• SPEAKER ID
  • TONE CHECK
  • TEXT DATA
  • HUMAN REVIEW

How to analyze meeting sentiment and speakers with your AI

Connect AssemblyAI to your AI client to turn raw audio into structured conversation data. Once connected, your agent handles the heavy lifting of transcription and emotional analysis.

Ask AI about this page

Short answer

How can I find out who said what and how they felt in a meeting?

Your AI uses AssemblyAI to transcribe the audio, identify individual speakers, and extract the emotional tone of the conversation. You'll get a clear breakdown of the dialogue and the sentiment behind the words.

Where every insight lands.

The outcomes of your analysis

The data your AI pulls from AssemblyAI feeds into these specific results.

SPEAKER ID

Who spoke when

The AI maps specific lines of text to individual participants. You'll see exactly which person drove which part of the conversation.

TONE CHECK

Emotional context

The agent identifies if the mood was positive, negative, or neutral. This helps you catch tension or excitement that text alone might miss.

TEXT DATA

Full conversation logs

The AI converts audio into a clean, searchable transcript. You can then ask your agent to summarize specific topics or decisions made.

HUMAN REVIEW

Manual verification

The AI provides the raw data and timestamps. You decide which specific emotional shifts or speaker errors need your personal attention.

The workflow

What your AI does when the audio arrives.

The AI moves through a sequence of data extraction steps to turn sound into intelligence.

  1. Convert audio to text

    The agent sends your audio file to be processed into a written format.

    transcribe_audio_url

  2. Identify participants

    The AI separates the transcript into distinct voices so you know who is talking.

    get_speakers

  3. Extract the transcript

    The agent pulls the full text of the conversation for your review or summarization.

    get_transcript

  4. Analyze the mood

    The AI scans the text to determine the emotional sentiment of the participants.

    get_sentiments

Try it

Copy these to start.

Use these prompts to trigger the analysis immediately.

Starting points

These are basic ways to start. Replace the bracketed info with your actual file links or meeting names.

AssemblyAI Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_IctBwuEI5fLw0DEGx6JV9ytMfgfL9zH337qQ7vjt/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — AssemblyAI capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "assemblyai-alternative-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_IctBwuEI5fLw0DEGx6JV9ytMfgfL9zH337qQ7vjt/mcp"
    }
  }
}
Copy into chat04

  • Transcribe this meeting recording and tell me who the main speakers were: [URL]

  • Analyze the sentiment of this audio file and let me know if the tone was positive or negative: [URL]

  • Get the transcript for the recording at [URL] and summarize the key decisions.

  • Who was the most frustrated speaker in this recording? [URL]

  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Start here

Connect AssemblyAI once, then ask.

Just link your account with one click. Your credentials stay encrypted, and you can start asking questions about your audio files right away.

Connect AssemblyAI to your AI

FAQ

How the analysis works

  • 01

    Can the AI edit the audio file?

    No. The AI only reads and analyzes the audio provided via the tools.

  • 02

    Does the AI automatically save the transcript to my computer?

    No. The AI retrieves the transcript for your chat session, but it does not write files to your local hard drive.

  • 03

    Can it identify people by name?

    The AI identifies different speakers, but it won't know their real-world names unless they say them during the recording.

  • 04

    Can the AI delete my recordings?

    No. This MCP only has tools to read and analyze data, not to delete or modify your files.

  • 05

    How does it know the sentiment?

    It uses the sentiment tool to scan the transcribed text for emotional cues and tone.

  • More questions about AssemblyAI? See everything the AssemblyAI Connector can do

Connect AssemblyAI to Claude, Cursor, ChatGPT & more