InnerVault

Whisper Transcribe

Stale Official MCP Registry, io.github.ZahiriNatZuke

Transcribe audio locally with faster-whisper or through the OpenAI Whisper API.

Open the source (opens github.com) https://github.com/zahirinatzuke/whisper-transcribe-mcp

Before you use it

  • Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
  • Needs credentials: OPENAI_API_KEY. Use a key with the least access you can.

What it is

MCP servers from io.github.ZahiriNatZuke.

The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.

How to get it

pypi package (stdio)

whisper-transcribe-mcp@1.1.3

From the server's entry in the official MCP Registry

Settings it asks for

  • OPENAI_API_KEY secret · OpenAI API key. Enables the cloud backend and optional GPT post-processing.
  • WHISPER_MODEL · Default faster-whisper model size when using the local backend.
  • WHISPER_POST_PROCESS_MODEL · OpenAI chat model used for optional GPT post-processing.

Related

  1. Speech to text from audio/video files and podcast feeds: text, timestamps and SRT subtitles.

    Stale Official MCP Registry, io.github.prometheus-maker Updated 10 days ago 1 note

  2. whisper-mcp

    MCP servers

    Local audio transcription using whisper.cpp. Transcribe with OpenAI Whisper models.

    Stale Official MCP Registry, io.github.jwulff Updated 10 months ago 1 note

    whisper-mcp@0.1.1
  3. Turn recordings into captions and searchable transcripts in 28 languages. 6 USD per 1,000 minutes.

    Stale Official MCP Registry, io.github.bepolabs Updated 4 days ago 1 note

  4. Nojoin

    MCP servers

    Self-hosted meeting notes with no bot in the call. Records Meet, Teams and Zoom from the browser, transcribes on your own hardware, and lets Claude or ChatGPT read and edit your library over MCP.

    Indexed GitHub, Valtora 86 ★AGPL-3.0Updated 3 days ago

    git clone https://github.com/Valtora/Nojoin.git
  5. Transcribe local audio and video using Whisper or the OpenAI API.

    Stale Official MCP Registry, io.github.cykk Updated 5 days ago 1 note

    audio-transcription-mcp@0.1.0
  6. FunASR

    MCP servers

    Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

    Indexed GitHub, modelscope 21.0k ★MITUpdated yesterday

    git clone https://github.com/modelscope/FunASR.git