AI Audio Editing Tools

April 26, 2026 · View on GitHub

A curated index of GitHub projects that give AI agents reliable, programmatic ways to edit, process, transcribe, and synthesise audio — skills, CLIs, MCP servers, and podcast production pipelines.

Last Updated: 2026-04-26 Entries: 14

Scope

OUT OF SCOPE: Models (Whisper weights, Bark, XTTS, DeepFilterNet checkpoints, etc.), DAWs and human-facing GUI apps (Audacity, Reaper, Logic Pro). MCP/CLI wrappers around DAWs are in scope when they expose an agent-callable surface.

FOCUS: Tooling (MCPs, Agent Skills, CLIs) that gives AI agents reliable, programmatic ways to handle audio production: normalization (LUFS / EBU R128), denoising, EQ, de-essing, silence trimming, format conversion, splicing, leveling, mastering, transcription (STT), and speech synthesis (TTS).

DEFINING FEATURE: Built for agents with human users — not for human UIs. Inclusion criterion is a stable agent-callable surface (skill, CLI, MCP, SDK) rather than a GUI workflow.

In scope: skills, CLIs, MCPs, podcast production pipelines.

Note on coverage: the agent-native audio space is genuinely thinner than image and video right now — most production-grade EQ, de-essing, and mastering still lives behind GUI/VST surfaces. Submissions welcome.

CLIs
MCPs
Skills — Editing & Processing
Skills — Podcast Pipelines
Skills — Synthesis (TTS)
Skills — Transcription

CLIs

ffmpeg-normalize

Audio Normalization for Python/ffmpeg

Stars Last commit Language

⭐ 1500 · Last updated: 2026-04-13 · slhck/ffmpeg-normalize

podwise-cli

CLI client for podwise.ai — turn any podcast episode into AI-powered insights, designed for use in AI agents and skills workflows.

Stars Last commit Language

⭐ 224 · Last updated: 2026-04-04 · hardhackerlabs/podwise-cli

MCPs

elevenlabs-mcp

The official ElevenLabs MCP server

Stars Last commit Language

⭐ 1330 · Last updated: 2026-03-20 · elevenlabs/elevenlabs-mcp

notebooklm-mcp

Bridge Google NotebookLM with Claude via MCP. Full programmatic access to create notebooks, manage sources, and generate AI-powered content — podcasts, videos, slides, mind maps, quizzes, flashcards, and reports — all through natural language.

Stars Last commit Language

⭐ 17 · Last updated: 2026-01-26 · alfredang/notebooklm-mcp

REAPER-MCP-Skills-Example

MCP server for controlling REAPER DAW through Python scripts.

Stars Last commit Language

⭐ 5 · Last updated: 2026-01-27 · wastee/REAPER-MCP-Skills-Example

video-audio-mcp

An FFMPEG powered MCP server for basic Video and Audio editing

Stars Last commit Language

⭐ 71 · Last updated: 2025-05-24 · misbahsy/video-audio-mcp

Skills — Editing & Processing

Claude-Audio-Production-Plugin

Claude Code plugin: audio production workflow — normalize, VAD, transcribe, diarize, podcast assembly, with engineering/podcast/transcript variants.

Stars Last commit Language

⭐ 0 · Last updated: 2026-04-19 · danielrosehill/Claude-Audio-Production-Plugin

Skills — Podcast Pipelines

content-pipeline

AI-powered content production pipeline for creators. One prompt → multi-platform publishing. Claude Code Skill.

Stars Last commit Language

⭐ 146 · Last updated: 2026-04-12 · OrangeViolin/content-pipeline

podcast-content-studio

Agent skill for generating podcast show notes from transcripts

Stars Last commit Language

⭐ 7 · Last updated: 2026-04-01 · fanyu-meng/podcast-content-studio

podcastcut-skills

Claude Code Skills for podcast/video editing: transcription, content editing, rough/fine cut, final polish

Stars Last commit Language

⭐ 28 · Last updated: 2026-03-17 · luoyuweidu1/podcastcut-skills

podcastfy-clawdbot-skill

A Clawdbot skill that generates a podcast-style MP3 from one or more URLs using the open-source Podcastfy project.

Stars Last commit Language

⭐ 16 · Last updated: 2026-01-31 · win4r/podcastfy-clawdbot-skill

video-podcast-maker

AI-powered video podcast creation skill for coding agents. Supports Bilibili & YouTube, multi-language (zh-CN/en-US), 6 TTS engines (Edge/Azure/ElevenLabs/OpenAI/Doubao/CosyVoice), 4K Remotion rendering.

Stars Last commit Language

⭐ 606 · Last updated: 2026-04-26 · Agents365-ai/video-podcast-maker

Skills — Synthesis (TTS)

Generative-Media-Skills

Multi-modal Generative Media Skills for AI Agents (Claude Code, Cursor, Gemini CLI). High-quality image, video, and audio generation powered by muapi.ai.

Stars Last commit Language