• TEXT
  • SUBTITLES
  • HUMAN
  • STATUS

How to transcribe audio to text with your AI

Connect Speechmatics to your AI client once. After that, you just send audio files to get text or subtitles back.

Ask AI about this page

Short answer

How can I turn audio into text using my AI?

You tell your AI to send an audio file to Speechmatics. The AI handles the transcription and brings the text or subtitle files back to you. You'll see exactly how it works below.

Transcription outcomes

What you get back

The AI delivers these specific files once the processing finishes.

TEXT

Plain text transcripts

The AI pulls the raw text from the audio. You get a clean transcript you can read or summarize.

SUBTITLES

Subtitle files

The AI generates timed subtitle files. You can use these in video editing software.

HUMAN

Manual review

The AI provides the draft, but you're responsible for checking the accuracy and making final edits.

STATUS

Job tracking

The AI monitors the progress of your request so you know when the files are ready.

The workflow

What your AI does when the audio arrives.

Your AI manages the entire lifecycle of the transcription request.

  1. Start the job

    The AI sends your audio file to the Speechmatics engine to begin processing.

    create_job

  2. Check progress

    The AI periodically checks to see if the transcription is finished.

    get_job

  3. Retrieve text

    Once the job is complete, the AI pulls the transcript or subtitle data.

    get_transcript

  4. Deliver files

    The AI brings the final text or subtitle content directly into your chat.

    get_transcript

Try it

Copy these to start.

Paste these into your chat to begin transcribing.

Starting points

Swap out the file names in these examples for your own audio files.

Speechmatics Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_FRLuaMwEkSVVnPCae4yQUSbZdPUlWPw9NvqN4KDY/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 — Speechmatics capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "speechmatics-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_FRLuaMwEkSVVnPCae4yQUSbZdPUlWPw9NvqN4KDY/mcp"
    }
  }
}
Copy into chat04

  • Transcribe the audio file 'meeting_recording.mp3' for me.

  • Create a subtitle file from 'interview_audio.wav'.

  • Check the status of my transcription job for 'lecture_01.m4a'.

  • Get the text transcript for 'podcast_episode.mp3'.

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

Start here

Connect Speechmatics once, then ask.

Connect your account once to give your AI access. Your login stays encrypted on our side, and you can find the full tool list on the Connector page.

Connect Speechmatics to your AI

FAQ

How the task behaves

  • 01

    Can the AI edit the transcript?

    No. The AI only retrieves the text produced by Speechmatics. You'll need to make any edits yourself.

  • 02

    Can the AI delete my audio files?

    No. The tools only allow the AI to send files for transcription and retrieve the resulting text.

  • 03

    How do I know when it's done?

    The AI checks the job status and will tell you in the chat when the files are ready.

  • 04

    Can the AI create video files?

    No. It only provides text transcripts or subtitle files.

  • 05

    Does the AI handle the file uploading?

    Yes. The AI uses the provided tools to send your audio data to the engine.

  • More questions about Speechmatics? The Connector page answers them. See everything the Speechmatics Connector can do

Connect Speechmatics to Claude, Cursor, ChatGPT & more