Option Catalogs

Comprehensive reference of narrator voices, framing positions, and transition types.

This catalog aggregates every preset and configurable value available within Serelius Flow Video for voices, framing, sound effects, and transitions.

1. Narrator Voice Profiles

The tool includes four studio-calibrated narrator voices alongside custom voice prompts:

Voice Profile	Gender & Age	Timbre and Acoustic Characteristics	Delivery Tempo
Deep Documentary	Masculine, 38yo	Deep, warm baritone with close studio acoustics.	Calm and measured (~130 wpm)
Serene Documentary	Feminine, 32yo	Clear, warm contralto with articulate resonance.	Serene and balanced (~135 wpm)
Storyteller	Masculine, 48yo	Rich, resonant timbre suited for narrative depth.	Thoughtful with dramatic pauses
Dynamic Youth	Neutral, 26yo	Crisp, bright, and modern vocal profile.	Modern and upbeat (~145 wpm)
Custom Profile	User-defined	Free-form description of 15 to 400 characters.	Configurable via prompt

For scene characters, you can assign automated voice inference, custom descriptions, or standard vocal archetypes:

AUTO (Default): Automatically infers voice characteristics from the character's physical description and age.
Deep Masculine: 34 years old, grounded baritone delivery.
Authoritative Masculine: 45 years old, firm commanding cadence.
Youthful Masculine: 24 years old, energetic and articulate.
Serene Feminine: 32 years old, calm and articulate tone.
Youthful Feminine: 24 years old, bright and expressive delivery.
Wise Elder: 68 years old, warm and deliberate cadence.

Framing controls establish subject placement in accordance with cinematography principles across different aspect ratios:

Framing Position	16:9 Landscape	9:16 Portrait	Prompt Instruction Behavior
Standard (Free)	Supported	Supported	Unconstrained composition decided by the AI model.
Center	Supported	Supported	Subject anchored dead-center in frame.
Left	Supported	Not Applicable	Rule of thirds: subject on left third with open space on right.
Right	Supported	Not Applicable	Rule of thirds: subject on right third with open space on left.
Top	Not Applicable	Supported	Vertical rule: subject anchored in upper half of frame.
Bottom	Not Applicable	Supported	Vertical rule: subject anchored in lower half of frame.

Optical transitions are applied by local code during video render without calling Flow or spending credits:

Continuous Stitch (Default): Micro-zoom of 2–2.5% combined with a 12–14% subtle darkening edge effect over a 0.28s window.
Soft Edges: Gentle darkening reaching up to 45% opacity across a 0.22s boundary window.
Cinematic Fade: Classic cinematic fade reaching 85% opacity across a 0.30s window.
Kinetic Push-In: Dynamic continuous forward scale (1.0x to 1.06x) into the cut over 0.38s.
Hard Cut: Clean, immediate frame cut with no boundary transformation.

Sound design and line timing are governed by dedicated production tiers:

SFX Intensity: Moderate (balanced ambient texture and foley), Intense (heightened impact foley), Subtle (quiet acoustic air), or Disabled.
Speech Pacing: Standard (12 to 18 words per 8s scene), Moderate (18 to 20 words per 8s scene), or Fast (20 to 22 words per 8s scene).

The application provides independent controls for interface localization and generated content:

Context	Supported Languages	Functional Scope
User Interface	English, Brazilian Portuguese, Spanish	Buttons, form labels, errors, and system warnings.
Video Production	Brazilian Portuguese (pt-BR), US English (en-US), Neutral Spanish (es)	Dictates audio synthesis, lip-sync, and subtitle files.

Nuxfire Production Kit

Get 100% full source code ownership, no proprietary wrappers, with architecture ready for millions of requests on Cloudflare.

On this page