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: pipe prompt via stdin to Claude CLI (was broken with shell expansion)
Nika Siradze160ae34f4aac
diff --git a/backend/services/claude_suggest.py b/backend/services/claude_suggest.pyindex 129f68e..9bfcc89 100644--- a/backend/services/claude_suggest.py+++ b/backend/services/claude_suggest.py@@ -136,10 +136,10 @@ def suggest_with_claude(progress_callback(20, "Asking Claude to analyze transcript...")try:- # Call claude with --print (non-interactive, outputs result directly)+ # Pipe prompt via stdin — avoids shell escaping and arg size limits# Run from the podcli project dir so it picks up CLAUDE.md + knowledge baseresult = subprocess.run(- [claude_path, "--print", "-p", f"$(cat {prompt_file})"],+ f'cat "{prompt_file}" | "{claude_path}" --print -p -',capture_output=True,text=True,cwd=project_dir,