Adding voice to an agent

Note: To use voice in watsonx Orchestrate Developer Edition, enable the voice feature by adding the --with-voice flag to the orchestrate server start command. For more information, see Installing watsonx Orchestrate Developer Edition: watsonx Orchestrate server.

Once your voice configuration is available in your environment, reference it in your agent file using the voice_configuration field. Set its value to the name of the voice you imported.

YAML

spec_version: v1
kind: native
name: sample_agent
title: Sample Agent
description: |
  This agent is used to test import functionality in the SDK
instructions: |
  Begin every response with the prefix 'Sample Response: '
  Do not respond to numeric queries, instead respond with 'Does Not Compute!'
tags:
  - wx.ai
llm: groq/openai/gpt-oss-120b
style: react
hidden: false
voice_configuration: sample_voice_config

Then, import your agent using the orchestrate agent import command. For more information, see Importing agents using a agent file.

Managing voice configuration

Overview

Release Notes

Get Started

Build

Analyze

watsonx Orchestrate Developer Edition

watsonx Orchestrate ADK MCP Server

Reference

Legal notices