Murmur

io.github.tarunyadav1Published by GitHub account tarunyadav1v1.0.1Updated Nov 7, 2026

Offline text to speech and voice cloning on macOS through the Murmur app.

VerifiedSTDIODesktop onlyMedia & Design AI & ML

Server details

Identifier: io.github.tarunyadav1/murmur-cli
Transport: STDIO
Runtime: Desktop only
Trust: Verified
Published: Nov 7, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified the GitHub account tarunyadav1 for this listing. That does not show the account is the product's maker.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.tarunyadav1%2Fmurmur-cli.svg)](https://sourceweft.com/mcp/io.github.tarunyadav1%2Fmurmur-cli?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

Murmur gives an assistant offline text-to-speech and voice cloning on macOS by driving the local Murmur app to produce audio files.

What you can do: Generate speech from text or a text file into audio files, choosing voice, model, speed and output format.
List and install speech models, and list available voices.
Run batch jobs from a manifest and check the status of a job.
Check whether the local Murmur helper is reachable and ready.
When to use it: Useful when you want an assistant to produce voiceovers, narration or audio drafts on a Mac without sending text to a cloud service. Suited to local, privacy-conscious audio workflows and batch generation of many clips.
Requirements: macOS 15 or later on Apple Silicon or Intel, with the Murmur app installed and Automation enabled once in its settings. The npm package murmur-cli runs via npx or a global install; if the app is not in a standard location, the MURMUR_HELPER environment variable must point to its helper binary.

Before you install

The app has a free plan and a one-time Pro upgrade, so some features may require a paid license. Voice cloning raises consent and rights questions about the voices used. Generation writes audio files to the paths you specify.

Installation

In SourceWeft

Open Murmur in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

murmur-cli

Command line and MCP access to Murmur, an offline text-to-speech and voice cloning app for Mac. Speech is generated on your own computer; your text is never uploaded.

This package is a small launcher. It finds the signed CLI that ships inside Murmur.app and runs it, so you can call murmur from any project, npm script or AI agent.

Requirements

macOS 15 or later (Apple Silicon or Intel)
The Murmur app, free to download: https://www.murmurtts.com/download/latest
Automation turned on once in Murmur > Settings > Automation

Install

Or run it without installing:

Generate speech

murmur generate --text "Welcome back. Today we're building a local voice workflow." \  --voice af_bella --speed 0.95 --output audio/intro.wav
murmur generate --input scripts/chapter-01.txt --model kokoro --output audio/chapter-01.m4a

murmur generate --text "Welcome back. Today we're building a local voice workflow." \  --voice af_bella --speed 0.95 --output audio/intro.wav
murmur generate --input scripts/chapter-01.txt --model kokoro --output audio/chapter-01.m4a

Other commands:

murmur models [--json]murmur models install MODEL_IDmurmur voices [--model ID] [--json]murmur batch --manifest scenes.jsonmurmur jobs get JOB_ID

murmur models [--json]murmur models install MODEL_IDmurmur voices [--model ID] [--json]murmur batch --manifest scenes.jsonmurmur jobs get JOB_ID

Run murmur --help for every option.

Use with AI agents (MCP)

Murmur includes an MCP server, so Claude Code, Codex, Cursor and other MCP clients can generate voiceovers on your Mac.

json

{  "mcpServers": {    "murmur": { "command": "npx", "args": ["-y", "murmur-cli", "mcp", "serve"] }  }}

{  "mcpServers": {    "murmur": { "command": "npx", "args": ["-y", "murmur-cli", "mcp", "serve"] }  }}

Custom app location

If Murmur.app is not in /Applications or ~/Applications, point to the helper:

Docs

Full CLI and MCP guide: https://www.murmurtts.com/docs/automation

The launcher in this package is MIT licensed. The Murmur app has its own license, with a free plan and a one-time Pro upgrade.

Source: README.md at commit 6ff05e5

Tools

SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

v1.0.1LatestNov 7, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
License10 pts