ProjectsAgentsModelFactory.VoiceAgentDefinition Method

modelType

Nullable<VoiceModelType>

How the model backing this voice agent is served. Required with model for a model-backed voice agent and omitted when conversation_engine is provided. This is independent of the architecture (realtime or cascaded), which the service derives from the selected model.

model

String

The model to use for this agent. Required with model_type for a model-backed voice agent and omitted when conversation_engine is provided. The model must support realtime or cascaded voice.

conversationEngine

VoiceConversationEngine

The engine that owns conversation handling for this voice agent. Exactly one of this property and the model-backed configuration (model_type with model) must be provided. When this property is provided, model_type, model, instructions, tools, and tool_choice must be omitted, and greeting.tool_choice cannot be required, because the engine owns the conversation logic. The initial implementation supports a hosted-agent engine.

instructions

String

A system (or developer) message inserted into the model's context. Supports template substitution via structured_inputs, rendered per session before the live session starts.

greeting

VoiceAgentGreetingConfig

Optional session-start greeting. Template mode speaks exact rendered text; LLM-generated mode asks the session model to author the opening response and may use configured tools.

audio

VoiceAgentAudioConfig

The audio configuration, including input and output formats, voice, turn detection, noise reduction, and transcription. These values are session defaults; a client may override supported fields when connecting.

outputModalities

IEnumerable<VoiceOutputModality>

The output modalities the agent produces. Defaults to ["audio"]. animation and avatar are available when an avatar is configured.

maxOutputTokens

BinaryData

The maximum output-token count for one response.

include

IEnumerable<VoiceAgentSessionIncludeOption>

Additional fields to include in service outputs.

interimResponse

VoiceAgentInterimResponseConfig

Interim-response settings for latency and tool execution.

avatar

VoiceAgentAvatarConfig

Optional avatar configuration. These values are session defaults and may be overridden when connecting.

tools

IEnumerable<VoiceAgentTool>

The tools the voice agent may use. Supported tool kinds are function (executed by the client), mcp, system (service-managed session controls), and toolbox. Server-side tools such as web_search, azure_ai_search, and openapi are provided through a toolbox rather than declared directly.

toolChoice

BinaryData

How the model chooses tools for generated responses. none prevents tool calls, auto lets the model decide, required requires at least one tool call, and a specific function or MCP tool can be selected with an object. Defaults to auto.

parallelToolCalls

Nullable<Boolean>

Whether the model may call multiple tools in parallel.

structuredInputs

IDictionary<String,StructuredInputDefinition>

Set of structured inputs that participate in prompt template substitution, rendered per session before the live session starts.

subagentConfig

VoiceAgentSubagentConfig

Optional configuration for sibling Foundry text agents that this voice agent may consult as background specialists.

store

Nullable<Boolean>

Whether conversations with this agent are persisted. A single, all-or-nothing persistence switch that defaults to false (privacy-safe: off by default). When true, Foundry persists the full conversation — the transcript/event timeline and raw audio. When false, nothing is persisted and no conversation is surfaced. There is no separate audio-logging control; audio is persisted only as part of this switch. Latency/performance telemetry (e.g. time-to-first-audio, inter-token latency, interruption) is observability-only (customer trace / App Insights) and is not part of the persisted conversation content.