Create Agent - eigi.ai Documentation

curl --request POST \
  --url https://api.eigi.ai/v1/public/agents \
  --header 'Content-Type: application/json' \
  --header 'X-API-Key: <api-key>' \
  --data '
{
  "agent_name": "Support Agent",
  "agent_type": "INBOUND",
  "agent_category": "Customer Service",
  "stt": {
    "provider_name": "DEEPGRAM",
    "model_name": "nova-2",
    "language": "en",
    "params": {}
  },
  "llm": {
    "provider_name": "OPENAI",
    "model_name": "gpt-4o",
    "params": {
      "temperature": 0.7
    }
  },
  "tts": {
    "provider_name": "CARTESIA",
    "model_name": "sonic-2",
    "language": "en",
    "voice_id": "a0e99841-438c-4a64-b679-ae501e7d6091",
    "params": {
      "speed": 1
    }
  },
  "prompt_content": "You are a helpful customer support agent.",
  "call_analysis_enabled": true,
  "call_analysis_prompt": {
    "prompt_name": "support_call_analysis",
    "custom_prompt": "Analyze the call outcome, customer sentiment, and follow-up actions."
  },
  "call_analysis_schema": {
    "call_outcome": {
      "type": "str"
    },
    "customer_sentiment": {
      "type": "str"
    },
    "follow_up_required": {
      "type": "bool"
    }
  },
  "first_message_prompt": "Hello! How can I help you today?",
  "tools": {
    "end_call": true,
    "transfer_call": {
      "transfer_phone_number": "+919876543210"
    }
  }
}
'

{
  "id": "<string>",
  "agent_name": "<string>",
  "agent_description": "<string>",
  "agent_category": "<string>",
  "agent_tips": [
    "<string>"
  ],
  "agent_mobile_number": [
    "<string>"
  ],
  "stt": {},
  "llm": {},
  "tts": {},
  "sts": {},
  "call_analysis_enabled": true,
  "prompt": {
    "prompt_name": "<string>",
    "prompt_version": 123,
    "prompt_content": "<string>"
  },
  "first_message_prompt": "<string>",
  "dynamic_variables": [
    "<string>"
  ],
  "tools": {},
  "widget_config": {},
  "MediaFiles": [
    {
      "fileType": "<string>",
      "mediaUrl": "<string>"
    }
  ],
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z"
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

POST

public

agents

curl --request POST \
  --url https://api.eigi.ai/v1/public/agents \
  --header 'Content-Type: application/json' \
  --header 'X-API-Key: <api-key>' \
  --data '
{
  "agent_name": "Support Agent",
  "agent_type": "INBOUND",
  "agent_category": "Customer Service",
  "stt": {
    "provider_name": "DEEPGRAM",
    "model_name": "nova-2",
    "language": "en",
    "params": {}
  },
  "llm": {
    "provider_name": "OPENAI",
    "model_name": "gpt-4o",
    "params": {
      "temperature": 0.7
    }
  },
  "tts": {
    "provider_name": "CARTESIA",
    "model_name": "sonic-2",
    "language": "en",
    "voice_id": "a0e99841-438c-4a64-b679-ae501e7d6091",
    "params": {
      "speed": 1
    }
  },
  "prompt_content": "You are a helpful customer support agent.",
  "call_analysis_enabled": true,
  "call_analysis_prompt": {
    "prompt_name": "support_call_analysis",
    "custom_prompt": "Analyze the call outcome, customer sentiment, and follow-up actions."
  },
  "call_analysis_schema": {
    "call_outcome": {
      "type": "str"
    },
    "customer_sentiment": {
      "type": "str"
    },
    "follow_up_required": {
      "type": "bool"
    }
  },
  "first_message_prompt": "Hello! How can I help you today?",
  "tools": {
    "end_call": true,
    "transfer_call": {
      "transfer_phone_number": "+919876543210"
    }
  }
}
'

{
  "id": "<string>",
  "agent_name": "<string>",
  "agent_description": "<string>",
  "agent_category": "<string>",
  "agent_tips": [
    "<string>"
  ],
  "agent_mobile_number": [
    "<string>"
  ],
  "stt": {},
  "llm": {},
  "tts": {},
  "sts": {},
  "call_analysis_enabled": true,
  "prompt": {
    "prompt_name": "<string>",
    "prompt_version": 123,
    "prompt_content": "<string>"
  },
  "first_message_prompt": "<string>",
  "dynamic_variables": [
    "<string>"
  ],
  "tools": {},
  "widget_config": {},
  "MediaFiles": [
    {
      "fileType": "<string>",
      "mediaUrl": "<string>"
    }
  ],
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z"
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

Overview

Create a new AI agent with full configuration including speech-to-text (STT), speech-to-speech (STS), large language model (LLM), text-to-speech (TTS), main prompt, call analysis prompt, tools, and widget settings.

