Nemotron Transcribe MCP

Local MCP server that transcribes an audio file by calling an already-running Nemotron 3.5 Transcribe endpoint. It does not download weights or start the model.

Long files are cut at a pause, about every 55 minutes, and sent one piece at a time. Pass speakers from 2 to 8 to repeat 10 seconds at each join. Speaker numbers start over on every piece.

This server writes a transcript. A YouTube link is saved first, then handled like a file. For timed subtitles (SRT or VTT), use another model. This checkpoint returns no word times.

Languages

The server hears the language in the file.

Leading

State of the art, or close to it, out of the box.

Production-ready

Production-level quality.

Supported

Supported, and fine-tuning can help.

Requirements

• An already-running Nemotron 3.5 Transcribe endpoint (this repo does not start the model)
• Docker Compose or Python 3.12+, uv, and ffmpeg/ffprobe on your PATH

Settings live in .env (copy from .env.example). Names and defaults are documented there once. Compose and the app only read those names.

Docker (home)

One path: Compose starts the MCP; Hermes connects over HTTP.

1. Copy settings and edit them:

cp .env.example .env

Set at least:

• NEMOTRON_BASE_URL=http://host.docker.internal:8010/v1 (model on the same machine; use 127.0.0.1 only without Docker)
• MCP_AUTH_TOKEN= to a long random string

.env is not copied into the image. Compose reads it on the host and injects the values when the container starts (env_file in compose.yaml).

1. Start / stop:

docker compose up -d --build
docker compose logs -f mcp
docker compose down

Image name: nemo-transcribe-mcp:0.1.0. MCP listens inside the container on port 8080 and is published on the host as 127.0.0.1:8083 by default (MCP_HOST_PORT).

1. Hermes (~/.hermes/config.yaml):

mcp_servers:
  nemo-transcribe:
    url: "http://127.0.0.1:8083/mcp"
    headers:
      Authorization: "Bearer YOUR_TOKEN_FROM_ENV"
    timeout: 300
    connect_timeout: 60

1. Audio: put files in ./audio on the host. Ask Hermes to use /data/audio/your-file.m4a (that is the path inside the container).

2. If the MCP cannot reach the model: inside Docker, localhost means the container. Prefer host.docker.internal for a model on the same host.

Check the process is up: curl -s http://127.0.0.1:8083/healthz

Without Docker

uv sync
cp .env.example .env

Edit .env and set NEMOTRON_BASE_URL (for a local process, http://127.0.0.1:8010/v1 is fine). Leave MCP_TRANSPORT=stdio.

uv run nemo-transcribe-mcp

Log lines go to stderr. Default format is one JSON object per line. Set NEMOTRON_LOG_FORMAT=text for a plain line in a terminal.

Cursor can launch it from this directory:

{
  "mcpServers": {
    "nemo-transcribe": {
      "command": "uv",
      "args": ["run", "nemo-transcribe-mcp"]
    }
  }
}

Ask the client to transcribe a file path. The tool is transcribe.

Tests and lint

uv run pytest
uv run ruff check .
uv run ruff format --check .
npm install
npm run check:yaml

Ruff covers Python. Prettier covers YAML (compose.yaml, prompts.yaml, languages.yaml).

The same checks run in GitHub Actions on every pull request (workflow: .github/workflows/ci.yml).

The tests do not call a model. They do need ffmpeg and ffprobe.