---
title: "Queue Voice Agent Test Run"
description: "Queue a test run of a voice agent's scripted test suite."
---

> Documentation Index
> Fetch the complete documentation index at: https://docs.speakai.co/llms.txt
> Use this file to discover all available pages before exploring further.

# Queue Voice Agent Test Run

`start_voice_test_run` is a tool in the Speak AI MCP server. Queue a test run of a
voice agent's scripted test suite.

## What does it do?

Queue a test run of a voice agent's scripted test suite. Creates a run record in
queued status and returns it; it does not place phone calls, start a conversation,
or use credits. Requires the OWNER or ADMIN role. Returns 404 if the agent or its
test suite does not exist, and 409 if the suite has no enabled scenarios or the
agent already has a queued, running, or paused run. The live execution engine is not
wired up yet: a run created here stays queued, scenarioResults stays empty, and
overallScore stays 0.

## Parameters

`start_voice_test_run` takes 1 parameter, all of them required.

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `agentId` | string | Yes | ID of the voice agent (from `list_voice_agents`) |

## Behaviour

The Speak AI MCP server publishes these behaviour hints for `start_voice_test_run`.

- Can change data in your workspace.
- Does not delete or overwrite existing data.
- Repeating an identical call can have an extra effect.
- Stays inside Speak AI. Does not reach other systems.

## Related

- [Voice agents](/mcp/tools/voice-agents/) lists the rest of the Voice agents
  category.
- [Tool reference](/mcp/tools/) lists every Speak AI MCP server tool.
- [MCP server](/mcp/) covers setup, supported clients, and what agents can do once
  connected.

Source: https://docs.speakai.co/mcp/tools/voice-agents/start_voice_test_run/index.mdx