feat: expand Studio podcast workflow

README.md

@@ -2,6 +2,20 @@
   <img src="public/podcli-badge.png" height="72" alt="podcli" />
 </p>
 
+> [!NOTE]
+> **This is a maintained product fork of [nmbrthirteen/podcli](https://github.com/nmbrthirteen/podcli).** It preserves Podcli's local-first engine and CLI while extending Studio for a simpler podcast-production workflow. Upstream changes are reviewed and merged regularly to limit drift.
+
+### What this fork adds
+
+- One-command local Studio launch with `podclip`
+- Local silence detection, review, and removal before editing
+- Full-episode YouTube workflow with a large 16:9 preview and export
+- Live caption and logo previews with placement and font-size controls
+- Format-aware captions, including single-line captions for YouTube
+- Readable full-episode and per-clip transcripts with one-click copying
+
+Launch the Studio from any directory with `podclip`.
+
 <p align="center">
   <strong>Open-source AI podcast clipper.</strong><br/>
   Turn a long episode into short clips with face tracking and burned-in captions. Drive it from the CLI, a web studio, or your coding agent.

backend/main.py

@@ -169,6 +169,9 @@ def handle_create_clip(task_id: str, params: dict):
         start_second=params["start_second"],
         end_second=params["end_second"],
         caption_style=params.get("caption_style", "hormozi"),
+        caption_position=params.get("caption_position", "auto"),
+        caption_font_scale=params.get("caption_font_scale", 100),
+        logo_position=params.get("logo_position", "top-left"),
         crop_strategy=params.get("crop_strategy", "face"),
         format=params.get("format", "vertical"),
         crop_keyframes=params.get("crop_keyframes"),
@@ -223,6 +226,9 @@ def render_one(i: int, clip: dict) -> dict:
             start_second=clip["start_second"],
             end_second=clip["end_second"],
             caption_style=clip.get("caption_style", "hormozi"),
+            caption_position=clip.get("caption_position", params.get("caption_position", "auto")),
+            caption_font_scale=clip.get("caption_font_scale", params.get("caption_font_scale", 100)),
+            logo_position=clip.get("logo_position", params.get("logo_position", "top-left")),
             crop_strategy=clip.get("crop_strategy", "face"),
             format=clip.get("format", params.get("format", "vertical")),
             transcript_words=params.get("transcript_words", []),
@@ -876,6 +882,46 @@ def handle_manage_config(task_id: str, params: dict):
         emit_result(task_id, "error", error=str(e))
 
 
+def handle_analyze_silence(task_id: str, params: dict):
+    """Analyze a full episode locally and return a conservative cut plan."""
+    from services.silence_removal import analyze_silence
+
+    try:
+        result = analyze_silence(
+            video_path=params.get("video_path", ""),
+            transcript_words=params.get("transcript_words") or [],
+            threshold=float(params.get("threshold", 0.5)),
+            min_silence_seconds=float(params.get("min_silence_seconds", 0.65)),
+            padding_seconds=float(params.get("padding_seconds", 0.12)),
+            progress_callback=lambda pct, msg: emit_progress(
+                task_id, "silence_analysis", pct, msg
+            ),
+        )
+        emit_result(task_id, "success", data=result)
+    except (FileNotFoundError, RuntimeError, ValueError) as e:
+        emit_result(task_id, "error", error=str(e))
+
+
+def handle_render_silence_removed(task_id: str, params: dict):
+    """Render the approved local cut plan and remap transcript timestamps."""
+    from config.paths import paths
+    from services.silence_removal import render_silence_removed
+
+    try:
+        result = render_silence_removed(
+            video_path=params.get("video_path", ""),
+            keep_segments=params.get("keep_segments") or [],
+            transcript=params.get("transcript") or {},
+            output_dir=params.get("output_dir") or paths["output"],
+            progress_callback=lambda pct, msg: emit_progress(
+                task_id, "silence_render", pct, msg
+            ),
+        )
+        emit_result(task_id, "success", data=result)
+    except (FileNotFoundError, RuntimeError, ValueError) as e:
+        emit_result(task_id, "error", error=str(e))
+
+
 def handle_run_integration_tool(task_id: str, params: dict):
     from services.integrations import IntegrationRegistry, IntegrationsManager
 
@@ -932,6 +978,8 @@ def handle_run_integration_tool(task_id: str, params: dict):
     "manage_integrations": handle_manage_integrations,
     "run_integration_tool": handle_run_integration_tool,
     "manage_config": handle_manage_config,
+    "analyze_silence": handle_analyze_silence,
+    "render_silence_removed": handle_render_silence_removed,
 }
 
