The logo goes on every clip, the outro plays whole, and a guest has a name

backend/cli.py

@@ -576,6 +576,15 @@ def cmd_process(args):
         config["format"] = args.format
     if getattr(args, "profile", None):
         config["profile"] = args.profile
+    if getattr(args, "name_card", None):
+        config["name_card"] = {
+            "title": args.name_card,
+            "subtitle": getattr(args, "name_card_sub", None),
+            "seconds": getattr(args, "name_card_seconds", None),
+            "accent": getattr(args, "name_card_accent", None),
+        }
+    if getattr(args, "bookend_fade", None) is not None:
+        config["bookend_fade"] = args.bookend_fade
     if getattr(args, "thumbnails", None) is not None:
         config["generate_thumbnails"] = args.thumbnails
     if args.top:
@@ -1056,6 +1065,8 @@ def _transcribe_progress(pct, msg):
                         logo_path=config.get("logo_path") or None,
                         outro_path=config.get("outro_path") or None,
                         intro_path=config.get("intro_path") or None,
+                        name_card=config.get("name_card"),
+                        bookend_fade=config.get("bookend_fade", 0.0),
                         keep_segments=clip.get("segments"),
                         face_map=face_map,
                         allow_ass_fallback=config.get("allow_ass_fallback", False),
@@ -1274,6 +1285,8 @@ def _transcribe_progress(pct, msg):
                                 face_map=face_map,
                                 allow_ass_fallback=config.get("allow_ass_fallback", False),
                                 use_ass_captions=config.get("use_ass_captions", False),
+                                name_card=config.get("name_card"),
+                                bookend_fade=config.get("bookend_fade", 0.0),
                             )
                             results[-1] = result
                             print(f"         ✓ Re-rendered: {result['file_size_mb']}MB")
@@ -3990,6 +4003,16 @@ def main():
     proc.add_argument("--profile", choices=["podcast", "party", "action"], help="Detection profile: podcast (transcript-first, default), party/action (laughter/energy highlights)")
     proc.add_argument("--logo", help="Logo image (asset name or path)")
     proc.add_argument("--outro", help="Outro video (asset name or path)")
+    proc.add_argument("--name-card", dest="name_card",
+                      help="Lower third naming the speaker, shown for the first seconds")
+    proc.add_argument("--name-card-sub", dest="name_card_sub",
+                      help="Second line of the lower third")
+    proc.add_argument("--name-card-seconds", dest="name_card_seconds", type=float,
+                      help="How long the lower third holds (default 3)")
+    proc.add_argument("--name-card-accent", dest="name_card_accent",
+                      help="Underline colour on the lower third")
+    proc.add_argument("--bookend-fade", dest="bookend_fade", type=float, default=None,
+                      help="Seconds of crossfade into an intro or outro (default 0, a cut)")
     proc.add_argument("--no-outro", action="store_true", help="Do not append an outro (default for highlight profiles)")
     proc.add_argument("--intro", help="Intro video (asset name or path)")
     proc.add_argument("--time-adjust", type=float, help="Timestamp offset in seconds")

backend/config/caption_styles.py

@@ -74,7 +74,6 @@ def _detect_font() -> str:
         "words_per_chunk": 3,                  # Show 3 words at a time
         "uppercase": True,
         "gradient_overlay": False,
-        "logo_support": False,
     },
     "karaoke": {
         "description": "Full sentence visible, words highlight progressively",
@@ -92,7 +91,6 @@ def _detect_font() -> str:
         "words_per_chunk": 5,
         "uppercase": False,
         "gradient_overlay": False,
-        "logo_support": False,
     },
     "subtle": {
         "description": "Clean white text at bottom with shadow, professional look",
@@ -110,7 +108,6 @@ def _detect_font() -> str:
         "words_per_chunk": 5,
         "uppercase": False,
         "gradient_overlay": False,
-        "logo_support": False,
     },
     "branded": {
         "description": "Large bold text, 5-7 words wrapping across 2 lines, dark rounded pill on active word. Clean, no gradient.",
@@ -134,7 +131,6 @@ def _detect_font() -> str:
         "uppercase": False,                     # Mixed case, natural capitalization
         "gradient_overlay": False,              # No gradient — clean direct-on-video
         "gradient_opacity": 0.0,
-        "logo_support": True,                   # Logo top-left
         "logo_margin_x": 40,                    # Logo X offset from left
         "logo_margin_y": 60,                    # Logo Y offset from top
         "logo_height": 100,                     # Logo height in px

backend/services/clip_generator.py

@@ -465,6 +465,7 @@ def _render_with_remotion(
     output_path: str,
     time_offset: float = 0.0,
     logo_path: Optional[str] = None,
+    name_card: Optional[dict] = None,
     keep_caption_overlay: bool = False,
     caption_position: str = "auto",
     caption_font_scale: int = 100,
@@ -596,6 +597,14 @@ def _render_with_remotion(
         ]
         if logo_path and os.path.exists(logo_path):
             cmd.extend(["--logo", os.path.abspath(logo_path)])
+        if name_card and name_card.get("title"):
+            cmd.extend(["--name-card", str(name_card["title"])])
+            if name_card.get("subtitle"):
+                cmd.extend(["--name-card-sub", str(name_card["subtitle"])])
+            if name_card.get("seconds"):
+                cmd.extend(["--name-card-seconds", str(name_card["seconds"])])
+            if name_card.get("accent"):
+                cmd.extend(["--name-card-accent", str(name_card["accent"])])
         if keep_caption_overlay:
             cmd.append("--keep-overlay")
 
