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

Q: How do I index audio files with Gladia (Speech AI) and LlamaIndex?

First, upload the audio using uploadaudiofile. Then, run inittranscription and feed the output of gettranscription directly into your LlamaIndex vector store.

Q: Can I search past transcriptions in LlamaIndex using this MCP Server?

Yes. Use listtranscriptions to retrieve your job history. Your LlamaIndex agent can then query specific records and index them for semantic search.

Q: How does Gladia (Speech AI) handle live audio streaming inside LlamaIndex?

You initiate a live connection using initlivesession. The tool returns WebSocket details, allowing your LlamaIndex pipeline to process live audio chunks as they arrive.

Q: How do I delete old audio data from the server?

Call deletetranscription with the target job ID. This removes the audio data from Gladia's servers, keeping your storage footprints clean.

Convert audio files into searchable vector indexes using LlamaIndex and this Gladia Speech AI MCP Server.

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 LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index speech output into LlamaIndex vector stores

`get_transcription` retrieves the raw text and metadata from your completed audio jobs. LlamaIndex takes this text and converts it into searchable vector embeddings immediately. This turns Gladia's spoken conversations into queryable LlamaIndex knowledge. You can search past meetings transcribed by Gladia using LlamaIndex semantic search instead of scrolling through raw audio files.

Feed audio files directly to LlamaIndex pipelines

`upload_audio_file` sends your local recordings straight to Gladia's processing pipeline. This MCP tool acts as the bridge, ensuring your local files are uploaded and ready for index ingestion. Your RAG pipeline uses the resulting file path to trigger `init_transcription`. This starts Gladia's speech-to-text engine and feeds the structured text back into your LlamaIndex document index.

Track and list historical audio data

`list_transcriptions` fetches the index of all past audio processing jobs. Your LlamaIndex agent queries this list to identify which files have already been indexed. This prevents LlamaIndex from indexing the same Gladia audio twice. If a file is missing, the LlamaIndex agent triggers `init_transcription` to process it, keeping your knowledge base current.

Setup guide

Set up Gladia (Speech AI) MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Gladia (Speech AI) MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Gladia (Speech AI) tools.",
)
response = await agent.run("List recent Gladia (Speech AI) data")

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 LlamaIndex

First, upload the audio using `upload_audio_file`. Then, run `init_transcription` and feed the output of `get_transcription` directly into your LlamaIndex vector store.

Yes. Use `list_transcriptions` to retrieve your job history. Your LlamaIndex agent can then query specific records and index them for semantic search.

You initiate a live connection using `init_live_session`. The tool returns WebSocket details, allowing your LlamaIndex pipeline to process live audio chunks as they arrive.

Call `delete_transcription` with the target job ID. This removes the audio data from Gladia's servers, keeping your storage footprints clean.

Audio payloads and transcription metadata pass through Vinkius's ephemeral, zero-trust infrastructure. Your LlamaIndex client connects via a single secure MCP token, meaning your credentials never leak and files are destroyed after processing.

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