Gladia (Speech AI)

Gladia (Speech AI) MCP Connector for Claude

A+

Transcribe, translate, and analyze audio with Gladia's high-speed Speech AI — support for pre-recorded files and live streaming.

6 tools Official Updated Jun 28, 2026 Official Vinkius Partner

Connect Gladia to your AI agent to unlock enterprise-grade speech-to-text capabilities. Process audio files or live streams with advanced features like speaker diarization, multi-language translation, and automated summarization.

What you can do

  • Audio Processing — Upload local files to generate secure URLs for immediate transcription processing.
  • Advanced Transcription — Initiate jobs with speaker diarization (who said what), summarization, and translation across 100+ languages.
  • Audio-to-LLM — Apply custom LLM prompts directly to your audio data to extract specific insights or structured data.
  • Live Streaming — Initialize secure WebSocket sessions for real-time transcription of meetings or broadcasts.
  • Job Management — List, retrieve, and manage your transcription history and results directly through conversation.

How it works

  1. Subscribe to this server
  2. Enter your Gladia API Key
  3. Start transcribing audio files or live streams from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • Developers — Integrate speech-to-text workflows into apps without managing complex API calls manually.
  • Content Creators — Quickly generate transcripts, summaries, and translations for podcasts or videos.
  • Business Teams — Analyze meeting recordings to extract action items and speaker insights using natural language.
speech-to-texttranscriptionaudio-analysisspeaker-diarizationtranslationnatural-language-processing

6 tools expose this connector's capabilities to your AI agent.

delete_transcription

Delete a transcription job

upload_audio_file

Upload an audio file to Gladia

get_transcription

Get status and results of a transcription job

list_transcriptions

List pre-recorded transcriptions

init_live_session

Initiate a live transcription session

init_transcription

Start a pre-recorded transcription job

See how to talk to your AI agent using Gladia (Speech AI).

List my 5 most recent transcription jobs.

I've retrieved your recent jobs. You have 5 tasks: 'Meeting_Notes.mp3' (Done), 'Interview_01.wav' (Done), and 3 others. Would you like the results for any of these?

Start a transcription for this audio URL with summarization enabled: https://example.com/audio.mp3

Transcription job initiated! The Job ID is `job_12345`. I've enabled summarization as requested. I'll monitor the status for you.

I need a WebSocket URL to start a live transcription session in 16000Hz.

I've generated a live session. Here is your secure WebSocket URL: `wss://api.gladia.io/v2/live/...`. The sample rate is set to 16000Hz.

Use the `get_transcription` tool with the Job ID. It will return the current status (queued, processing, done, or error) and the results if completed.

Related Connectors