Open-source AI podcast clipper. Generate vertical clips with face tracking and burned-in captions. CLI, MCP server, web app.
Python ai-toolsauto-captionscaptionscliffmpegmcpmcp-serveropusclip-alternativepodcast-clipspodcastsshortform-videovertical-videowhisper
fix: suppress Remotion/FFmpeg terminal noise, add swap speaker + custom feedback
Nika Siradzea2cada1e84c0
diff --git a/backend/cli.py b/backend/cli.pyindex e6510a9..83e96f8 100644--- a/backend/cli.py+++ b/backend/cli.py@@ -563,6 +563,7 @@ def cmd_process(args):_rq.Choice("Make longer (extend 5s)", value="longer"),_rq.Choice("Start earlier (5s)", value="earlier"),_rq.Choice("Start later (3s)", value="later"),+ _rq.Choice("Swap speaker (camera on wrong person)", value="swap"),_rq.Choice("Tell me what to change", value="custom"),_rq.Choice("Render the rest without asking", value="skip_review"),],@@ -577,6 +578,25 @@ def cmd_process(args):_skip_review = Truebreak+ if _raction == "swap":+ # Swap speaker labels in the words for this clip's time range+ # so the camera follows the other person+ clip_speakers = sorted(set(+ w.get("speaker") for w in words+ if w.get("speaker") and w["start"] >= clip["start_second"] and w["end"] <= clip["end_second"]+ ))+ if len(clip_speakers) >= 2:+ swap_map = {clip_speakers[0]: clip_speakers[1], clip_speakers[1]: clip_speakers[0]}+ for w in words:+ if w["start"] >= clip["start_second"] and w["end"] <= clip["end_second"]:+ sp = w.get("speaker")+ if sp in swap_map:+ w["speaker"] = swap_map[sp]+ print(f" Swapped speakers: {clip_speakers[0]} ↔ {clip_speakers[1]}")+ else:+ print(f" Only one speaker detected in this clip")+ continue+if _raction == "custom":_feedback = _rq.text("What should I change?",@@ -633,8 +653,26 @@ def cmd_process(args):config["caption_style"] = sprint(f" Changing to {s} style")break+ elif any(w in fb for w in ["wrong person", "swap", "other speaker", "other face", "wrong face", "wrong speaker"]):+ _raction = "swap"+ # Will hit the swap handler on next iteration+ clip_speakers = sorted(set(+ w.get("speaker") for w in words+ if w.get("speaker") and w["start"] >= clip["start_second"] and w["end"] <= clip["end_second"]+ ))+ if len(clip_speakers) >= 2:+ swap_map = {clip_speakers[0]: clip_speakers[1], clip_speakers[1]: clip_speakers[0]}+ for w in words:+ if w["start"] >= clip["start_second"] and w["end"] <= clip["end_second"]:+ sp = w.get("speaker")+ if sp in swap_map:+ w["speaker"] = swap_map[sp]+ print(f" Swapped speakers: {clip_speakers[0]} ↔ {clip_speakers[1]}")+ else:+ print(f" Only one speaker in this clip")+ continueelse:- print(f" Couldn't parse that. Try: 'shorter', 'longer 10', 'start 3s earlier', 'hormozi style'")+ print(f" Couldn't parse that. Try: 'shorter', 'longer 10', 'start 3s earlier', 'hormozi style', 'wrong person'")continueelse:continuediff --git a/backend/services/clip_generator.py b/backend/services/clip_generator.pyindex a242faf..acba080 100644--- a/backend/services/clip_generator.py+++ b/backend/services/clip_generator.py@@ -278,11 +278,13 @@ def _render_with_remotion(if logo_path and os.path.exists(logo_path):cmd.extend(["--logo", os.path.abspath(logo_path)])- # Stream stderr to terminal for progress+ # Redirect stderr to devnull to suppress Chrome/FFmpeg noise+ # (avoids buffer deadlock and terminal spam)+ _devnull = open(os.devnull, 'w')result = subprocess.run(cmd,stdout=subprocess.PIPE,- stderr=None,+ stderr=_devnull,text=True,timeout=600,cwd=project_root,diff --git a/remotion/render.mjs b/remotion/render.mjsindex a51cd18..e136bfa 100644--- a/remotion/render.mjs+++ b/remotion/render.mjs@@ -243,10 +243,10 @@ async function main() {const { execSync } = await import("child_process");process.stderr.write(" compositing...\n");execSync(- `ffmpeg -y -i "${path.resolve(opts.video)}" -i "${captionOverlay}" ` ++ `ffmpeg -y -hide_banner -loglevel warning -i "${path.resolve(opts.video)}" -i "${captionOverlay}" ` +`-filter_complex "[0:v][1:v]overlay=0:0:shortest=1" ` +`-c:v libx264 -crf 18 -preset fast -map 0:a -c:a copy "${opts.output}"`,- { stdio: ["pipe", "pipe", "inherit"], timeout: 300000 }+ { stdio: ["pipe", "pipe", "pipe"], timeout: 300000 });// Clean up overlay