--- title: 'Podcast MCP Video Workflow Example - OpenClip' description: 'A worked example of clipping a podcast episode through MCP: the real tool calls from submit_video to render_clip and what comes back at each step.' canonical: 'https://openclip.app/examples/podcast-mcp-video-workflow-example' markdown: 'https://openclip.app/examples/podcast-mcp-video-workflow-example.md' --- Part of OpenClip's video editing MCP resource hub Explore setup guides, assistant workflows, examples, and prompt templates for controlling OpenClip from MCP-compatible AI assistants. [Open MCP hub](/mcp)Worked Example # Podcast MCP Video Workflow Example Here is a complete assistant-led session on real material: a 60-minute interview episode goes in as a URL, and four captioned vertical clips come out, with every tool call shown. Podcasts are the ideal MCP source because the value is buried in conversation, exactly what moment detection is built to find. ## Workflow 1 ### Submit the episode by URL You paste the episode link and the brief ("4 clips for Reels, audience is indie hackers, skip the ad reads"). The assistant calls submit\_video with the URL; for hosts that are not directly supported per list\_supported\_providers, it asks for the raw video URL or uses create\_upload for a local file. Resubmitting the same URL within 24 hours reuses the existing run. 2 ### OpenClip processes while the assistant polls For an hour of conversation, expect several minutes of processing: transcription, viral-moment detection, and speaker tracking for the video feed. The assistant polls get\_video\_status every 10 to 15 seconds and reports transitions (downloading, processing, completed) so you can go do something else. 3 ### Review the detected moments list\_clips returns the scored moments: for an interview episode that typically means the contrarian take, the origin story beat, the tactical breakdown, and the quotable exchange. Titles, hooks, and quotes are generated from the audio and marked as untrusted content, so the assistant presents them for judgment. You pick four. 4 ### Verify a quote before rendering For the moment you are unsure about, the assistant pulls get\_transcript with a window around the timestamp at word level, so you can check the guest's exact phrasing (and that the answer is not missing its caveat) before spending a render on it. 5 ### Render with the show's caption style The assistant calls render\_clip for each approved moment with your preset (confirmed once via list\_caption\_presets), polls get\_render\_status, and returns four clip URLs: vertical crops that follow the active speaker, word-level captions in your style. 6 ### Repeat next week in one message With the show's settings saved as a processing agent (create\_agent: tracker, captions, logo), next episode is "same as last week" plus a URL. get\_usage shows the credit spend in minutes per episode so you can budget a season. ## Key Metrics One 60-minute episode Source 5 distinct tools Tool calls Brief + approvals Your active time ## Features ### Interview-tuned detection Moment detection surfaces the exchanges that work as standalone clips: strong claims, stories, and answers with a beginning and an end. ### Speaker-aware framing Vertical crops follow whoever is talking, so two-person episodes do not become a static wide shot with unreadable faces. ### Quote verification built in get\_transcript at word level lets you check exact phrasing before rendering, which matters when a guest's nuance is the story. ### Sound-off ready Word-level captions in a consistent preset carry the conversation for the majority of viewers who scroll on mute. ### Weekly cadence, one message A saved processing agent turns episode clipping into a recurring one-liner instead of a recurring project. ### Season-level budgeting Credits are minutes of processing, so a weekly one-hour show maps cleanly onto plan allowances (150 minutes on Starter, 300 on Pro). ## Frequently Asked Questions ### Does this work for audio-only podcasts? Yes; submit the audio and OpenClip transcribes and detects moments the same way. Clips render with captions carrying the content; video episodes additionally get speaker-tracked framing. ### How many clips should I expect per episode? list\_clips typically returns a healthy shortlist of scored moments for an hour of conversation. Rendering four or five keeps quality high; the approval gate means weak moments cost you nothing. ### What if my podcast host's link is not supported? Check list\_supported\_providers through your assistant. When the host wraps media in a player page, use the direct file URL or upload the episode with create\_upload and complete\_upload. ### How is this different from the webinar example? Podcasts are conversation-first: the wins are quotable exchanges and speaker-tracked framing. Webinars add slides, demos, and Q&A segments, which change what you clip and how you find it; see the webinar workflow example. ## Clip this week's episode from your assistant Connect OpenClip, paste the episode URL, and approve your four best moments before the next recording. [Get Started Free](https://openclip.app/register) ## Related Pages ### Examples [Webinar MCP Clip Workflow Example](/examples/webinar-mcp-clip-workflow-example) ### Guides [How to Automate Video Editing with MCP](/guides/automate-video-editing-with-mcp) [Claude Video Editing Workflow: A Worked MCP Example](/guides/claude-video-editing-mcp-workflow) ### Templates [MCP Video Clipping Prompt Template (Copy-Paste)](/templates/mcp-video-clipping-prompt-template) ### Use Cases [Control Video Editing from AI Assistants](/use-cases/control-video-editing-from-ai-assistants)