 

backend/services/caption_renderer.py

@@ -93,6 +93,8 @@ def render_captions(
     caption_style: str,
     output_path: str,
     time_offset: float = 0.0,
+    caption_position: str = "auto",
+    caption_font_scale: int = 100,
 ) -> str:
     """
     Generate an ASS subtitle file from word-level timestamps.
@@ -113,7 +115,12 @@ def render_captions(
             f.write(generate_ass_header(get_style(caption_style)))
         return output_path
 
-    style = get_style(caption_style)
+    style = dict(get_style(caption_style))
+    scale = max(60, min(160, int(caption_font_scale))) / 100
+    style["font_size"] = round(style["font_size"] * scale)
+    position_margins = {"upper": 760, "center": 480, "lower": 220}
+    if caption_position in position_margins:
+        style["margin_v"] = position_margins[caption_position]
 
     if caption_style == "hormozi":
         content = _render_hormozi(words, style, time_offset)

backend/services/captions_burn.py

@@ -64,6 +64,7 @@ def burn_captions(
     logo_height: int = 80,
     logo_margin_x: int = 30,
     logo_margin_y: int = 40,
+    logo_position: str = "top-left",
 ) -> str:
     """Burn ASS subtitles into the video.
 
@@ -99,9 +100,13 @@ def burn_captions(
         logo_idx = input_idx
         input_idx += 1
         filter_parts.append(f"[{logo_idx}:v]scale=-1:{logo_height}[logo]")
-        filter_parts.append(
-            f"[{current_label}][logo]overlay={logo_margin_x}:{logo_margin_y}[withlogo]"
+        logo_x = (
+            str(logo_margin_x) if logo_position.endswith("-left")
+            else f"main_w-overlay_w-{logo_margin_x}" if logo_position.endswith("-right")
+            else "(main_w-overlay_w)/2"
         )
+        logo_y = str(logo_margin_y) if logo_position.startswith("top-") else f"main_h-overlay_h-{logo_margin_y}"
+        filter_parts.append(f"[{current_label}][logo]overlay={logo_x}:{logo_y}[withlogo]")
         current_label = "withlogo"
 
     # Burn ASS subtitles

backend/services/clip_generator.py

@@ -465,6 +465,9 @@ def _render_with_remotion(
     time_offset: float = 0.0,
     logo_path: Optional[str] = None,
     keep_caption_overlay: bool = False,
+    caption_position: str = "auto",
+    caption_font_scale: int = 100,
+    logo_position: str = "top-left",
 ) -> tuple[bool, Optional[str]]:
     """
     Render captions using Remotion. Returns (success, optional_prores_overlay_path).
@@ -586,6 +589,9 @@ def _render_with_remotion(
             "--words", os.path.abspath(words_file),
             "--style", caption_style,
             "--output", os.path.abspath(output_path),
+            "--caption-position", caption_position,
+            "--caption-font-scale", str(caption_font_scale),
+            "--logo-position", logo_position,
         ]
         if logo_path and os.path.exists(logo_path):
             cmd.extend(["--logo", os.path.abspath(logo_path)])
@@ -641,6 +647,9 @@ def generate_clip(
     start_second: float,
     end_second: float,
     caption_style: str = "hormozi",
+    caption_position: str = "auto",
+    caption_font_scale: int = 100,
+    logo_position: str = "top-left",
     crop_strategy: str = "face",
     format: str = "vertical",
     crop_keyframes: list[dict] = None,
@@ -908,6 +917,9 @@ def generate_clip(
                         time_offset=caption_time_offset,
                         logo_path=logo_path if (style_config.get("logo_support", False) and logo_path) else None,
                         keep_caption_overlay=keep_caption_overlay,
+                        caption_position=caption_position,
+                        caption_font_scale=caption_font_scale,
+                        logo_position=logo_position,
                     )
 
                 if not remotion_ok and not allow_ass_fallback:
@@ -924,6 +936,8 @@ def generate_clip(
                         caption_style=caption_style,
                         output_path=ass_path,
                         time_offset=caption_time_offset,
+                        caption_position=caption_position,
+                        caption_font_scale=caption_font_scale,
                     )
 
                     use_gradient = style_config.get("gradient_overlay", False)
@@ -940,6 +954,7 @@ def generate_clip(
                         logo_height=style_config.get("logo_height", 80),
                         logo_margin_x=style_config.get("logo_margin_x", 30),
                         logo_margin_y=style_config.get("logo_margin_y", 40),
+                        logo_position=logo_position,
                     )
             else:
                 captioned_path = cropped_path