@@ -661,6 +670,8 @@ def generate_clip(
     logo_path: Optional[str] = None,
     outro_path: Optional[str] = None,
     intro_path: Optional[str] = None,
+    name_card: Optional[dict] = None,
+    bookend_fade: float = 0.0,
     clean_fillers: bool = True,
     keep_segments: list[dict] = None,
     trim_opening: Optional[bool] = None,
@@ -886,6 +897,21 @@ def generate_clip(
             else:
                 fit_to_frame(segment_path, cropped_path, target_dims=spec.dims)
 
+        # Only Remotion draws the name card, and it is reached only when there
+        # are words to caption. Refusing beats returning a clip that quietly
+        # lacks the overlay that was asked for.
+        if name_card and name_card.get("title"):
+            if use_ass_captions or allow_ass_fallback:
+                raise ValueError(
+                    "A name card can only be drawn by the Remotion renderer. "
+                    "Drop --name-card, or drop --fast and --allow-ass-fallback."
+                )
+            if not transcript_words:
+                raise ValueError(
+                    "A name card needs the caption renderer, which only runs when "
+                    "there is a transcript. Drop --name-card for an uncaptioned render."
+                )
+
         # Step 3: Render captions (Remotion-first; ASS fallback optional)
         if transcript_words:
             if progress_callback:
@@ -918,7 +944,8 @@ def generate_clip(
                         caption_style=caption_style,
                         output_path=captioned_path,
                         time_offset=caption_time_offset,
-                        logo_path=logo_path if (style_config.get("logo_support", False) and logo_path) else None,
+                        logo_path=logo_path or None,
+                        name_card=name_card,
                         keep_caption_overlay=keep_caption_overlay,
                         caption_position=caption_position,
                         caption_font_scale=caption_font_scale,
@@ -945,7 +972,7 @@ def generate_clip(
 
                     use_gradient = style_config.get("gradient_overlay", False)
                     gradient_opacity = style_config.get("gradient_opacity", 0.6)
-                    use_logo = style_config.get("logo_support", False) and logo_path
+                    use_logo = bool(logo_path)
 
                     burn_captions(
                         input_path=cropped_path,
@@ -985,15 +1012,17 @@ def generate_clip(
             intro_scaled = os.path.join(work_dir, "intro_scaled.mp4")
             scale_to_frame(intro_path, intro_scaled, cw, ch)
             with_intro_path = os.path.join(work_dir, "with_intro.mp4")
-            concat_outro(intro_scaled, final_video_path, with_intro_path)
+            concat_outro(intro_scaled, final_video_path, with_intro_path,
+                         crossfade_duration=bookend_fade)
             final_video_path = with_intro_path
 
         if outro_path and os.path.exists(outro_path):
             if progress_callback:
                 progress_callback(85, f"Adding outro ({total_steps}/{total_steps})")
 
             with_outro_path = os.path.join(work_dir, "with_outro.mp4")
-            concat_outro(final_video_path, outro_path, with_outro_path)
+            concat_outro(final_video_path, outro_path, with_outro_path,
+                         crossfade_duration=bookend_fade)
             final_video_path = with_outro_path
 
         # Step 6: Move to output

remotion/render.mjs

@@ -150,12 +150,24 @@ async function main() {
   const durationSec = videoDuration || (lastWord ? lastWord.end + 0.5 : 30);
   const durationInFrames = Math.ceil(durationSec * fps);
 
+  // Who is speaking, for the lower third. Sent whole so the composition takes
+  // one prop rather than six loose ones.
+  const nameCard = opts["name-card"]
+    ? {
+        title: opts["name-card"],
+        subtitle: opts["name-card-sub"] || undefined,
+        seconds: opts["name-card-seconds"] ? parseFloat(opts["name-card-seconds"]) : undefined,
+        accent: opts["name-card-accent"] || undefined,
+      }
+    : null;
+
   const inputProps = {
     videoSrc,
     words,
     styleName,
     logoSrc,
     faceY,
+    nameCard,
     durationInFrames,
     fps,
     captionPosition: opts["caption-position"] || "auto",

remotion/src/CaptionedClip.tsx

@@ -1,9 +1,12 @@
 import React from "react";
-import { AbsoluteFill } from "remotion";
+import { AbsoluteFill, useVideoConfig } from "remotion";
 import { HormoziCaptions } from "./components/HormoziCaptions";
 import { KaraokeCaptions } from "./components/KaraokeCaptions";
 import { SubtleCaptions } from "./components/SubtleCaptions";
 import { BrandedCaptions } from "./components/BrandedCaptions";
+import { NameCard } from "./components/NameCard";
+import type { NameCardProps } from "./components/NameCard";
+import { Watermark } from "./components/Watermark";
 import type { Word, CaptionStyle, CaptionPosition, LogoPosition } from "./types";
 
