Podcast to
content studio

Hand it an episode and it gives you back the viral moments cropped 9:16 with captions burned in, ready to drop into TikTok, YouTube Shorts, or Reels. The whole thing runs from one binary on your laptop, and you can drive it from Claude Code by saying “clip this episode.”

podcli

Runs from one binary on your laptop

Once it's installed, the only thing that needs the internet is the optional AI scoring step (and only if you bring an API key for it).

Whisper transcription

Word-level timestamps and speaker diarization. Cached by file hash, so re-runs are instant.

Face-tracking crop

YuNet face detection plus per-clip mouth-motion speaker tracking. No diarization needed for 2-person split-screen. Scene-cut guard kills jittery pans.

Burned-in captions

4 styles (branded, hormozi, karaoke, subtle), rendered via Remotion. Synced to word timing, filler stripped.

Web UI at :3847

Drop a video, review clips, get a live 9:16 phone preview with optional TikTok wireframe, export. All in-browser.

AI clip suggestion

Claude or Codex scores moments on four dimensions against your knowledge base. Checks the episode database so you don't ship the same clip twice.

MCP server (19 tools)

Add to Claude Code, Claude Desktop, or Codex. Tell it "clip this episode" and it handles the rest.

Hardware encoding

Auto-picks VideoToolbox on Mac, NVENC on NVIDIA, VAAPI on Linux. CPU fallback works too.

Knowledge base

13 markdown files you fill out once. Teach the AI your voice, title formulas, and banned words.

One command, six stages

CLI, Web UI, or AI agent. Same pipeline.

01

Transcribe

Whisper + pyannote for word timestamps and speaker labels

02

Score

Claude or Codex reads the transcript plus your knowledge base and picks clips

03

Export

Batch render 1080×1920 MP4s with captions and −14 LUFS audio

04

Titles & Descriptions

8 options per clip, descriptions with hooks and SEO keywords

05

Thumbnails

Two-line text briefs for podcast (16:9) and shorts (9:16)

06

Publish

Pre-upload checklist, first-24-hours ops, day 3 to 4 optimization

01-03: video engine. 04-06: PodStack slash commands.

Four styles, one flag

Burned in at word-level timing. Filler words stripped.

the key to success is showing up every single day

--caption-style branded

Dark box on the active word. Optional logo. The safe default.

THE KEY TO SUCCESS IS SHOWING UP EVERY DAY

--caption-style hormozi

Bold uppercase with a yellow highlight. For clips that need to hit hard.

the key to success is showing up every single day

--caption-style karaoke

Whole line is visible. Words light up as they're spoken. Works for story clips.

the key to success is showing up every single day

--caption-style subtle

Small clean text at the bottom. Stays out of the way.

Plan before recording. Publish after. PodStack handles both.

Nine slash commands that work in Claude Code, Codex, Cursor, or any AI coding tool that reads markdown. Plan the episode before you record. After, turn the transcript into titles, descriptions, and thumbnails you can paste straight into YouTube.

/plan-episode
Episode Architect

Before you record: drafts questions, story arc, and moments to steer toward

/process-transcript
Content Analyst

Pulls 8 to 15 moments and scores each one on hook strength

/generate-titles
Title Writer

Writes 8 title options per clip and checks them against your rules

/generate-descriptions
Copywriter

Writes descriptions with hooks, hashtags, and SEO keywords you can paste in

/plan-thumbnails
Art Director

Two-line thumbnail briefs for the 16:9 and 9:16 formats

/review-content
Brand Guardian

Fix-first review. Parallel subagents catch voice, banned words, weak hooks, SEO, titles

/produce-shorts
Producer

Runs the whole pipeline from transcript to a ready-to-publish bundle

/publish-checklist
Launch Manager

Steps for pre-upload, launch day, first 24 hours, and day 3 to 4

/retro-episode
Analyst

Looks at how the episode did, then appends patterns to knowledge/13-learnings.md

KB
Knowledge base. Teach the AI your brand.
.podcli/knowledge/
  01-brand-identity.md · show, positioning, hosts
  02-voice-and-tone.md · voice, banned words
  05-title-formulas.md · title shapes, rules
  07-thumbnail-guide.md · layouts, colors, type
  ... 13 files, all customizable

It's an MCP server

Add it to Claude Code, Claude Desktop, or Codex. Say "clip this episode" and it runs transcription through export.

See all 19 MCP tools
1
transcribe_podcast
1
transcribe_start
1
set_video
1
import_transcript
2
suggest_clips
2
modify_clip
2
toggle_clip
3
create_clip
3
batch_create_clips
-
job_status
-
get_ui_state
-
knowledge_base
-
manage_assets
-
clip_history
-
analyze_energy
-
manage_presets
-
update_settings
-
list_outputs
-
parse_transcript
// claude_desktop_config.json or codex setup
{
  "mcpServers": {
    "podcli": {
      "command": "node",
      "args": ["dist/index.js"],
      "cwd": "./podcli"
    }
  }
}
Comparisons

Side-by-side with the tools you might be on

Real pricing, what each one actually does, and what changes when you move.

See the open-source landscape
Podcli vs

OpusClip

OpusClip is hosted, polished, and zero-setup. Podcli is the open-source local version: no watermark, no minute caps, your files never leave your laptop.

Read the comparison
Podcli vs

Vizard

Vizard is a hosted clipper with a clean dashboard. Podcli is the local-first open-source version: no monthly cap, no watermark, no upload, scriptable from the CLI.

Read the comparison
Podcli vs

Submagic

Submagic does captions on clips you already have. Podcli does the full pipeline: finds the clip, crops it, captions it, exports it. Captions are open-source React components you can edit.

Read the comparison
Podcli vs

ClipsAI

ClipsAI is a Python library that gives you clip-detection and dynamic 9:16 reframing primitives. Podcli is the end-to-end product around the same idea: CLI, web UI, captions, AI scoring, MCP server.

Read the comparison
Podcli vs

SupoClip

Both are open-source. SupoClip's path leads to a hosted upsell. Podcli stays local-first, ships an MCP server, and adds a knowledge-base layer so the AI picks clips that sound like your show.

Read the comparison
Podcli vs

Descript

Descript is a full transcript-driven editor for whole episodes. Podcli is the clip-only pipeline that runs after the episode is edited: it finds the moments, crops 9:16, burns captions, and exports.

Read the comparison
Podcli vs

Riverside

Riverside is where you record the podcast. Podcli is where you clip it. The overlap is Riverside's Magic Clips feature, and that's the part Podcli does better, free, and locally.

Read the comparison

Questions

How does Podcli compare to hosted clippers?+

Podcli is open source (AGPL-3.0) and runs on your laptop. There's no watermark on the output, no monthly minute cap, and no signup. Your podcast files stay on your machine. Hosted SaaS clippers charge a subscription and require you to upload the source video, which is a different tradeoff for a different audience.

Does Podcli upload my podcast files anywhere?+

No. Transcription, clip picking, cropping, and export all run on your machine. The only network calls are to the Claude or Codex API when you ask for AI clip suggestions, and even those are optional.

Can Podcli turn a podcast into TikTok and YouTube Shorts?+

Yes. That's the job. Podcli takes a long-form podcast episode, picks the moments worth clipping, crops to 1080×1920 with face tracking, burns in captions, and gives you files ready to upload to TikTok, YouTube Shorts, and Reels.

How is Podcli different from ClipsAI or SupoClip?+

ClipsAI is a Python library you wire into your own pipeline. SupoClip is an open-source clipper with a hosted upsell. Podcli ships three entry points (CLI, web UI, MCP server) and includes a knowledge base layer, so Claude or Codex picks clips that match your show's voice, banned words, and title formulas rather than picking on transcript heuristics alone.

What platforms does Podcli run on?+

macOS, Linux, and Windows. Hardware encoding uses VideoToolbox on Mac, NVENC on NVIDIA GPUs, and VAAPI on Linux, with a CPU fallback for anything else.

How does the AI clip picking work?+

Podcli sends the transcript and your knowledge base to Claude or Codex. The model returns scored clip candidates with timestamps. The knowledge base is a folder of markdown files that teaches the model your voice, title formulas, and banned words. Each candidate is scored on four dimensions, and the episode database is checked so you don't ship the same clip twice.

What is the MCP server for?+

Podcli ships as a Model Context Protocol server with 19 tools. Plug it into Claude Code, Claude Desktop, or Codex and tell the agent to clip an episode. It handles transcription, clip scoring, and export end to end.

Which AI coding tools does PodStack work with?+

Claude Code, OpenAI Codex, Cursor, or any AI coding tool that reads markdown commands. setup.sh auto-detects your tool from existing folders and falls back to a generic install for everything else.

Is Podcli free and open source?+

Yes. AGPL-3.0 licensed. Source is on GitHub. A commercial license is available if you need to use Podcli without AGPL terms — email siradze@nikusha.me.

Three ways to use it

CLI, Web UI, or AI agent. Same pipeline.

Process an episode
./podcli process episode.mp4 --top 8
 
All options
-t --transcript file.txt Use existing transcript
-n --top 8 Number of clips
-o --output ./shorts Output directory
--caption-style branded | hormozi | karaoke | subtle
--crop face (speaker-aware) | center
--quality low | medium | high | max
--logo asset name or path to PNG
-p --preset myshow Load saved config
 
Manage
./podcli assets add mylogo /path/to/logo.png
./podcli presets save myshow --caption-style branded
./podcli info
Install
Terminal
git clone https://github.com/nmbrthirteen/podcli.git
cd podcli
./setup.sh
Needs Node ≥ 18, Python ≥ 3.10, FFmpeg. Optional: Claude Code or Codex for AI clip suggestion.
Built with
TypeScript
Python
FFmpeg
Whisper
OpenCV
Remotion
React
Express
MCP SDK