List AI Agents

{
  "data": [
    {
      "ai_agent_id": "<string>",
      "agent_name": "<string>",
      "llm": {
        "llm_id": "<string>",
        "llm_type": "<string>",
        "model_provider": "openai",
        "model_name": "<string>",
        "system_prompt": "<string>",
        "model_temperature": 0,
        "llm_name": "<string>",
        "llm_description": "<string>",
        "base_url": "<string>",
        "api_key": "<string>",
        "max_tokens": 123,
        "required_dynamic_data": [
          "<string>"
        ],
        "tools": [
          {}
        ]
      },
      "stt": {
        "provider": "<string>",
        "model": "nova-2-general"
      },
      "tts": {
        "provider": "<string>",
        "voice_id": "<string>",
        "voice_name": "<string>",
        "model_name": "eleven_turbo_v2_5",
        "voice_temperature": 0.2
      },
      "created_by_user_id": "<string>",
      "language_code": "en-US",
      "knowledge_base_id": "<string>",
      "enable_user_interruptions": true,
      "minimum_speech_duration_for_interruptions": 0.5,
      "minimum_words_before_interruption": 0,
      "wait_time_before_detecting_end_of_speech": 0.5,
      "ambient_sound": "none",
      "ambient_sound_volume": 1,
      "webhook_url": "<string>",
      "end_call_after_silence_seconds": 10,
      "max_call_duration_seconds": 1800,
      "welcome_message": "<string>",
      "voicemail_detection_timeout_seconds": 90,
      "dynamic_data_config": [
        {
          "url": "<string>",
          "method": "<string>",
          "timeout": 123,
          "headers": {},
          "body": {},
          "query": {},
          "cache": true,
          "response_data": [
            {
              "name": "<string>",
              "data": "<string>",
              "context": "<string>"
            }
          ]
        }
      ],
      "post_call_analysis": [
        {
          "type": "<string>",
          "name": "<string>",
          "description": "<string>",
          "system_prompt": "<string>",
          "examples": [
            "<string>"
          ]
        }
      ]
    }
  ],
  "next_page_token": "<string>"
}

GET

ai-agents

{
  "data": [
    {
      "ai_agent_id": "<string>",
      "agent_name": "<string>",
      "llm": {
        "llm_id": "<string>",
        "llm_type": "<string>",
        "model_provider": "openai",
        "model_name": "<string>",
        "system_prompt": "<string>",
        "model_temperature": 0,
        "llm_name": "<string>",
        "llm_description": "<string>",
        "base_url": "<string>",
        "api_key": "<string>",
        "max_tokens": 123,
        "required_dynamic_data": [
          "<string>"
        ],
        "tools": [
          {}
        ]
      },
      "stt": {
        "provider": "<string>",
        "model": "nova-2-general"
      },
      "tts": {
        "provider": "<string>",
        "voice_id": "<string>",
        "voice_name": "<string>",
        "model_name": "eleven_turbo_v2_5",
        "voice_temperature": 0.2
      },
      "created_by_user_id": "<string>",
      "language_code": "en-US",
      "knowledge_base_id": "<string>",
      "enable_user_interruptions": true,
      "minimum_speech_duration_for_interruptions": 0.5,
      "minimum_words_before_interruption": 0,
      "wait_time_before_detecting_end_of_speech": 0.5,
      "ambient_sound": "none",
      "ambient_sound_volume": 1,
      "webhook_url": "<string>",
      "end_call_after_silence_seconds": 10,
      "max_call_duration_seconds": 1800,
      "welcome_message": "<string>",
      "voicemail_detection_timeout_seconds": 90,
      "dynamic_data_config": [
        {
          "url": "<string>",
          "method": "<string>",
          "timeout": 123,
          "headers": {},
          "body": {},
          "query": {},
          "cache": true,
          "response_data": [
            {
              "name": "<string>",
              "data": "<string>",
              "context": "<string>"
            }
          ]
        }
      ],
      "post_call_analysis": [
        {
          "type": "<string>",
          "name": "<string>",
          "description": "<string>",
          "system_prompt": "<string>",
          "examples": [
            "<string>"
          ]
        }
      ]
    }
  ],
  "next_page_token": "<string>"
}

