Log inSubmit server
Viberadio Fm logo

Viberadio Fm

Narrates agent output and session recaps through a local stdio MCP server with monologue, podcast, and music styles.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Viberadio Fm

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "viberadio-fm": {
      "command": "npx",
      "args": [
        "-y",
        "viberadio-fm"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

We couldn’t confirm it starts correctly

We ran the install command but it didn't respond within our test window — this can mean a slow first-time install rather than a real problem.

npx -y viberadio-fm

No response to initialize.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked Today.

Overview

viberadio-fm MCP server lets an agent turn text or session events into spoken audio and styled recaps. Its stdio MCP entry point exposes `narrate` and `recap` tools, with optional style and mode settings. Narration uses the local system TTS tier by default, so it can run offline without API keys. Reach for it when you want to follow coding work by listening instead of reading.

Use cases

  • Narrate agent progress while away from the desk
  • Generate a spoken recap after a coding session
  • Convert session events into a two-host podcast
  • Speak individual status messages through local TTS

Key features

  • Stdio MCP server
  • Narration and session recap tools
  • Monologue, podcast, and reactive-music styles
  • Offline on-device speech
  • Live or asynchronous recap modes
  • TypeScript and JavaScript library API

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 3d ago

Recent health check succeeded.

4/4 checks healthy over the last 40d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 8d ago via OSV.dev · viberadio-fm (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

Last commit7d agoMost recent push to the default branch.
Install checkInconclusiveDidn't respond in our test window — often a slow first install.
Directory activity1 viewsConfig copies, upvotes, and views on AllMCPs.

How Viberadio Fm works

What viberadio-fm does

The viberadio-fm MCP server adds audio narration to agent workflows. An agent can send a line of text to the narrate tool or provide session events to recap. The result is intended for listening while coding, commuting, or handling another task.

Narration supports three documented styles: a spoken monologue, a two-host podcast, and reactive music. Recaps can be generated as a task summary or a longer session recap, while an ambient stream can narrate activity as work happens. Timing can be configured for live updates or for processing after a turn or session.

How it works

Run the CLI's MCP subcommand to start a standard input/output server. The MCP client launches viberadio mcp, then invokes the available tools with structured arguments. narrate accepts text and an optional style. recap accepts events, with optional style and mode values.

The default voice path uses the on-device tier of the shared Vibe model cascade. On macOS, Linux, and other supported local environments, this can use system speech commands such as say, espeak, or spd-say. The documented default does not require credentials or send audio text away from the machine. Hosted text-to-speech providers can be supplied later through the cascade, including providers such as ElevenLabs and OpenAI.

The package also exposes JavaScript and TypeScript functions for applications that do not need MCP. narrate speaks text, recap builds and speaks a recap, and buildRecapScript converts events into a script without producing audio.

Setup and configuration

Install the package globally with npm:

Terminal
npm i -g viberadio-fm

Register the MCP process in a client configuration using the viberadio server name, the viberadio command, and mcp as its argument:

config.json
{
  "mcpServers": {
    "viberadio": { "command": "viberadio", "args": ["mcp"] }
  }
}

No environment variables or API keys are required for the documented on-device setup. Voice and model selection can be varied by style when a different local or hosted provider is configured.

Tools and capabilities

  • narrate({ text, style? }) speaks an individual message.
  • recap({ events, style?, mode? }) creates an audio recap from session events.
  • Monologue, two-host podcast, and reactive-music styles are documented.
  • Recap timing supports live or post-turn/session workflows.
  • Local speech works offline when the on-device tier is used.

Limitations and notes

The MCP interface documents two tools only: narrate and recap. Features such as recording, visualizers, OBS streaming, collaborative playback, and desktop controls are described as broader project features, not as MCP tool parameters. Reactive music is listed as a style, but the MCP excerpt does not specify a separate music-control tool.

The viberadio-fm MCP server depends on the host's available speech system for its local tier. Provider-specific behavior, voice availability, and hosted TTS configuration are not detailed in the MCP setup instructions.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Viberadio Fm

viberadio-fm is an MCP server that connects agent workflows to local text-to-speech and exposes `narrate` and `recap` tools. Agents can speak a text message or turn session events into an audio recap, using monologue, two-host podcast, or reactive-music styles. Its on-device tier works offline without API keys.

Install it globally with `npm i -g viberadio-fm`, then configure your MCP client to run `viberadio mcp`. The documented configuration uses the `viberadio` command with `mcp` as its only argument. The local speech setup does not require environment variables or API keys.

It provides `narrate` and `recap`. Use `narrate` with text and an optional style for immediate speech; use `recap` with session events and optional style or mode settings to create an audio recap.

It provides a standard stdio MCP command and a generic MCP configuration example, but does not document Cursor-specific setup steps.

Related MCP servers

All in Text-to-Speech All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewViberadio Fm AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/viberadio-fm?style=directory)](https://allmcps.com/mcp/viberadio-fm)
HTML Embed
<a href="https://allmcps.com/mcp/viberadio-fm"><img src="https://allmcps.com/api/badge/viberadio-fm?style=directory" alt="Viberadio Fm on AllMCPs" /></a>