Prompt Configuration

You can configure the agent’s prompt in two ways:

Inline prompt (prompt_content) — Provide the prompt text directly. An internal prompt is auto-created for the agent.
Prompt reference (prompt) — Reference an existing prompt by name and optionally version.

Call Analysis Configuration

You can optionally configure a dedicated call analysis prompt and schema:

Enable analysis (call_analysis_enabled) — Set this to true only when you want call analysis to run.
Analysis prompt reference (call_analysis_prompt) — Reference an existing analysis prompt by name and optionally version.
Inline analysis prompt (call_analysis_prompt.custom_prompt) — Provide prompt content directly to create a new analysis prompt version before linking it to the agent.
Structured output schema (call_analysis_schema) — Define the expected JSON structure for call analysis output.

If you do not want call analysis, omit call_analysis_enabled, call_analysis_prompt, and call_analysis_schema. If call_analysis_enabled is true, provide call_analysis_prompt as well.

Try It Behavior

In Try it, llm is shown as a single object.

For standard providers, fill llm.params.temperature only.
For CUSTOM_LLM, fill llm.params.base_url, llm.params.api_key, and optionally llm.params.API_TYPE.

Provider Restrictions (Public API)

Provider	Allowed params
STT	No params allowed (must be empty `{}`)
STS	No public API param restrictions
LLM	Standard providers: only `temperature` (0.0 - 2.0). `CUSTOM_LLM`: requires `base_url` plus `api_key`; optional `API_TYPE` and `temperature`
TTS	Only `speed`

Authentication

X-API-Key

string

required

Your eigi.ai API key. Must be prefixed with vk_.

Request Body

agent_name

string

required

Agent name (1-100 characters).

agent_type

string

required

Agent type: INBOUND or OUTBOUND.

stt

object

required

Speech-to-Text configuration.

Show properties

provider_name

string

required

STT provider: DEEPGRAM, OPENAI, WHISPER, or GROK.

model_name

string

required

Model name (e.g., nova-2).

language

string

required

Language code (e.g., en, hi).

params

object

Must be empty {} for public API requests.

llm

object

required

Large Language Model configuration.

Show properties

provider_name

string

required

LLM provider: OPENAI, OPENAI_RESPONSES, ANTHROPIC, GOOGLE, GROK, OPENROUTER, or CUSTOM_LLM.

model_name

string

required

Model name (e.g., gpt-4o).

params

object

For standard LLM providers, only temperature (0.0-2.0) is allowed. For CUSTOM_LLM, provide base_url, api_key, and optionally API_TYPE (CHAT_COMPLETION or RESPONSES) and temperature. If API_TYPE is omitted, it defaults to CHAT_COMPLETION.

tts

object

required

Text-to-Speech configuration.

Show properties

provider_name

string

required

TTS provider: CARTESIA, DEEPGRAM, ELEVENLABS, SARVAM, GOOGLE, HUME, or GROK.

model_name

string

required

Model name (e.g., sonic-2).

language

string

required

Language code.

voice_id

string

required

Voice ID from the provider. Use the List Voices endpoint to find available voices.

params

object

Only speed is allowed.

sts

object

Speech-to-Speech configuration for realtime voice generation.

Show properties

speech_to_speech_enabled

boolean

Whether speech-to-speech is enabled.

provider_name

string

required

STS provider: GOOGLE, OPENAI, or GROK.

model_name

string

required

Model name for the STS provider.

voice_id

string

required

Voice ID for the STS provider.

language

string

required

Language code.

params

object

Additional provider-specific STS parameters.

agent_description

string

Agent description (max 500 characters).

agent_category

string

default:"other"

Agent category (e.g., Customer Service, Sales, Healthcare, etc.).

agent_tips

array

Array of usage tip strings for the agent.

agent_mobile_number

array

Mobile numbers to associate with the agent.

prompt_content

string

Inline prompt content. Auto-creates an internal prompt for the agent.

prompt

object

Reference to an existing prompt (alternative to prompt_content).

Show properties

prompt_name

string

required

Name of the existing prompt.

prompt_version

integer

Specific version (omit for latest).

call_analysis_prompt

object

Optional call analysis prompt configuration.

