podwise-cli
A Podwise console client that gives an agent transcripts, summaries, chapters and answers for podcast episodes and YouTube videos
- 419 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The CLI calls the podwise.ai API with your key and uploads links and local audio files there.
Install
- Works in
Manual install
brew install hardhackerlabs/podwise-tap/podwiseThe first README option for macOS. There is also an `install.sh` script, prebuilt binaries and a Go build.
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The CLI calls the podwise.ai API with your key and uploads links and local audio files there.
This is third-party code. Review the repository files before installing.
What it does
podwise-cli connects an agent to podwise.ai, a service that breaks podcasts into a transcript, a summary, timestamped chapters, Q&A and a mind map. The `podwise process` command accepts a Podwise or Xiaoyuzhou episode link, a YouTube video or a local audio file. The `podwise get summary` and `podwise get transcript` commands fetch the results, `podwise ask` answers a question from transcripts of many episodes, and `podwise search` finds episodes and shows. The output is meant for a model to read, with no browser involved. The `skills/` folder holds a skill with eight scenarios: catching up on missed episodes, a weekly recap, notes in Notion, Obsidian or Logseq, topic research, debating an episode, Anki flashcards and recommendations. The same binary also runs as an MCP server with `podwise mcp`.
Who it is for. Researchers, content creators and product managers who follow many podcasts and want summaries and quotes from them right inside the agent.
Good fit when
- A week of episodes from your favourite shows has piled up, and you want the key points without listening.
- You are preparing an article or a talk and want guests' views from several podcasts on one topic.
- An episode summary should land in Obsidian or Notion with chapters and timestamps.
- An English interview should become Anki flashcards for language learning.
Not a fit when
- Transcription has to happen locally without sending audio to an external service.
- You have no podwise.ai account and do not plan to create one.
- You work with private meeting recordings that must not leave your systems.
Example request
Put together a recap of this week's episodes from the podcasts I follow and pull three key ideas from each.Limitations
All processing happens on podwise.ai servers, so you need an account and an API key; `podwise auth` obtains it through the browser and saves it in `~/.config/podwise/config.toml`. Local files and links are sent to the service for processing. Supported sources are Podwise, Xiaoyuzhou, YouTube and local files; other platforms are not listed in the README. The skill needs the CLI installed and configured beforehand. The hosted MCP server with OAuth lives in the separate podwise-plugin repository.
How to disable. Remove the `podwise` binary from its PATH directory, the `~/.config/podwise` folder and the skill from the agent's skills folder. Delete the `podwise` block from your MCP settings.
FAQ
How do I connect podwise-cli to Claude Desktop or Cursor as an MCP server?
Add a `podwise` server to the MCP settings with the command `podwise` and the argument `mcp`. The CLI must be installed and authorized first.
Can I process my own audio file?
Yes, `podwise process ./episode.mp3` accepts a local file. It is uploaded to podwise.ai, and the results are fetched with `podwise get` commands.
Which scenarios does the skill cover?
Eight: catch-up, weekly-recap, episode-notes, topic-research, episode-debate, language-learning, discover and refine-taste. The skill picks a scenario from the request or calls the matching CLI command.
Where is the access key stored?
In `~/.config/podwise/config.toml`. You can get the key through the browser with `podwise auth` or set it by hand with `podwise config set api_key`.
Is there an option without installing the binary?
There is a hosted MCP server at `https://mcp.podwise.ai/mcp` with OAuth 2.1. It ships together with the skill in the hardhackerlabs/podwise-plugin repository.
Discussion
No questions or reviews yet.
Related
CLI toolsA command-line tool that finds podcast episodes on Apple Podcasts, RSS or Xiaoyuzhou and saves them as files, with agent support.
watch-cli is a skill and CLI that hands an agent the frames and transcript of any social video so it can read the clip itself.
Self-hosted podcast studio whose built-in MCP endpoint creates episodes from links and text and manages schedules.
The skill turns a video or podcast link or file into a transcript and summary using platform subtitles and Whisper.
A local short-video studio: topic, script, CC0 images, voice-over and MP4 with subtitles, driven by Claude Code or Codex
Four BibiGPT skills: the agent summarizes YouTube and Bilibili videos and podcasts, pulls subtitles and works with a notes library
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| podwise-cli (this card) | no | 419 | |
| AI Video Transcriber | no | 3,411 | transcribes video locally via subtitles and Whisper; here ready summaries, chapters and search across Podwise episodes |
| Podcast to Course | no | 115 | turns one episode into an interactive course; here follows, weekly recaps and questions across many podcasts |
README in short
The README lists install options from Homebrew to building from source, command examples and a table of skill scenarios. A separate section covers the nineteen MCP server tools and the settings snippet to connect it.