Skip to content
Agentmart
Submit a tool

Best agent skills for audio and music

We found 831 agent skills for audio and music in the catalog; these are the 15 that rank highest. The order comes from our rank, which weighs adoption, freshness, documentation and publisher identity. Nobody can pay for a place on this list. video-transcript-downloader, markdown-converter and elevenlabs lead it. voice-isolator and voice-changer are published by the company that makes them. video-transcript-downloader comes from the largest repository here (7,401 stars). 15 of the 15 had activity in the last 30 days. Each entry lists why it made the list and links to its install page.

Updated Oct 26, 2026 · Built from catalog data; how we rank and grade

Top 15 of 831

  1. 1
    video-transcript-downloader

    steipete

    yt-dlp downloads: video, audio, subtitles, transcripts, clips, playlists.

    • Largest repository here (7,401 stars)
    • Active in the last 30 days
    • Open source (MIT)

    ★ 7.4KLast active Oct 16, 2026Claude Code, Claude apps, Codex, Cursor +6

  2. 2
    markdown-converter

    steipete

    Markdown conversion: PDF, Office, HTML, data, OCR, audio, ZIP, YouTube.

    • Largest repository here (7,401 stars)
    • Active in the last 30 days
    • Open source (MIT)

    ★ 7.4KLast active Sep 30, 2026Claude Code, Claude apps, Codex, Cursor +6

  3. 3
    elevenlabs

    digitalsamba

    Generate AI voiceovers, sound effects, and music using ElevenLabs APIs.

    • Repository has 2.3K stars
    • Active in the last 30 days
    • Open source (MIT)

    ★ 2.3KLast active Oct 21, 2026Claude Code, Claude apps, Codex, Cursor +6

  4. 4
    acestep

    digitalsamba

    AI music generation with ACE-Step 1.5 — background music, vocal tracks, covers, stem extraction, audio repainting, and continuation for video production.

    • Repository has 2.3K stars
    • Active in the last 30 days
    • Open source (MIT)

    ★ 2.3KLast active Oct 21, 2026Claude Code, Claude apps, Codex, Cursor +6

  5. 5
    podcast-transcribe

    chubbyguan

    播客/小宇宙 → 下载 → 转录 → 存为 Markdown 的完整工作流。 支持 RSS 批量下载、单集链接转录。

    • Repository has 1.3K stars
    • Active in the last 30 days
    • Open source (MIT)

    ★ 1.3KLast active Oct 8, 2026Claude Code, Claude apps, Codex, Cursor +6

  6. 6
    voice-isolator

    elevenlabsOfficial

    Remove background noise and isolate vocals/speech from audio using ElevenLabs Voice Isolator (audio isolation) API.

    • Published by the vendor
    • Active in the last 30 days
    • Open source (MIT)

    ★ 508Last active Oct 18, 2026Claude Code, Claude apps, Codex, Cursor +6

  7. 7
    voice-changer

    elevenlabsOfficial

    Transform the voice in an audio recording into a different target voice while preserving emotion, timing, and delivery using the ElevenLabs Voice Changer…

    • Published by the vendor
    • Active in the last 30 days
    • Open source (MIT)

    ★ 508Last active Oct 18, 2026Claude Code, Claude apps, Codex, Cursor +6

  8. 8
    claudemy

    assafkip

    Turn any topic into a short audio course.

    • Active in the last 30 days
    • Open source (MIT)
    • Ships helper scripts

    ★ 422Last active Oct 16, 2026Claude Code, Claude apps, Codex, Cursor +6

  9. 9
    music-video

    NoizAI

    Build a music video from an existing song and lyrics, either as p5.js/p5.brush animation or by assembling local images and clips.

    • Active in the last 30 days
    • Ships helper scripts
    • For Python

    ★ 531Last active Sep 28, 2026Claude Code, Claude apps, Codex, Cursor +6

  10. 10
    xsai

    moeru-ai

    Choose xsAI packages or route tasks across text, audio, decisions, images, embeddings, and model lists.

    • Active in the last 30 days
    • Open source (MIT)

    ★ 664Last active Oct 10, 2026Claude Code, Claude apps, Codex, Cursor +6

  11. 11
    indextts2-audio

    vb2250158

    通过 RabiSpeech 的本地 IndexTTS2 模型生成中文或音色复刻语音。用户指定 IndexTTS2、中文参考音频、情绪/风格指令、角色声线或本地 WAV 验证时使用。不得直接运行技能内 worker、启动 OumuQ 或调用云端 API。

    • Active in the last 30 days
    • Open source (MIT)

    ★ 492Last active Oct 20, 2026Claude Code, Claude apps, Codex, Cursor +6

  12. 12
    qwen-tts-audio

    vb2250158

    通过 RabiSpeech 使用本地 Qwen3-TTS 0.6B 或 1.7B 生成角色、多语言或音色复刻语音。用户指定 Qwen3-TTS、日语/多语言、本地参考音频、角色名或模型大小对比时使用。不得启动技能内 worker、OumuQ 或任何 Qwen/DashScope 云端 API。

    • Active in the last 30 days
    • Open source (MIT)

    ★ 492Last active Oct 20, 2026Claude Code, Claude apps, Codex, Cursor +6

  13. 13
    transcribing-audio

    boldsoftware

    Use when a task requires STT/ASR.

    • Active in the last 30 days

    ★ 710Last active Oct 24, 2026Claude Code, Claude apps, Codex, Cursor +6

  14. 14
    fishjam

    software-mansion-labs

    Software Mansion's Fishjam — hosted WebRTC platform for video, audio, one-to-many livestreaming, and compositions.

    • Active in the last 30 days
    • Open source (MIT)

    ★ 296Last active Oct 15, 2026Claude Code, Claude apps, Codex, Cursor +6

  15. 15
    xsai-audio

    moeru-ai

    Generate or stream speech and transcribe recordings with xsAI's audio package.

    • Active in the last 30 days
    • Open source (MIT)

    ★ 664Last active Oct 10, 2026Claude Code, Claude apps, Codex, Cursor +6

Related