Audio Intelligence MCP Server

Transcribe, summarize, and analyze audio — meetings, interviews, podcasts, voice memos — directly from Claude Desktop or any MCP-compatible AI agent.

No OpenAI API key. No per-minute billing. No audio uploaded to third-party servers. Powered by Whisper + local AI inference on dedicated hardware.

What You Can Do

Tool	What It Does	Price
transcribe_audio	Speech-to-text with word-level timestamps	$0.05/call
summarize_audio	Transcription + AI summary (brief, detailed, or action items)	$0.10/call
analyze_audio	Full analysis: speakers, sentiment, topics, key phrases	$0.15/call

Connect to Claude Desktop

Add to your MCP config (claude_desktop_config.json):

{
  "mcpServers": {
    "audio-intelligence": {
      "url": "https://ntriqpro--audio-intelligence-mcp.apify.actor/mcp?token=YOUR_APIFY_TOKEN"
    }
  }
}

Replace YOUR_APIFY_TOKEN with your token from apify.com/settings/integrations.

Then ask Claude: "Summarize the action items from this meeting recording: [audio URL]"

Use Cases

• Meeting recordings — Get action items and decisions from standup, planning, or client calls
• Interview analysis — Transcribe user research interviews and extract key themes
• Podcast processing — Convert podcast episodes into searchable text
• Voice memo capture — Turn voice notes into structured text and bullet points
• Multilingual audio — Transcribe non-English recordings (Whisper supports 99 languages)

Tool Reference

transcribe_audio

audioUrl: "https://example.com/meeting.mp3"
language: "en"  # optional, auto-detect by default

Response:

{
  "status": "success",
  "text": "Hello, welcome to today's meeting. Let's start with the agenda.",
  "segments": [
    { "start": 0.0, "end": 3.5, "text": "Hello, welcome to today's meeting." },
    { "start": 3.5, "end": 7.2, "text": "Let's start with the agenda." }
  ],
  "language": "en",
  "model": "whisper-large-v3-turbo"
}

summarize_audio

audioUrl: "https://example.com/standup.mp3"
summaryType: "action_items"  # "brief" | "detailed" | "action_items"

Response:

{
  "status": "success",
  "transcript": "...",
  "summary": {
    "action_items": ["Review Q1 report by Friday", "Schedule follow-up with legal"],
    "decisions": ["Approved new budget allocation"],
    "follow_ups": ["Check with legal team on contract terms"]
  }
}

analyze_audio

audioUrl: "https://example.com/interview.mp3"

Response:

{
  "status": "success",
  "transcript": "...",
  "analysis": {
    "speakers_estimated": 2,
    "topics": ["quarterly review", "budget planning"],
    "sentiment": "positive",
    "key_phrases": ["revenue growth", "new market expansion"],
    "summary": "A productive meeting discussing Q1 results and Q2 plans."
  }
}

Supported Formats

MP3, WAV, M4A, OGG, FLAC, WebM, and most common audio formats.

Technology

• Speech Recognition: OpenAI Whisper large-v3-turbo (MIT License) — runs on dedicated hardware, not OpenAI's API
• Text Analysis: Qwen 3.5 (Apache 2.0) — local inference, zero data retention
• Privacy: Audio processed in real-time. Files are not stored or used for training.

Legal Disclaimer

Users are solely responsible for obtaining all necessary consents and authorizations before submitting audio recordings for processing. This includes compliance with applicable laws regarding recording consent (including two-party consent laws in relevant jurisdictions). Audio data is processed in real-time and is not stored or retained. This service does not constitute legal advice.

---

🔗 Related Actors by ntriqpro

Extend this actor with the ntriqpro intelligence network:

• supply-chain-risk-mcp — MCP server for supply chain risk
• video-intelligence-mcp — MCP server for video intelligence
• content-factory-mcp — MCP server for content-factory

⭐ Love it? Leave a Review

Your rating helps professionals discover this actor. Rate it here.