How to Use the Gladia (Speech AI) MCP in Claude Code

Q: Can I use Gladia (Speech AI) with Claude Code in CI/CD pipelines?

Yes, Claude Code runs headless and can trigger inittranscription during automated test runs. This lets you verify audio processing pipelines inside GitHub Actions or Docker containers.

Q: How do I configure Gladia (Speech AI) in Claude Code?

Run the claude mcp add command to register the MCP Server using HTTP or SSE transport. Claude Code will save the configuration to your /.claude.json file.

Q: Can Claude Code monitor long-running audio jobs?

Yes, the CLI agent uses gettranscription to poll the Gladia API status. It will block your terminal pipeline until the transcription changes from processing to completed.

Q: How does Gladia (Speech AI) handle large audio files via Claude Code MCP tools?

The agent executes uploadaudiofile to stream large media payloads directly to Gladia. Once uploaded, it initiates batch processing and returns the structured transcript to your shell.

Pipe audio files and manage live transcription sessions directly from your terminal using Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Gladia (Speech AI) MCP to Claude Code

Create your Vinkius account to connect Gladia (Speech AI) to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Gladia (Speech AI) with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Command Line Audio Ingestion via MCP Server

`upload_audio_file` pushes local audio files from your terminal directly to the Gladia Speech API using this MCP server. Your terminal agent handles the multipart upload instantly, removing the need for curl scripts. The agent then chains `init_transcription` to start the processing queue. You get a clean job ID piped directly to your standard output for downstream processing.

Terminal-Based Real-Time Speech Streaming

`init_live_session` starts a live WebSocket session directly from your CLI environment. Claude Code uses this tool to establish low-latency connections for real-time terminal captioning. You can pipe the live text output into other CLI utilities or save it directly to log files. This is ideal for headless environments where you need immediate speech processing.

Batch Transcription Management and Auditing

`list_transcriptions` pulls your historical transcription records directly into your terminal session. Claude Code parses this JSON payload to find specific job IDs or check processing statuses. To keep your remote storage clean, the terminal agent executes `delete_transcription` on expired jobs. This allows you to run automated cleanup cron jobs entirely through the CLI.

Setup guide

Set up Gladia (Speech AI) MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see gladia-speech-ai-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Gladia (Speech AI) transactions." It will automatically discover and invoke the available Gladia (Speech AI) tools.

Terminal

claude mcp add --transport http gladia-speech-ai-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Gladia (Speech AI) MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "gladia-speech-ai-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Gladia. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Gladia (Speech AI) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Gladia (Speech AI) MCP in Claude Code

Yes, Claude Code runs headless and can trigger `init_transcription` during automated test runs. This lets you verify audio processing pipelines inside GitHub Actions or Docker containers.

Run the `claude mcp add` command to register the MCP Server using HTTP or SSE transport. Claude Code will save the configuration to your `~/.claude.json` file.

Yes, the CLI agent uses `get_transcription` to poll the Gladia API status. It will block your terminal pipeline until the transcription changes from processing to completed.

The agent executes `upload_audio_file` to stream large media payloads directly to Gladia. Once uploaded, it initiates batch processing and returns the structured transcript to your shell.

Gladia stores your audio files temporarily to process them, while Claude Code keeps the text output in your local terminal buffer. You can permanently wipe any remote transcript from Gladia's servers by running `delete_transcription`.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript