User repository on GitHub
MinusPod is a self-hosted server that removes ads before you ever hit play
- Forks
- 49
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Tools & CLIs
MinusPod
A self-hosted server that removes ads from podcasts before you hit play: it transcribes locally with faster-whisper or Parakeet, detects and cuts ad segments with your choice of LLM or System One, and learns sponsors across episodes.
- Stars
- 479
- Language
- Python
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- ttlequals0
- Last verified
- Oct 2026
- Languages
- Python
- Capabilities
- Open sourceSelf-hostedRuns locally
Highlights
- Local transcription with faster-whisper (Whisper) or NVIDIA Parakeet TDT 0.6B v3 on GPU or CPU, or through a remote API.
- Native System One support for detection and verification, with an experimental review stage; docs/system-one.md holds the details.
- Cross-episode ad patterns built from your corrections catch repeat sponsors without re-asking the LLM.
- Audio-side signals: loudness analysis, DAI transition detection, a cross-fetch differential, pre/post-roll, VAD-gap, and per-feed cue detection.
- Segment categories (sponsor, cross-promo, self-promo, interaction, intro/outro/recap) resolve to remove, beep, keep, or mark.
Watch out
README reviewed 2026-10-17 is truncated before the Quick start section, so install commands, hardware requirements, and container details are not in the digest. The System One path is labeled experimental, and no supported models, endpoints, or detection-accuracy numbers appear in the excerpt.
Questions about this entry
Short answers drawn from the linked project or page.
A self-hosted server that removes ads from podcasts before you ever hit play: it transcribes episodes locally, detects and cuts ad segments with an LLM, and learns ad patterns across episodes from your corrections.
It lists native System One support for detection and verification with experimental review, and its topics include systemone and jev. The README says you can bring your own LLM — Claude, Ollama, OpenRouter, OpenAI-compatible providers, or System One.
Local faster-whisper (Whisper) or NVIDIA Parakeet TDT 0.6B v3 running on GPU or CPU, or a remote API. Five per-feed processing modes and per-episode pass-through tune how much detection runs.
A first-pass LLM detection runs over sliding windows with a verification pass on the re-cut audio; an optional ad-reviewer stage confirms, adjusts, or rejects each cut, and confidence scoring feeds a review queue.
Yes: it builds cross-episode ad patterns from your corrections so repeat sponsors get caught without re-asking the LLM, and rejected detections stay visible for auditing.
The repo is MIT-licensed and describes a self-hosted server; GitHub shows 478 stars, 49 forks, created 2025-11-26, last pushed 2026-10-16. The digest states no pricing.
The digest cuts off before Quick start, so it does not cover installation, GPU minimums, the System One review details, or accuracy numbers; docs pages for system-one, workflows, and transcript differential are linked but their content is not in the digest.
More Jev resources like this
A local workbench that pairs OpenCV vision with Laya or Jev decision models: images are segmented and measured, hard rules settle the numbers, and the model gives the verdict — with one-click installers and an "open-source JEV" training path served at /v1/systemone.
Jev Tools & CLIs#community#github#python
Community
uu889/laya-opencvPython
uu889/laya-opencvPythonA local deep-research tool that turns your own PDF, DOCX, PPTX, image, TXT, or Markdown files into a structured report, using TypeSafe's Jev to rerank Qdrant chunks and verify evidence coverage while an LLM plans and writes.
Jev Tools & CLIs#community#github#python
Community
oqura-ai/deepdocPython
oqura-ai/deepdocPythonA drop-in proxy that distills a repeated Jev classification call into a local model as it runs: it learns from Jev's own probability distributions, then answers most requests itself while uncertain ones and a 2% audit slice keep going to Jev.
Jev Tools & CLIs#community#python#distillation
Community
tomerglick57/JevstillerPython
tomerglick57/JevstillerPythonFloating real-time translated subtitles for Japanese and English video and livestreams on Android, macOS, and Windows: speech recognition runs fully offline with bundled models, translation uses your own OpenAI-compatible endpoint, and optional TypeSafe Jev helpers refine the result.
Jev Tools & CLIs#community#github#subtitles
Community
korenkrita/simul-subtitleKotlin
korenkrita/simul-subtitleKotlinAn open-source platform for creating, distributing, and running sovereign EU-compliant LLMs: one Rust binary with OpenAI- and Ollama-compatible APIs, decisions answered as probabilities in milliseconds, and an audit trail designed for the EU AI Act.
Jev Tools & CLIs#community#github#local-llm
Community
eullm/eullmPython
eullm/eullmPythonA search API over about 203 million OpenAlex English title and abstract records, running DenseOn embedding search by meaning and a tantivy index for exact words behind one HTTP service. Its whole-field topic maps use TypeSafe's Jev to judge archetype and cited papers.
Jev Tools & CLIs#community#github#python
Community
maximerivest/srl-searchPython
maximerivest/srl-searchPythonFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.