Show properties

prompt_name

string

required

Name of an existing analysis prompt to reference.

prompt_version

integer

Specific analysis prompt version to use (omit for latest).

custom_prompt

string

Inline analysis prompt content. If provided, a new analysis prompt version is created before linking it to the agent.

call_analysis_enabled

boolean

Toggle call analysis on or off for the agent. Set this to true only when you want call analysis to run. If true, provide call_analysis_prompt as well.

call_analysis_schema

object

Optional schema describing the structured JSON output expected from call analysis.

first_message_prompt

string

Agent’s greeting message displayed when a chat session starts.

tools

object

Configure agent tools. Each tool can be true (enable), false (disable), or an object with configuration.Available tools: end_call, transfer_call, schedule_call, set_language, background_audio, user_idle.

Widget configuration for chat interface customization.

Response

Returns the complete agent object with all configurations, id, and timestamps.

Authorizations

X-API-Key

string

header

required

API key for authentication. Get your API key from the eigi.ai Dashboard under Settings â†’ API Keys.

Body

application/json

agent_name

string

required

Agent name (1-100 characters)

Required string length: 1 - 100

Example:

"Customer Support Agent"

agent_type

enum<string>

required

Agent type

Available options:

INBOUND,

OUTBOUND

stt

object

required

Show child attributes

llm

object

required

LLM configuration. Use provider_name to choose a standard provider or CUSTOM_LLM. For standard providers, only params.temperature applies. For CUSTOM_LLM, use params.base_url, params.api_key, and optional params.API_TYPE.

Show child attributes

tts

object

required

Show child attributes

agent_description

string

Agent description (max 500 characters)

Maximum string length: 500

agent_category

enum<string>

default:other

Agent category

Available options:

Customer Service,

Sales,

Scheduling,

Research,

Healthcare,

Customer Success,

Education,

Finance,

HR,

Legal,

Productivity,

Creative,

IT/DevOps,

E-commerce,

Entertainment,

Travel,

Wellness,

Anime,

Cartoon,

Gaming,

Lifestyle,

other

agent_tips

string[]

Usage tips for the agent

agent_mobile_number

string[]

Mobile numbers associated with the agent

call_analysis_prompt

object

Optional call analysis prompt reference. Provide custom_prompt to create a new analysis prompt version before linking it to the agent.

Show child attributes

call_analysis_enabled

boolean

Toggle call analysis on or off for the agent. Set to true only when you want call analysis to run; when true, provide call_analysis_prompt as well.

call_analysis_schema

object

Optional schema for structured call analysis output, keyed by field name.

Show child attributes

Example:

{
  "summary": { "type": "str" },
  "customer_intent": { "type": "Optional[str]" },
  "follow_up_required": { "type": "bool" }
}

prompt_content

string

Inline prompt content — auto-creates an internal prompt for the agent

prompt

object

Reference to an existing prompt (alternative to prompt_content)

Show child attributes

first_message_prompt

string

Agent's greeting message shown when chat starts

tools

object

Configure agent tools. Each tool can be true (enable), false (disable), or an object with configuration.

Show child attributes

Widget configuration for chat interface customization

Show child attributes

Response

Agent created successfully

string

Agent ID

agent_name

string

Agent name

agent_description

string

Agent description

agent_type

enum<string>

Agent type

Available options:

INBOUND,

OUTBOUND

agent_category

string

Agent category

agent_tips

string[]

Usage tips

agent_mobile_number

string[]

Associated mobile numbers

stt

object

STT configuration

llm

object

LLM configuration

tts

object

TTS configuration

sts

object

STS configuration (if set)

call_analysis_enabled

boolean

Whether call analysis is enabled for the agent

prompt

object

Prompt reference

Show child attributes

first_message_prompt

string

Agent's greeting message

dynamic_variables

string[]

Dynamic variables in the prompt

tools

object

Configured tools

Widget configuration

MediaFiles

object[]

Media files associated with the agent

Show child attributes

created_at

string<date-time>

Creation timestamp

updated_at

string<date-time>

Last update timestamp

Delete Prompt List Agents

​Overview

​Prompt Configuration

​Call Analysis Configuration

​Try It Behavior

​Provider Restrictions (Public API)

​Authentication

​Request Body

​Response

Authorizations

Body

Response

Overview

Prompt Configuration

Call Analysis Configuration

Try It Behavior

Provider Restrictions (Public API)

Authentication

Request Body

Response