Skip to content
Agentmart
Submit a tool

Best MCP servers for transcription

We found 193 MCP servers for transcription 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. FunASR, BibiGPT and Voicemode lead it. Paxa Labs is published by the company that makes it. FunASR has the most GitHub stars here (20,801). 14 of the 15 had activity in the last 30 days. Remote servers need no local install; local ones run on your machine and can reach local files. 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 193

  1. 1
    FunASR

    modelscope

    Transcribe local audio with FunASR and SenseVoice using private, on-device inference.

    • Most GitHub stars here (20,801)
    • Open source (MIT)

    ★ 20.8KLast active Sep 18, 2026Local (stdio)Claude Code, Codex, VS Code, Cursor +2

  2. 2
    BibiGPT

    JimmyLv

    Summarize, transcribe and search YouTube, Bilibili, TikTok, podcasts and other videos with AI.

    • Remote server, no local install
    • Active in the last 30 days

    ★ 131Last active Oct 13, 2026Remote (HTTP)Claude Code, VS Code, Cursor, Windsurf

  3. 3
    Voicemode

    voicemode.dev

    Natural voice conversations for AI assistants - STT/TTS.

    • 1.4K GitHub stars
    • Most weekly downloads here (1.4K)
    • Active in the last 30 days

    ★ 1.4K↓ 1.4K/wkLast active Oct 25, 2026Local (stdio)Claude Code, Codex, VS Code, Cursor +2

  4. 4
    three.ws Audio

    nirholas

    Text-to-speech, speech-to-text, audio-to-face lipsync, and motion-capture clips for 3D agents.

    • Active in the last 30 days
    • Open source (Apache-2.0)

    ★ 247Last active Oct 23, 2026Local (stdio)Claude Code, Codex, VS Code, Cursor +2

  5. 5
    showtime

    FavioVazquez

    Local video studio for your coding agent: scenes, voice, music and captions, on your machine.

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

    ★ 281↓ 338/wkLast active Oct 17, 2026Local (stdio)Claude Code, Codex, VS Code, Claude Desktop +2

  6. 6
    SuperCMO

    SupercmoHQ

    Marketing media generation — image, video, voice — for AI agents.

    • Active in the last 30 days
    • Open source (Apache-2.0)

    ★ 206↓ 292/wkLast active Oct 21, 2026Local (stdio)Claude Code, Codex, VS Code, Cursor +2

  7. 7
    Paxa Labs

    paxalabs.comOfficial

    Thai, English, Mandarin speech AI: TTS with playback, transcription, translation, OCR, extraction

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

    ★ 10↓ 414/wkLast active Oct 18, 2026Local (stdio)Claude Code, Codex, VS Code, Cursor +2

  8. 8
    Bilibili MCP Server

    XZXZZX-Ai

    Bilibili MCP tool for video metadata, transcripts, subtitles, and comment summarization

    • Active in the last 30 days
    • Open source (Apache-2.0)

    ★ 39Last active Oct 23, 2026Local (stdio)Claude Code, Codex, VS Code, Cursor +2

  9. 9
    Transcriptor MCP

    samson-art

    Fetch transcripts, subtitles, chapters, metadata and frames from YouTube and 10+ video platforms

    • Runs locally or as a remote server
    • Active in the last 30 days
    • Open source (MIT)

    ★ 24Last active Oct 17, 2026Local (stdio), Remote (HTTP)Claude Code, VS Code, Codex, Cursor +2

  10. 10
    whosaid

    sblattj

    Local speaker-attributed transcription and meeting search for Apple Silicon.

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

    ★ 6↓ 283/wkLast active Oct 23, 2026Local (stdio)Claude Code, Codex, VS Code, Cursor +2

  11. 11
    Transcription

    www.scriptivox.com

    Transcribe audio and video and work with your transcript library from any AI app.

    • Remote server, no local install
    • Active in the last 30 days
    • Open source (MIT)

    ★ 9Last active Oct 23, 2026Remote (HTTP)Claude Code, VS Code, Cursor, Windsurf

  12. 12
    babelscribe

    phonology024

    Offline speech-to-text and SRT subtitles in 99 languages on your own AMD/NVIDIA/Intel/Apple GPU.

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

    ★ 6↓ 87/wkLast active Oct 10, 2026Local (stdio)Claude Code, Codex, VS Code, Cursor +2

  13. 13
    Talkies

    psyb0t

    Self-hosted MCP server for speech: ASR transcription, TTS synthesis, and file staging tools.

    • Remote server, no local install
    • Active in the last 30 days
    • Open source (WTFPL)

    ★ 7Last active Oct 19, 2026Remote (HTTP)

  14. 14
    Whisper MCP

    jwulff

    Local audio transcription using whisper.cpp.

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

    ★ 3Last active Oct 20, 2026Local (stdio)Claude Code, Codex, VS Code, Cursor +2

  15. 15
    tvsub MCP

    launzi

    Control tvsub for Apple TV.app: subtitles, glossary-aware translation, overlay, styling, and sync.

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

    ↓ 237/wkLast active Oct 22, 2026Local (stdio)Claude Code, Codex, VS Code, Cursor +2

Related