How to Use the Gladia (Speech AI) MCP in Windsurf

Q: Can I run real-time audio streams with Gladia (Speech AI) in Windsurf?

Yes, Cascade connects to WebSockets using initlivesession to handle live audio feeds. This allows the agent to process ongoing speech and write the text straight to your workspace.

Q: Do I need to manually configure API keys for Gladia (Speech AI) in Windsurf?

No, you set your Gladia token once in the mcpconfig.json file inside Windsurf. Cascade handles all authentication behind the scenes for every tool execution.

Q: How does Cascade track the progress of long audio files?

Cascade triggers inittranscription and then periodically runs gettranscription to check the status. It waits until the job completes before writing the final markdown file to your project.

Feed audio files directly to Cascade in Windsurf to transcribe, translate, and analyze audio files dynamically.

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 Windsurf

Create your Vinkius account to connect Gladia (Speech AI) to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automating Audio Pipeline Tasks via Windsurf

`upload_audio_file` sends raw audio to Gladia, letting Cascade process audio files directly from your workspace using this MCP server. This tool accepts your local media and transfers it to the secure cloud environment instantly. Cascade chains this file transfer with `init_transcription` to kick off the speech-to-text pipeline without asking you for manual confirmation. You get your raw text output in seconds rather than waiting on manual API scripts.

Real-Time Speech Streaming in Cascade

`init_live_session` spins up a WebSocket connection to stream live audio directly into your Windsurf workspace. Cascade uses this connection to capture active conversations or live audio feeds as they happen. You receive live text tokens back, which Cascade can immediately write into your open editors. This removes the manual copy-pasting step from your meeting summary workflows.

Managing Transcription History Dynamically

`list_transcriptions` pulls your entire history of audio jobs directly into the Windsurf context window. Cascade checks this index to find specific past files without forcing you to log into a separate web dashboard. If a run is no longer needed, Cascade runs `delete_transcription` to purge the data and keep your billing clean. This MCP integration automatically cross-references your current workspace files to decide what to prune.

Setup guide

Set up Gladia (Speech AI) MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Gladia (Speech AI) payment history." If connected, Cascade will call the Gladia (Speech AI) tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "gladia-speech-ai-mcp": {
      "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 Windsurf

Cascade uses the Gladia (Speech AI) MCP server to read, process, and transcribe audio files directly within your IDE. It runs tasks like file uploads and real-time session management autonomously.

Yes, Cascade connects to WebSockets using `init_live_session` to handle live audio feeds. This allows the agent to process ongoing speech and write the text straight to your workspace.

No, you set your Gladia token once in the `mcp_config.json` file inside Windsurf. Cascade handles all authentication behind the scenes for every tool execution.

Cascade triggers `init_transcription` and then periodically runs `get_transcription` to check the status. It waits until the job completes before writing the final markdown file to your project.

Your audio files go to Gladia's secure servers for processing, and you can run `delete_transcription` to remove them. Windsurf keeps all transcript data local to your workspace.

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