Skip to content

Open-source AI podcast clipper. Generate vertical clips with face tracking and burned-in captions. CLI, MCP server, web app.

2.3 KB
Raw Blame
# podcli

Open-source AI podcast clipper. Turn a long episode into short clips with face tracking and burned-in captions. Drive it from the CLI, a web studio, or your coding agent.

Install: `curl -fsSL https://podcli.com/install.sh | sh`
Windows: `irm https://podcli.com/install.ps1 | iex`

Version: 2.8.2
License: AGPL-3.0. Commercial licensing: [email protected]
Repo: https://github.com/nmbrthirteen/podcli
Site: https://podcli.com

## Platforms

macOS (Apple Silicon), Linux (x64 and arm64), Windows (x64). Intel Macs aren't supported.

## Auth for AI scoring

Clip scoring uses Claude Code or Codex login, or an Anthropic API key; without those it falls back to heuristics. Speaker diarization needs HF_TOKEN. The local engine is free; podcli Pro is an optional cloud editor and account (`podcli login`).

## First run

`podcli process episode.mp4` (or studio / transcribe / multicam) provisions the engine on first run.
`podcli mcp` does not: stdout is JSON-RPC. Run `podcli setup` once before pointing an agent at it.
`--help` and `--version` never download anything.

## Agent CLI

```
podcli process episode.mp4 --json --yes
podcli doctor --json
```

JSON on stdout; progress and logs on stderr. `-y/--yes` skips prompts. `NO_COLOR=1` or a non-TTY turns off colour and spinners.

Exit codes: 0 success, 1 runtime error, 2 usage, 130 interrupted.

## MCP

32 tools. `podcli mcp` on stdio; `podcli mcp install` registers with Claude Code and Codex.

- ai_cli_status
- analyze_energy
- batch_create_clips
- clip_history
- compare_transcription_engines
- create_clip
- export_to_davinci_resolve
- get_ui_state
- import_transcript
- job_status
- knowledge_base
- list_outputs
- manage_assets
- manage_config
- manage_env
- manage_integrations
- manage_multicam
- manage_presets
- manage_reel
- manage_thumbnail_config
- mine_channel
- modify_clip
- parse_transcript
- process_episode
- rank_clip_candidates
- record_decisions
- set_video
- suggest_clips
- toggle_clip
- transcribe_podcast
- transcribe_start
- update_settings

`rank_clip_candidates` returns a shortlist so you do not have to read the whole transcript.
`process_episode` runs the pipeline as one job; poll it with `job_status`.

## Also

Clips (9:16 / 16:9 / 1:1) and full-episode multicam edit. Knowledge base at .podcli/knowledge/. PodStack slash commands in .claude/commands/.