Query Parameters

page_size

integer

default:20

Required range: 1 <= x <= 100

page_token

string

Response

Successful Response

data

AIAgentResponse · object[]

List of AI agents matching the query criteria

Show child attributes

data.ai_agent_id

string

required

Unique identifier for the AI agent

data.agent_name

string

required

Name of the AI agent

data.llm

SimplePiaLLMResponse · object

required

Language model configuration for the AI agent

SimplePiaLLMResponse
AgenticPiaLLMResponse
CustomPiaLLMResponse

Show child attributes

data.llm.llm_id

string

required

Unique identifier for the Language Learning Model (LLM)

data.llm.llm_type

string

required

Indicates this is a simple LLM type that uses standard model providers

Allowed value: "simple"

data.llm.model_provider

enum<string>

required

The provider of the language model - OpenAI, Anthropic, verbex, or OpenAI Compatible

Available options:

openai,

anthropic,

verbex,

openai_compatible

data.llm.model_name

string

required

Name of the specific model from the provider (e.g. 'gpt-4', 'claude-2')

data.llm.system_prompt

string

required

The base prompt that defines the LLM's behavior, role and operating parameters

data.llm.model_temperature

number

default:0

Controls randomness in model outputs - 0 is focused/deterministic, 1 is more creative/random

Required range: 0 <= x <= 1

data.llm.llm_name

string | null

Name of the LLM to use

data.llm.llm_description

string | null

Description of the LLM to use

data.llm.base_url

string | null

Base URL for the LLM API endpoint

data.llm.api_key

string | null

API key for authentication with the LLM service

data.llm.max_tokens

integer | null

Maximum number of tokens allowed in the response

data.llm.required_dynamic_data

string[] | null

List of dynamic data fields that must be provided to this LLM during operation

data.llm.tools

Tools · object[] | null

List of tools/functions available to the LLM for external interactions and API calls

data.stt

DeepgramSTTResponse · object

required

Speech-to-text configuration for the AI agent

DeepgramSTTResponse
GoogleSTTResponse
PiaSTTResponse

Show child attributes

data.stt.provider

string

required

Indicates Deepgram is being used as the STT provider

Allowed value: "deepgram"

data.stt.model

enum<string>

required

Specific Deepgram model being used for speech recognition, each optimized for different use cases

Available options:

nova-2-general,

nova-2-phonecall,

nova-meeting,

nova-2-meeting,

nova-2-finance,

nova-2-conversationalai,

nova-2-voicemail,

nova-2-video,

nova-2-medical,

nova-2-drivethru,

nova-2-automotive,

enhanced-general,

enhanced-meeting,

enhanced-phonecall,

enhanced-finance,

base,

meeting,

phonecall,

finance,

conversationalai,

voicemail,

video,

whisper-tiny,

whisper-base,

whisper-small,

whisper-medium,

whisper-large

data.tts

ElevenLabsTTSResponse · object

required

Text-to-speech configuration for the AI agent

ElevenLabsTTSResponse
GoogleTTSResponse
AzureTTSResponse
CartesiaTTSResponse
PiaTTSResponse

Show child attributes

data.tts.provider

string

required

Indicates ElevenLabs is being used as the TTS provider

Allowed value: "elevenlabs"

data.tts.voice_id

string

required

Unique identifier for the selected ElevenLabs voice

data.tts.voice_name

string | null

required

Human-readable name of the selected voice

data.tts.model_name

enum<string> | null

Specific ElevenLabs model version being used for voice synthesis

Available options:

