Create Agent

curl --request POST \
  --url https://api.eqho.ai/v1/agents \
  --header 'Content-Type: application/json' \
  --header 'X-API-KEY: <api-key>' \
  --data '{
  "name": "Liz",
  "description": "An agent that the sales team is testing.",
  "language": "EN",
  "avatar": "MAN",
  "voice_audio_id": "<string>",
  "role_ids": [
    "<string>"
  ],
  "action_ids": [
    "<string>"
  ],
  "action_flows": [
    [
      "<string>"
    ]
  ],
  "script_ids": [
    "<string>"
  ],
  "data_store_ids": [
    "<string>"
  ],
  "personality": {
    "adherence": 0.75,
    "empathy": 0.5,
    "humor": 0.25
  },
  "disable_greeting": true,
  "system_prompt": null,
  "conversation_flow_id": "<string>",
  "end_conversation_on_goodbye": true,
  "enable_user_idle_timeout": true,
  "enable_parallel_tool_calls": true,
  "ai_settings": {
    "ai_model": "<string>",
    "frequency_penalty": 123,
    "max_tokens": 123,
    "presence_penalty": 123,
    "temperature": 123
  },
  "greeting_type_inbound": "static",
  "greeting_type_outbound": "static",
  "structured_greetings": [
    {
      "call_type": "inbound",
      "greeting_type": "static",
      "text": "Hello! Welcome to our service. How can I assist you today?"
    }
  ],
  "tts_settings": {
    "utterance_end_ms": "1000",
    "smart_format": false,
    "profanity_filter": false,
    "punctuate": true,
    "numerals": false,
    "keywords": [
      "<string>"
    ],
    "diarize": false,
    "dictation": false,
    "endpointing": "10",
    "filler_words": false
  },
  "smart_turn_detection": true,
  "voice_settings": null,
  "feature_flags": null
}'

{
  "avatar": "WOMAN",
  "data_store_ids": [
    "65a9758171f55af646a19890"
  ],
  "description": "An agent that the sales team is testing.",
  "greeting_type_inbound": "static",
  "greeting_type_outbound": "ai",
  "name": "Liz",
  "personality": {
    "adherence": 0.75,
    "empathy": 0.5,
    "humor": 0.25
  },
  "role_ids": [
    "65a9758171f55af646a19890"
  ],
  "script_id": "65a9758171f55af646a19890",
  "structured_greetings": [
    {
      "call_type": "inbound",
      "greeting_type": "static",
      "text": "Hello! Welcome to our service. How can I assist you today?"
    },
    {
      "call_type": "outbound",
      "communication_tone": "friendly",
      "greeting_length": "short",
      "greeting_type": "ai",
      "mention_ids": [
        "673e488ce7d69488a458cf3e",
        "973e488ce7d69488a458cf3e"
      ]
    }
  ],
  "voice_audio_id": "Y94lg6clSowTJ0jJOlyc"
}

POST

agents

Create Agent

curl --request POST \
  --url https://api.eqho.ai/v1/agents \
  --header 'Content-Type: application/json' \
  --header 'X-API-KEY: <api-key>' \
  --data '{
  "name": "Liz",
  "description": "An agent that the sales team is testing.",
  "language": "EN",
  "avatar": "MAN",
  "voice_audio_id": "<string>",
  "role_ids": [
    "<string>"
  ],
  "action_ids": [
    "<string>"
  ],
  "action_flows": [
    [
      "<string>"
    ]
  ],
  "script_ids": [
    "<string>"
  ],
  "data_store_ids": [
    "<string>"
  ],
  "personality": {
    "adherence": 0.75,
    "empathy": 0.5,
    "humor": 0.25
  },
  "disable_greeting": true,
  "system_prompt": null,
  "conversation_flow_id": "<string>",
  "end_conversation_on_goodbye": true,
  "enable_user_idle_timeout": true,
  "enable_parallel_tool_calls": true,
  "ai_settings": {
    "ai_model": "<string>",
    "frequency_penalty": 123,
    "max_tokens": 123,
    "presence_penalty": 123,
    "temperature": 123
  },
  "greeting_type_inbound": "static",
  "greeting_type_outbound": "static",
  "structured_greetings": [
    {
      "call_type": "inbound",
      "greeting_type": "static",
      "text": "Hello! Welcome to our service. How can I assist you today?"
    }
  ],
  "tts_settings": {
    "utterance_end_ms": "1000",
    "smart_format": false,
    "profanity_filter": false,
    "punctuate": true,
    "numerals": false,
    "keywords": [
      "<string>"
    ],
    "diarize": false,
    "dictation": false,
    "endpointing": "10",
    "filler_words": false
  },
  "smart_turn_detection": true,
  "voice_settings": null,
  "feature_flags": null
}'

{
  "avatar": "WOMAN",
  "data_store_ids": [
    "65a9758171f55af646a19890"
  ],
  "description": "An agent that the sales team is testing.",
  "greeting_type_inbound": "static",
  "greeting_type_outbound": "ai",
  "name": "Liz",
  "personality": {
    "adherence": 0.75,
    "empathy": 0.5,
    "humor": 0.25
  },
  "role_ids": [
    "65a9758171f55af646a19890"
  ],
  "script_id": "65a9758171f55af646a19890",
  "structured_greetings": [
    {
      "call_type": "inbound",
      "greeting_type": "static",
      "text": "Hello! Welcome to our service. How can I assist you today?"
    },
    {
      "call_type": "outbound",
      "communication_tone": "friendly",
      "greeting_length": "short",
      "greeting_type": "ai",
      "mention_ids": [
        "673e488ce7d69488a458cf3e",
        "973e488ce7d69488a458cf3e"
      ]
    }
  ],
  "voice_audio_id": "Y94lg6clSowTJ0jJOlyc"
}

Authorizations

X-API-KEY

string

header

required

Body

application/json

name

string

required

The name of the agent. Agent may use this name in the conversation.

Examples:

"Liz"

voice_audio_id

string

required

Identifier of the voice that will be used by Agent, you can query them using GET /v1/voices

role_ids

string[]

required

The roles your agent will have, you can query them using GET /v1/roles. When multiple roles are provided, each role will be added to the LLM prompt using Eqho's proprietary prompt structure.

personality

object

required

Agent's personality settings.

Show child attributes

description

string | null

The description of the agent. Only used for your own reference.

Examples:

"An agent that the sales team is testing."

language

enum<string>

The langauge Agent speaks in.

Available options:

multi,

bg,

ca,

cs,

da,

da-DK,

de,

de-CH,

el,

en,

en-US,

en-AU,

en-GB,

en-NZ,

en-IN,

es,

et,

fi,

fr,

fr-CA,

hi,

hu,

id,

it,

ja,

lt,

lv,

no,

nl,

pl,

pt,

pt-BR,

pt-PT,

ro,

ru,

sk,

th,

th-TH,

tr,

uk,

vi,

zh,

zh-CN,

zh-TW,

zh-HK

avatar

enum<string> | null

The avatar of the agent used in the UI and widget.

Available options:

MAN,

WOMAN

action_ids

string[] | null

The list of Action IDs Agent will have access to, you can query them using GET /v1/actions.

action_flows

string[][] | null

Action flows allow you to define sequences of actions that an agent must follow in a strict, ordered manner.

Each element in the action_flows array is a list of action ids. Within each list, the agent executes the actions in the order they are listed. Each action on the list should be an action ID listed in action_ids.

If not provided, the agent can execute actions from action_ids in any order.

Use case: appointment booking, where the agent must first check availability, create a calendar entry, and finally confirm the booking with the user.

script_ids

string[] | null

A list of script IDs that the agent will have access to; you can query them using GET /v1/scripts.

Assigning multiple scripts to an Agent is usually not recommended. When multiple scripts are provided, each script will be added to the LLM prompt using Eqho's proprietary prompt structure.

data_store_ids

string[] | null

A list of Knowledge Base IDs that the agent will have access to, you can query them using GET /v1/data-stores. Agent can use content from provided Knowledge Base to enrich responses.

disable_greeting

boolean | null

deprecated

Deprecated. This field is no longer recommended for use and will be removed in future versions. Use greeting_type with value 'none' instead.

system_prompt

object | null

Advanced setting to override the Eqho default system prompt. In most cases, you should not need to use this.

Show child attributes

Examples:

null

conversation_flow_id

string | null

The conversation flow your agent should follow. If not provided, it is referred as Single Prompt agent. When provided, agent is referred as Conversation Flow agent. ID should be a valid Conversation Flows Id. Conversation flow agent allows you to create multiple nodes to handle different scenarios in the conversation.

end_conversation_on_goodbye

boolean | null

If true, the agent will end the conversation if the user or agent says 'goodbye' or a similar phrase.

enable_user_idle_timeout

boolean | null

default:false

If true, the agent will end the conversation if the user is idle (not talking, not typing) for a certain period of time. The agent will ask the user if they are still there up to 3 times before ending the conversation.

Amount of time agent waits for user to respond is set by Eqho and can not be changed.

enable_parallel_tool_calls

boolean | null

default:false

If true, the agent can execute multiple tools at the same time.

ai_settings

object | null

Settings for the Agent's LLM model.

Show child attributes

greeting_type_inbound

enum<string> | null

default:static

Available options:

static,

ai,

none

greeting_type_outbound

enum<string> | null

default:static

Available options:

static,

ai,

none

structured_greetings

StructuredGreetingInputModel · object[] | null

Show child attributes

tts_settings

object | null

Show child attributes

smart_turn_detection

boolean | null

default:false

If true, the agent will use ML to detect turns changes in the conversation.

voice_settings

object | null

Advanced setting to override the Eqho default voice settings. In most cases, you should not need to use this. If not provided, the agent will use the default Eqho voice settings.

Show child attributes

Examples:

null

feature_flags

string[] | null

Examples:

null

Response

Successful Response

Container for a single agent record.

name

string | null

language

enum<string>

Language codes that are supported by Eqho Agents.

Available options:

multi,

bg,

ca,

cs,

da,

da-DK,

de,

de-CH,

el,

en,

en-US,

en-AU,

en-GB,

en-NZ,

en-IN,

es,

et,

fi,

fr,

fr-CA,

hi,

hu,

id,

it,

ja,

lt,

lv,

no,

nl,

pl,

pt,

pt-BR,

pt-PT,

ro,

ru,

sk,

th,

th-TH,

tr,

uk,

vi,

zh,

zh-CN,

zh-TW,

zh-HK

description

string | null

avatar

string | null

voice_audio_id

string | null

role_ids

string[] | null

action_ids

string[] | null

action_flows

string[][] | null

script_id

string | null

deprecated

Deprecated. Use script_ids instead.

script_ids

string[] | null

data_store_ids

string[] | null

personality

object | null

Describes the personality of an agent. These values will be injected into the agent's prompt. LLM might use them to adjust the agent's responses.

Show child attributes

disable_greeting

boolean | null

deprecated

Deprecated. This field is no longer recommended for use and will be removed in future versions. Use greeting_type with value 'none' instead.

rag_collection

string | null

system_prompt

object | null

Show child attributes

conversation_flow_id

string | null

enable_parallel_tool_calls

boolean | null

default:false

end_conversation_on_goodbye

boolean | null

enable_user_idle_timeout

boolean | null

default:false

ai_settings

object | null

Settings for the Agent's LLM model.

Show child attributes

tts_settings

object | null

Show child attributes

voice_settings

object | null

Show child attributes

greeting_type_inbound

enum<string> | null

default:static

Available options:

static,

ai,

none

greeting_type_outbound

enum<string> | null

default:static

Available options:

static,

ai,

none

structured_greetings

StructuredGreetingModel · object[] | null

Show child attributes

greetings

string[] | null

deprecated

Deprecated. Use structured_greetings instead.

alias

string | null

smart_turn_detection

boolean | null

default:false

feature_flags

string[] | null

Examples:

"CHAT_HISTORY"

"VAPI_ENABLED"

"CONVERSATION_STREAM"

_id

string | null

account_id

string | null

enabled

boolean | null

default:true

history

object

Show child attributes

Get Agents Get Agent By Id

API Reference

Endpoints

Create Agent

Authorizations

Body

Response