Voice Audio Mcp

io.github.CSOAI-ORGPublished by GitHub account CSOAI-ORGv1.0.10Updated Oct 30, 2026

Voice Audio MCP server. Tools: text to speech, list voices, transcribe. Built by MEOK AI Labs.

VerifiedSTDIODesktop onlyMedia & DesignAI & ML

Overview

AI-generated overview

Local MCP server for voice and audio work: text-to-speech, voice listing, transcription, language detection and audio analysis.

What you can do
  • Generate speech from text and list available voices
  • Transcribe audio to text
  • Analyze audio, detect its language and estimate duration
  • Runs locally over stdio and is configured in the MCP client with uvx or the installed command
When to use it
Useful when an assistant should turn text into spoken audio, transcribe recordings, or inspect an audio file's language and length without leaving the chat client. It is a local, desktop-only tool, so it suits individual work on your own machine rather than shared or web-hosted setups.
Requirements
A local Python environment on a desktop machine; install the voice-audio-mcp package from PyPI (pip) or run it with uvx, then register it in the MCP client config with stdio transport. No accounts, API keys, environment variables or headers are declared. The README mentions Kokoro TTS and Whisper STT integration, which may need additional local models or downloads.
Before you install
The README is heavily promotional: it advertises paid tiers, Stripe purchase links, a governance pack installer and compliance claims, none of which are needed to use the audio tools; treat those claims and links with skepticism. Voice cloning and audio generation are mentioned, so check consent and rights for any voice or recording you process. Audio content you submit is handled by the local process.

Installation

In SourceWeft

  1. Open Voice Audio Mcp in the dashboard and add it to a workspace.
  2. 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

[MCP Scorecard: 86/100]

Voice Audio MCP

[MEOK AI Labs] [GSPC] [License] [PyPI] mcp-name: io.github.CSOAI-ORG/voice-audio-mcp

Voice Audio

[PyPI] [Python]

By MEOK AI Labs — MEOK AI Labs — Voice & Audio. Transcription, analysis, language detection, and duration estimation.

MEOK AI Labs — Voice & Audio

MEOK AI Labs — Voice & Audio. TTS, voice cloning, audio generation, transcription. Integrates with Kokoro TTS and Whisper STT.

🚀 Quick Start

bash
# Install via pippip install voice_audio_mcp
# Or install via Smitherynpx -y @smithery/cli@latest install voice-audio-mcp --client claude

✨ Features

  • MCP protocol compliant
  • Easy installation
  • Well-documented API
  • Production-ready
  • Active maintenance

📖 Documentation

🛡️ Compliance

This MCP server is built with EU AI Act compliance built-in:

  • ✅ Article 9 — Risk Management System
  • ✅ Article 13 — Transparency & Instructions for Use
  • ✅ Article 15 — Bias Detection & Testing
  • ✅ Article 26 — FRIA Support (where applicable)
  • ✅ Article 50 — AI Content Watermarking (where applicable)

Need help getting compliant? Book a free 15-min diagnostic →

🏢 Enterprise

Need custom development, SLA guarantees, or white-label deployment?

  • Pro: $99/mo — Full MCP suite + EU AI Act tracking
  • Enterprise: $499/mo — Custom dev + SLA + Dedicated support

View Pricing → | Contact Sales →

🤝 Part of the MEOK Ecosystem

This server is part of the MEOK AI Labs ecosystem — 300+ MCP servers for sovereign AI governance.

DomainPurpose
councilof.aiEU AI Act compliance marketplace
safetyof.aiAI safety & monitoring
meok.aiSovereign AI platform
cobolbridge.aiLegacy modernization

📜 License

MIT © CSOAI-ORG

Built with 💜 by MEOK AI Labs · UK Companies House 16939677

MIT — MEOK AI Labs

Pairs with MEOK Governance Suite

Build something that touches users? You need compliance. MEOK ships 38 governance MCPs that drop in alongside this tool — EU AI Act, DORA, NIS2, CRA, GDPR, ISO 42001, FDA SaMD, MDR, Basel, MiFID II, MiCA, COPPA, and more.

bash
# One-shot install of the governance packnpx meok-setup --pack governance

Free tier: 10 calls/day per MCP. Pro tier (£79/mo): unlimited + cryptographically signed compliance attestations your auditor verifies independently.

→ Full catalogue: councilof.ai/catalogue → MEOK AI Labs: meok.ai

💸 Try MEOK in 30 seconds — instant buy ladder

TierPriceWhat you getStripe
Smoke test£1Signed sample MCP-Hardening report + Article 50 PDFhttps://buy.stripe.com/aFa7sNcgAdQS0ZT1Uc8k91t
Quick Kit£9EU AI Act Article 50 implementation guide (C2PA + EU-Icon)https://buy.stripe.com/aFa7sNcgAdQS0ZT1Uc8k91t
Founder Call£2930-min 1-on-1 with the founderhttps://buy.stripe.com/aFa7sNcgAdQS0ZT1Uc8k91t

Refundable. UK Stripe — VAT-clean. Builds on the 81-MCP MEOK fleet. Verify any signed report at https://meok.ai/verify.

Configuration

Add to your claude_desktop_config.json (Claude Desktop) or your MCP client config:

json
{  "mcpServers": {    "voice-audio-mcp": {      "command": "uvx",      "args": ["voice-audio-mcp"]    }  }}

Or: pip install voice-audio-mcp then run the voice-audio-mcp command (stdio transport).

Examples

Once configured, ask your assistant, for example:

  • "Use transcribe_audio to …"
  • "Use analyze_audio to …"
  • "Use detect_language to …"

Source: README.md at commit 6ef04ee

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.10LatestSep 16, 2026

Score

40% 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

    Declare a license in the repository or the registry entry.