Skip to main content
Glama
nmbrthirteen

podcli

by nmbrthirteen
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

create_clip

Export a single podcast clip as a finished vertical short with burned-in captions and normalized audio; pass clip_number to auto-load session settings.

Instructions

STEP 3 — Export a single clip as a finished vertical short (1080x1920, 9:16).

EASIEST: just pass clip_number (e.g. 3) — everything else auto-loads from session state. Output: H.264 MP4 with burned-in captions, normalized audio (-14 LUFS).

For batch export, use batch_create_clips instead. Caption styles: branded (professional), hormozi (bold/yellow), karaoke (progressive highlight), subtle (minimal). Crop modes: speaker (speaker-aware), face (face tracking), center (fixed center crop). Set keep_caption_overlay=true to retain a ProRes alpha overlay for DaVinci Resolve (export_to_davinci_resolve).

Input Schema

NameRequiredDescriptionDefault
hookNoOpening hook for this render. Auto-loaded from clip_number if omitted; null renders without one.
titleNoClip titleclip
formatNoOutput aspect ratio (vertical=9:16, horizontal=16:9, square=1:1)vertical
logo_pathNoPath or registered asset name for PNG logo. Shown in top-left (branded style).
end_secondNoClip end time in seconds. Auto-loaded from clip_number if omitted.
outro_pathNoPath to an outro video to append at the end of the clip
video_pathNoPath to the original podcast video. Auto-loaded from session state if clip_number is provided.
clip_numberNoExport a suggested clip by its number (from suggest_clips). Auto-fills video_path, start/end times, title, and transcript_words from session state.
start_secondNoClip start time in seconds. Auto-loaded from clip_number if omitted.
caption_styleNoCaption stylehormozi
clean_fillersNoRemove filler words (um, uh, hmm) from captions and compress long silences. Defaults to the studio's clean filler words setting (on unless the user turned it off).
crop_strategyNoCropping strategyspeaker
transcript_wordsNoWord-level timestamps. Auto-loaded from session state if omitted.
allow_ass_fallbackNoAllow ASS caption fallback if Remotion rendering fails (default: false)
write_clean_variantNoAlso render a second file with the same audio, loudness, and intro/outro but no burned captions. Returns clean_output_path.
keep_caption_overlayNoKeep ProRes 4444 alpha caption overlay beside the render (for DaVinci Resolve export). Returns caption_overlay_path and cropped_source_path.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv2.8.0
    • addedInput schema / properties / hook
      Added value: +{
+  "anyOf": [
+    {
+      "description": "Opening hook: a 1-15s passage from inside the clip, played before the clip. It must be a line actually spoken inside the clip's range (or its segments), never invented text.",
+      "properties": {
+        "end": {
+          "description": "Hook end in seconds, on the source clock",
+          "type": "number"
+        },
+        "mode": {
+          "description": "repeat: the passage plays first and again in place. move: it plays first and is cut from its place.",
+          "enum": [
+            "repeat",
+            "move"
+          ],
+          "type": "string"
+        },
+        "start": {
+          "description": "Hook start in seconds, on the source clock",
+          "type": "number"
+        }
+      },
+      "required": [
+        "start",
+        "end",
+        "mode"
+      ],
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "Opening hook for this render. Auto-loaded from clip_number if omitted; null renders without one."
+}
    • addedInput schema / properties / write_clean_variant
      Added value: +{
+  "default": false,
+  "description": "Also render a second file with the same audio, loudness, and intro/outro but no burned captions. Returns clean_output_path.",
+  "type": "boolean"
+}
  2. Changed2 schema fields changedv2.7.2
    • removedInput schema / additionalProperties
      Removed value: -false
    • removedInput schema / properties / transcript_words / items / additionalProperties
      Removed value: -false
  3. Changed1 schema field changedv2.5.0
    • addedInput schema / properties / clean_fillers
      Added value: +{
+  "description": "Remove filler words (um, uh, hmm) from captions and compress long silences. Defaults to the studio's clean filler words setting (on unless the user turned it off).",
+  "type": "boolean"
+}
  4. Changed1 schema field changedv2.2.1
    • addedInput schema / properties / format
      Added value: +{
+  "default": "vertical",
+  "description": "Output aspect ratio (vertical=9:16, horizontal=16:9, square=1:1)",
+  "enum": [
+    "vertical",
+    "horizontal",
+    "square"
+  ],
+  "type": "string"
+}
  5. First observedv2.0.0

TDQS

A4.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden, and it does disclose meaningful behavior: the produced artifact type (H.264 MP4 with burned-in captions, normalized to -14 LUFS), and the side effects of keep_caption_overlay and write_clean_variant producing extra files. It stops short of stating where renders are written, overwrite behavior, or expected runtime, which for a 16-parameter writer is still a gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the step number, the easy-path invocation, and the output artifact before the option catalogs, and every sentence carries information. It is slightly list-heavy in the style/crop enumerations, but nothing is padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 16-parameter, zero-required, no-output-schema render tool, the description covers the invocation shortcut, the artifact, the batch alternative, and the two flags that emit extra return paths. Missing pieces are output location, failure/fallback behavior beyond allow_ass_fallback, and expected duration.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds real semantics the schema lacks: it explains each caption style (branded=professional, hormozi=bold/yellow, karaoke=progressive highlight, subtle=minimal) and each crop mode (speaker=speaker-aware, face=face tracking, center=fixed center), and clarifies the clip_number auto-load shortcut. It does not elaborate on hook, transcript_words, or the ffmpeg-ish fallback flag.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first line states a specific verb (export/render), a specific resource (a single clip) and a precise output spec (1080x1920, 9:16 vertical short). It also names the sibling it is not (batch_create_clips), so an agent can disambiguate without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit recommended invocation path ('EASIEST: just pass clip_number — everything else auto-loads from session state') and an explicit exclusion rule ('For batch export, use batch_create_clips instead'). It also names export_to_davinci_resolve as the consumer of the keep_caption_overlay output, which routes the agent correctly.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools