Manual re-editing required for Spanish, Vietnamese, or Japanese dubs | Automated 5-language TTS dubbing + SRT/VTT & burned-in caption export |
| Simultaneous 16:9 + 9:16 Export | Center-cropping 16:9 cuts off characters speaking on the left/right | Local GPU face-tracked smart pan-and-scan into 9:16 Reels/Shorts/TikTok |
| Pre-Publish TM & Loudness Gate | Audio peaks or accidental visual logos cause platform rejection | -14 LUFS loudness normalization + TM/Copyright Shield verification on export |
Questions
Which voice, speech, translation and lip-sync services are supported?
Voices: ElevenLabs (v3 with emotional tags, Multilingual v2, Flash v2.5), OpenAI TTS (Realtime mini WebSocket, gpt-4o-mini-tts, tts-1-hd), and Azure Neural HD. Lip-sync & video upscale: Kling Lip-sync, sync-lipsync 2 (4K), Hedra Character 3, and Topaz Video Upscale (2×–4×). Speech & translation: Whisper large-v3 (local GPU $0), Deepgram Nova-2/3, Gemini 2.5 Flash, DeepL, Google v3, GPT-5.1, and Claude Sonnet 4.5.
Can I export for Shorts and TikTok?
Yes. 9:16 export is built in and uses the same approved shot.
Where are the API endpoints described?
In the app, under Tools → Webhook & API, with an example for each call.