Saltar al contenido principal
POST
/
v1
/
agent
Create Agent
import requests

url = "http://localhost:3000/v1/agent/"

payload = {
    "voice_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "language": "es",
    "name": "<string>",
    "description": "<string>",
    "prompt": "<string>",
    "greeting": "<string>",
    "time_before_start": 123,
    "boosted_keywords": ["<string>"],
    "redirect_number": "<string>",
    "max_reminder_count": 3,
    "reminder_frequency_ms": 7500,
    "reminder_messages": [],
    "knowledge_base_ids": [],
    "mode": "free",
    "conversational_path_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "version_name": "<string>",
    "integrations": [],
    "call_tools": []
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)
{
  "agent_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "modified_at": "2023-11-07T05:31:56Z",
  "created_at": "2023-11-07T05:31:56Z",
  "version_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "version_number": 123,
  "version_created_at": "2023-11-07T05:31:56Z",
  "voice": {
    "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "name": "<string>",
    "description": "<string>"
  },
  "language": "es",
  "mode": "free",
  "version_name": "<string>",
  "is_draft": false,
  "is_published": false,
  "name": "<string>",
  "description": "<string>",
  "prompt": "<string>",
  "greeting": "<string>",
  "time_before_start": 123,
  "boosted_keywords": [
    "<string>"
  ],
  "redirect_number": "<string>",
  "max_reminder_count": 3,
  "reminder_frequency_ms": 7500,
  "reminder_messages": [],
  "knowledge_base_ids": [],
  "conversational_path_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "integrations": [],
  "call_tools": []
}

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Query Parameters

​
is_draft
boolean
default:false

If true, the agent is created as a draft.

Body

application/json
​
voice_id
string<uuid>
required

The voice id to be used by the agent

​
language
enum<string>
required

The language used by the agent. Use multi for the agent using both english and spanish in the same call (multi will expand to more languages in the future)

Opciones disponibles:
es,
en,
multi,
fr,
ca,
de,
bg,
zh,
zh-TW,
zh-HK,
cs,
da,
nl,
et,
fi,
nl-BE,
de-CH,
el,
hi,
hu,
id,
it,
ja,
ko,
lv,
lt,
ms,
no,
pl,
pt,
ro,
ru,
sk,
sv,
th,
tr,
uk,
vi
​
name
string | null

The name of the agent

​
description
string | null

The description given to the agent

​
prompt
string | null

The prompt given to the agent

​
greeting
string | null

The greeting message said by the agent to the caller at the beginning of the call

​
time_before_start
number | null

The time in seconds before the agent starts to speak

​
boosted_keywords
string[] | null

he list of keywords that are boosted for the agent speech recognition. Use this to improve the agent's recognition of domain-specific terms. For example, ['bradycardia']

​
redirect_number
string | null

The phone number to use by the agent if the call needs to be redirected. If not provided, you won't be able to redirect the call even if the tool is present

​
max_reminder_count
integer
default:3

The maximum number of reminders that can be sent to the caller. If not provided, the default value is 3. When reached the last reminder, the call gets hang up. Set this value to 0 to disable reminders

Rango requerido: x >= 0
​
reminder_frequency_ms
integer
default:7500

The frequency in milliseconds to send reminders to the caller. If not provided, the default value is 7500. Set this value to 0 to disable reminders

Rango requerido: x >= 1000
​
reminder_messages
string[]

The list of messages to send to the caller as reminders. If not provided, the default value is an empty list which makes the model to generate the reminder messages by itself. Please, note that when using an empty list, the reminder_frequency_ms can be a little bit higher than specified since it has to generate the messages

​
knowledge_base_ids
string<uuid>[] | null

The list of knowledge base ids available for the agent to use

​
mode
enum<string>
default:free

The mode of the agent. Can be 'free' or 'path'

Opciones disponibles:
free,
path
​
conversational_path_id
string<uuid> | null

The id of the conversational path used by the agent.

​
version_name
string | null

The name of the created version

​
integrations
IntegrationToolsRequest · object[] | null

The list of integrations and their tools to assign to the agent

​
call_tools
CallToolRequest · object[] | null

The list of call-tools (built-in tools) to assign to the agent

Response

Successful Response

​
agent_id
string<uuid>
required

The unique identifier for the agent

​
modified_at
string<date-time>
required

The date and time when the agent was last updated

​
created_at
string<date-time>
required

The date and time when the agent was created

​
version_id
string<uuid>
required

The version id of the agent

​
version_number
integer
required

The version number of the agent

​
version_created_at
string<date-time>
required

The date and time when the version was created

​
voice
Voice · object
required

The voice object used by the agent

​
language
enum<string>
required

The language used by the agent. Use multi for the agent using both english and spanish in the same call (multi will expand to more languages in the future)

Opciones disponibles:
es,
en,
multi,
fr,
ca,
de,
bg,
zh,
zh-TW,
zh-HK,
cs,
da,
nl,
et,
fi,
nl-BE,
de-CH,
el,
hi,
hu,
id,
it,
ja,
ko,
lv,
lt,
ms,
no,
pl,
pt,
ro,
ru,
sk,
sv,
th,
tr,
uk,
vi
​
mode
enum<string>
required

The mode of the agent. Can be 'free' or 'path'

Opciones disponibles:
free,
path
​
version_name
string | null

The version name of the agent

​
is_draft
boolean
default:false

Indicates if the agent is a draft version

​
is_published
boolean
default:false

Indicates if the agent is published

​
name
string | null

The name of the agent

​
description
string | null

The description given to the agent

​
prompt
string | null

The prompt given to the agent

​
greeting
string | null

The greeting message said by the agent to the caller at the beginning of the call. If set, the agent will always speak first both in inbound and outbound calls

​
time_before_start
number | null

The time in seconds before the agent starts to speak

​
boosted_keywords
string[] | null

he list of keywords that are boosted for the agent speech recognition. Use this to improve the agent's recognition of domain-specific terms. For example, ['bradycardia']

​
redirect_number
string | null

The phone number to use by the agent if the call needs to be redirected. If not provided, you won't be able to redirect the call even if the tool is present

​
max_reminder_count
integer
default:3

The maximum number of reminders that can be sent to the caller. If not provided, the default value is 3. Set this value to 0 to disable reminders

Rango requerido: x >= 0
​
reminder_frequency_ms
integer
default:7500

The frequency in milliseconds to send reminders to the caller. If not provided, the default value is 7500.

​
reminder_messages
string[]

The list of messages to send to the caller as reminders. If not provided, the default value is an empty list which makes the model to generate the reminder messages by itself. Please, note that when using an empty list, the reminder_frequency_ms can be a little bit higher than specified since it has to generate the messages

​
knowledge_base_ids
string<uuid>[] | null

The list of knowledge bases available for the agent to use

​
conversational_path_id
string<uuid> | null

The id of the conversational path used by the agent.

​
integrations
IntegrationToolsResponse · object[]

The list of integrations and their assigned tools for the agent

​
call_tools
CallToolResponse · object[]

The list of call-tools (built-in tools) assigned to the agent