 export interface CaptionedClipProps {
@@ -12,6 +15,8 @@ export interface CaptionedClipProps {
   style: CaptionStyle;
   logoSrc?: string;
   faceY?: number | null;
+  /** Who is speaking, shown for the first few seconds. */
+  nameCard?: NameCardProps | null;
   captionPosition?: CaptionPosition;
   logoPosition?: LogoPosition;
   singleLine?: boolean;
@@ -22,10 +27,12 @@ export const CaptionedClip: React.FC<CaptionedClipProps> = ({
   style,
   logoSrc,
   faceY,
+  nameCard,
   captionPosition = "auto",
   logoPosition = "top-left",
   singleLine = false,
 }) => {
+  const { height } = useVideoConfig();
   const CaptionComponent = {
     hormozi: HormoziCaptions,
     karaoke: KaraokeCaptions,
@@ -35,12 +42,14 @@ export const CaptionedClip: React.FC<CaptionedClipProps> = ({
 
   return (
     <AbsoluteFill style={{ backgroundColor: "transparent" }}>
+      <Watermark src={logoSrc} height={height} position={logoPosition} />
       {style.name === "branded" ? (
         <BrandedCaptions words={words} style={style} logoSrc={logoSrc} faceY={faceY}
           captionPosition={captionPosition} logoPosition={logoPosition} singleLine={singleLine} />
       ) : (
         <CaptionComponent words={words} style={style} singleLine={singleLine} />
       )}
+      {nameCard?.title && <NameCard {...nameCard} />}
     </AbsoluteFill>
   );
 };

remotion/src/Root.tsx

@@ -46,6 +46,14 @@ const inputProps = getInputProps() as {
   bookendPlatforms?: string[];
   bookendBg?: string;
   bookendAccent?: string;
+  nameCard?: {
+    title: string;
+    subtitle?: string;
+    seconds?: number;
+    background?: string;
+    color?: string;
+    accent?: string;
+  } | null;
 };
 
 export const RemotionRoot: React.FC = () => {
@@ -80,6 +88,7 @@ export const RemotionRoot: React.FC = () => {
           style,
           logoSrc: inputProps.logoSrc,
           faceY: inputProps.faceY ?? null,
+          nameCard: inputProps.nameCard ?? null,
           captionPosition,
           logoPosition: inputProps.logoPosition || "top-left",
           singleLine: inputProps.singleLine === true,

remotion/src/components/BrandedCaptions.tsx

@@ -3,16 +3,17 @@ import {
   useCurrentFrame,
   useVideoConfig,
   spring,
-  Img,
-  staticFile,
 } from "remotion";
 import type { Word, CaptionStyle, CaptionPosition, LogoPosition } from "../types";
 import { captionScale } from "../types";
 import { buildChunks, activeChunkAt, splitCaptionLines } from "../chunks";
+import { LOGO_CAPTION_GAP, LOGO_HEIGHT, LOGO_INSET } from "./Watermark";
 
 interface Props {
   words: Word[];
   style: CaptionStyle;
+  // The logo is drawn by Watermark now, but the caption margin still has to
+  // know it is there.
   logoSrc?: string;
   faceY?: number | null; // normalized 0-1 (0=top, 1=bottom)
   captionPosition?: CaptionPosition;
@@ -22,12 +23,6 @@ interface Props {
 
 const MAX_CHARS_PER_CHUNK = 18;
 
-// Unscaled logo box, shared by the logo style and the caption-margin guard so
-// the two cannot drift apart.
-const LOGO_INSET = 180;
-const LOGO_HEIGHT = 126;
-const LOGO_CAPTION_GAP = 24;
-
 /**
  * Active pill rendered as an absolutely positioned background behind the word.
  * The word itself is always rendered as plain inline text so layout doesn't shift.
@@ -161,24 +156,6 @@ export const BrandedCaptions: React.FC<Props> = ({
 
   return (
     <>
-      {logoSrc && (
-        <Img
-          src={logoSrc.startsWith("http") ? logoSrc : staticFile(logoSrc)}
-          style={{
-            position: "absolute",
-            ...(logoPosition.startsWith("top-") ? { top: LOGO_INSET * s } : { bottom: LOGO_INSET * s }),
-            ...(logoPosition.endsWith("-left")
-              ? { left: 108 * s }
-              : logoPosition.endsWith("-right")
-                ? { right: 108 * s }
-                : { left: "50%", transform: "translateX(-50%)" }),
-            width: 255 * s,
-            height: LOGO_HEIGHT * s,
-            objectFit: "contain",
-          }}
-        />
-      )}
-
       {activeChunk && (() => {
         const [line1, line2] = splitCaptionLines(activeChunk.words, 2, singleLine);