eleven_turbo_v2_5,

eleven_turbo_v2,

eleven_multilingual_v2,

eleven_monolingual_v1

data.tts.voice_temperature

number | null

default:0.2

Controls variation in voice output - higher values increase variability

Required range: 0 <= x <= 1

data.created_by_user_id

string

required

ID of the user who created this AI agent

data.language_code

string

default:en-US

Language code for the AI agent in BCP-47 format

data.knowledge_base_id

string | null

ID of the associated knowledge base, if any

data.enable_user_interruptions

boolean

default:true

Whether to allow users to interrupt the AI agent while speaking

data.minimum_speech_duration_for_interruptions

number

default:0.5

Minimum duration of speech in seconds before interruptions are allowed

Required range: 0 <= x <= 15

data.minimum_words_before_interruption

integer

default:0

Minimum number of words that must be spoken before interruption is allowed

Required range: 0 <= x <= 5

data.wait_time_before_detecting_end_of_speech

number

default:0.5

Time in seconds to wait before considering speech has ended

Required range: 0 <= x <= 15

data.ambient_sound

enum<string>

default:none

Type of ambient background sound to use during calls

Available options:

office,

cafe,

restaurant,

park,

street,

home,

library,

airport,

train_station,

beach,

none

data.ambient_sound_volume

number

default:1

Volume level for ambient sound, from 0 (muted) to 2 (loud)

Required range: 0 <= x <= 2

data.webhook_url

string | null

URL to send webhook notifications about call events

data.end_call_after_silence_seconds

number

default:10

Number of seconds of silence before automatically ending the call

Required range: 10 <= x <= 30

data.max_call_duration_seconds

number

default:1800

Maximum duration of a call in seconds

Required range: 30 <= x <= 3600

data.welcome_message

string | null

Custom welcome message to play at the start of calls

data.voicemail_detection_timeout_seconds

number

default:90

Time in seconds to wait for voicemail detection

Required range: x >= 0

data.dynamic_data_config

DynamicDataConfigItemResponse · object[] | null

Configuration for dynamic data sources that can be used during calls

Show child attributes

data.dynamic_data_config.url

string

required

Endpoint URL for retrieving dynamic data

data.dynamic_data_config.method

string

required

HTTP method to use when calling the endpoint (GET, POST, etc)

data.dynamic_data_config.timeout

integer

required

Maximum time in seconds to wait for the endpoint response

data.dynamic_data_config.headers

Headers · object

required

HTTP headers to include in the request

Show child attributes

data.dynamic_data_config.headers.{key}

string

data.dynamic_data_config.body

Body · object

required

Request body data to send to the endpoint

data.dynamic_data_config.query

Query · object

required

URL query parameters to include in the request

Show child attributes

data.dynamic_data_config.query.{key}

string

data.dynamic_data_config.cache

boolean

required

Whether to cache the response data for subsequent use

data.dynamic_data_config.response_data

DynamicDataResponseConfigItemResponse · object[]

required

Configuration for parsing and using the endpoint response data

Show child attributes

data.dynamic_data_config.response_data.name

string

required

Identifier for this dynamic data field

data.dynamic_data_config.response_data.data

string

required

The actual data value retrieved from the external source

data.dynamic_data_config.response_data.context

string

required

Additional context or metadata about this data field

data.post_call_analysis

(StringPostCallAnalysisItemResponse · object | EnumPostCallAnalysisItemResponse · object | BooleanPostCallAnalysisItemResponse · object | NumberPostCallAnalysisItemResponse · object)[] | null

Configuration for analysis items to be processed after calls

StringPostCallAnalysisItemResponse
EnumPostCallAnalysisItemResponse
BooleanPostCallAnalysisItemResponse
NumberPostCallAnalysisItemResponse

Show child attributes

data.post_call_analysis.type

string

required

Indicates this analysis item returns a text string

Allowed value: "string"

data.post_call_analysis.name

string

required

Identifier for this analysis item

data.post_call_analysis.description

string

required

Detailed description of what this analysis item measures or determines

data.post_call_analysis.system_prompt

string

required

Prompt used to guide the AI in performing this analysis

data.post_call_analysis.examples

string[] | null

Example responses to guide the analysis

next_page_token

string | null

Token to retrieve the next page of results. Null if there are no more results

Getting an API Key Create AI Agent

⌘I

API Reference

AI Agents v2

Built-in Tools

Custom Tools

Calls

Post-call Analysis

Phone Numbers

Knowledge Bases v2

Prompt Generation

Public Sharing

API Keys

Query Parameters

Response