CLI and browser extension that extracts clean text and generates summaries from web pages, PDFs, YouTube videos, podcasts, and audio or video files.
marswaveai/listenhub-cli
Command-line interface for the ListenHub API to create podcasts, text-to-speech audio, explainer videos, AI images, music and videos from the terminal.
- Stars
- 65
- Forks
- 5
- Open issues
- 0
- Last commit
- 4 days ago
What is it?
ListenHub CLI is a Node.js command-line client for the ListenHub platform, built on the @marswave/listenhub-sdk package. It exposes content creation commands such as podcast episodes, text-to-speech, explainer videos, slide decks, storybooks, AI images, music generation and video generation, along with listing, fetching and deleting of past creations.
The CLI supports two authentication modes. OAuth login via a browser (`listenhub auth login`) suits interactive use, while an OpenAPI key set through the LISTENHUB_API_KEY environment variable or `listenhub openapi config set-key` suits scripts and CI pipelines. The openapi subcommands also cover speech transcription with sentence and word timestamps, voice cloning, and PixVerse video generation.
Most creation commands accept a --no-wait flag and a --json output option, so results can be piped into other tools. Base URLs can be overridden for restricted networks, and the CLI includes a config show command to check which endpoint is in use.
Key features
- 01Generate podcasts, TTS audio, explainer videos and slide decks from the command line
- 02Create AI images and music, including covers, remixes and stem separation
- 03Speech transcription of local audio or video files with word-level timestamps
- 04Voice cloning workflow from reference audio to reusable private speakers
- 05JSON output and --no-wait options for scripting and automation
Use cases
- Batch-generating narration audio from scripts in a CI pipeline
- Creating podcast episodes or explainer videos from article URLs
- Transcribing recorded meetings or interviews with timestamps
- Producing background music or instrumental tracks from text prompts
Quick start
- 1
Install the CLI globally with npm
npm install -g @marswave/listenhub-cli - 2
Log in via browser OAuth
listenhub auth login - 3
Create a podcast from a query
listenhub podcast create --query "AI agent trends in 2026" --mode quick
Things to know
- Requires Node.js 20 or later.
- Most features need a ListenHub account, and some need paid credits.
In collections
Topics
FAQ
- What is listenhub-cli?
- Command-line interface for the ListenHub API to create podcasts, text-to-speech audio, explainer videos, AI images, music and videos from the terminal. ListenHub CLI is a Node.js command-line client for the ListenHub platform, built on the @marswave/listenhub-sdk package. It exposes content creation commands such as podcast episodes, text-to-speech, explainer videos, slide decks, storybooks, AI images, music generation and video generation, along with listing, fetching and deleting of past creations.
- Is listenhub-cli free to use? What license does it have?
- listenhub-cli is open source under the MIT license. Check the license terms before using it in commercial products.
- Is listenhub-cli still maintained?
- Actively maintained. The last commit to listenhub-cli was on Nov 3, 2026.
- What can I use listenhub-cli for?
- Batch-generating narration audio from scripts in a CI pipeline Creating podcast episodes or explainer videos from article URLs Transcribing recorded meetings or interviews with timestamps Producing background music or instrumental tracks from text prompts
- How do I install listenhub-cli?
- Install the CLI globally with npm: npm install -g @marswave/listenhub-cli Log in via browser OAuth: listenhub auth login Create a podcast from a query: listenhub podcast create --query "AI agent trends in 2026" --mode quick
- Where can I get listenhub-cli?
- The source code and installation instructions are on GitHub: https://github.com/marswaveai/listenhub-cli
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Local-first open-source AI voice studio for cloning voices, generating speech, dictating into any app, and giving AI agents a voice.
A zero-shot text-to-speech system that clones a voice from one reference audio clip, with emotion, speed and pronunciation control.
Open-source tool that transcribes, summarizes and archives videos and podcasts from YouTube, TikTok, Bilibili and 30+ platforms or local files.
Local, offline desktop studio for macOS and Windows that turns text into speech, clones voices, and generates songs with lyrics and MIDI scores.
A Python web app on Google Cloud's Vertex AI for generating images, video, music and speech with Gemini, Veo, Lyria and Chirp models.