> ## Documentation Index
> Fetch the complete documentation index at: https://docs.cartesia.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Agent configuration
> Configure how an agent behaves, listens, speaks, and acts.
An agent's `config` controls its behavior, model, audio, and tools. Set it when you [create an agent](/api-reference/agents/create). To change it, send only the fields you want to update with [`PATCH /v1/agents/{agent_id}`](/api-reference/agents/update).
```json theme={null}
{
"name": "Acme Support",
"config": {
"instructions": "You are Acme's support agent. Help callers with orders and returns. Be warm and concise.",
"initial_message": "Hi, thanks for calling Acme. How can I help?",
"model": { "id": "gpt-5.4-mini" },
"language": { "primary": "en" },
"audio": {
"input": {
"noise_suppression": "auto",
"keyterms": ["Acme", "ProGrip"]
},
"output": {
"voice_id": "e07c00bc-4134-4eae-9ea4-1a55fb45746b",
"speed": 1.0
}
},
"tools": [{ "id": "agent_tool_5RkP2wZmQ8xTnLc4vB7dHy" }],
"system_tools": {
"end_call": {
"description": null,
"pre_tool_speech": "force"
}
}
}
}
```
## Instructions and greeting
Use `instructions` to define the agent's role, speaking style, objectives, and limits. A short structure makes the prompt easier to review and maintain:
```text theme={null}
# Identity and personality
You are Acme's friendly and concise support agent.
# Speaking rules
Use short sentences. Ask one question at a time.
# Objectives
Help callers check orders and start returns.
# Guardrails
Never invent order details. Ask for an order number before using the lookup tool.
```
`initial_message` is what the agent says when the call begins. Set it to `null` to wait for the caller to speak first.
## Model
`model.id` selects the LLM that generates the agent's responses. `model.temperature` and `model.max_output_tokens` tune its output. See [LLMs](/agents/models) for the available models and settings.
## Language
`language.primary` sets the language the agent listens and speaks in, as an ISO 639-1 code such as `en`, `es`, or `fr`. Set it to `null` to detect the caller's language automatically.
## Audio input
* `noise_suppression` controls cleanup of incoming audio. Use `auto` for most calls, `max` for noisy environments, or `off` to disable it.
* `keyterms` helps Ink recognize names and domain-specific phrases. See [Improve transcription with keyterms](/use-the-api/stt/keyterms). Keyterms affect recognition; a pronunciation dictionary changes how the agent speaks a word.
## Audio output
| Field | Description |
| ----------------------------- | ------------------------------------------------------------------------------------------------- |
| `voice_id` | Voice used for agent speech. Required. |
| `speed` | Speech speed from `0.6` to `1.5`. `null` uses the voice default. |
| `volume` | Speech volume from `0.5` to `2`. `null` uses the default. |
| `emotion` | Emotion supported by the selected voice, such as `calm`, `happy`, or `sad`. |
| `pronunciation_dictionary_id` | [Pronunciation dictionary](/api-reference/pronunciation-dicts/create) used when the agent speaks. |
| `background_sound` | Ambient audio with a `file_id` and volume from `0` to `2`. `null` disables it. |
## Tools
`tools` lists the shared webhook and client tools the agent can invoke, by ID. `system_tools` enables the built-in actions: ending the call, sending DTMF tones, and transferring to a phone number. See [Tools](/agents/tools) for how each kind works and how to configure it.
Every effective configuration change creates an immutable [version](/agents/versions).