Agents

Overview

An agent defines the AI persona that handles calls and widget interactions. It holds the system prompt, voice configuration, and language settings. Create one agent per use case and reuse it across calls, widgets, and workflows. All provider and model identifiers are aliased — you will never see internal provider names. Use the alias values returned by the API when updating agent settings. Required scopes: agents:read (read operations), agents:write (create/update)

`GET /v1/agents/voices`

Returns available voice providers and their supported models and voices. Use these values when updating an agent’s voice configuration.

curl https://api.indigenius.ai/v1/agents/voices \
  -H "X-API-Key: $INDIGENIUS_API_KEY"

const response = await fetch('https://api.indigenius.ai/v1/agents/voices', {
  headers: { 'X-API-Key': process.env.INDIGENIUS_API_KEY },
});
console.log(await response.json());

import requests, os

response = requests.get(
    "https://api.indigenius.ai/v1/agents/voices",
    headers={"X-API-Key": os.environ["INDIGENIUS_API_KEY"]},
    timeout=30,
)
print(response.json())

200 OK

{
  "success": true,
  "message": "Voices fetched",
  "data": [
    {
      "name": "Voice Model 1",
      "provider": "indigenius_voice_model_1",
      "models": [
        "multilingual_v2",
        "multilingual_v1",
        "turbo_v2_5",
        "turbo_v2"
      ],
      "voices": [
        {
          "voice_id": "EXAVITQu4vr4xnSDxMaL",
          "name": "Sarah",
          "gender": "female"
        }
      ]
    },
    {
      "name": "Voice Model 2",
      "provider": "indigenius_voice_model_2",
      "models": [
        "indigenius_v1"
      ],
      "voices": [
        {
          "voice_id": "Pidgin Female",
          "name": "Pidgin Female",
          "gender": "female"
        },
        {
          "voice_id": "Yoruba Male",
          "name": "Yoruba Male",
          "gender": "male"
        }
      ]
    }
  ],
  "meta": {
    "requestId": "f3c9b29a-9f4d-4b71-8b3b-2cb77f4e9cf1",
    "timestamp": "2026-06-02T10:30:45.123Z",
    "version": "v1"
  }
}

Common errors: 403 missing agents:read scope

`GET /v1/agents`

Returns all agents available to your organization.

curl https://api.indigenius.ai/v1/agents \
  -H "X-API-Key: $INDIGENIUS_API_KEY"

const response = await fetch('https://api.indigenius.ai/v1/agents', {
  headers: { 'X-API-Key': process.env.INDIGENIUS_API_KEY },
});
console.log(await response.json());

import requests, os

response = requests.get(
    "https://api.indigenius.ai/v1/agents",
    headers={"X-API-Key": os.environ["INDIGENIUS_API_KEY"]},
    timeout=30,
)
print(response.json())

200 OK

{
  "success": true,
  "message": "Agents fetched",
  "data": [
    {
      "id": "665e4a34c65bb95f2f2d72e1",
      "name": "Sales Agent",
      "language": "English",
      "task_type": "lead_qualification"
    }
  ],
  "meta": {
    "requestId": "f3c9b29a-9f4d-4b71-8b3b-2cb77f4e9cf1",
    "timestamp": "2026-06-02T10:30:45.123Z",
    "version": "v1"
  }
}

Common errors: 403 missing agents:read scope · 404 key or org context not found

`POST /v1/agents`

Creates a new conversational agent for your organization, configured from a short business description rather than a raw prompt — the system generates the agent’s prompt and voice setup from these fields. To build a one-way announcer agent instead (plays a message, doesn’t converse), use POST /v1/agents/announcer below. Request body

Field	Type	Required	Description
`name`	string	yes	Agent’s display name.
`company_name`	string	yes	Business the agent represents — used to ground its responses.
`industry`	string	yes	Free-text industry description (e.g. `ecommerce`, `healthcare`).
`language`	string	yes	Language the agent speaks. One of `Spanish`, `French`, `English`, `Mandarin`, `Swahili`, `Portuguese`, `Arabic`, `German`, `Chinese`, `Igbo`, `Hausa`, `Yoruba`, `Pidgin`.
`voice`	string	yes	`male` or `female`.
`task_type`	string	yes	Free-text description of what the agent is for (e.g. `lead_qualification`, `customer_support`).
`website_url`	string (URL)	no	Business website to ground the agent’s responses in. Must include the `http://` or `https://` scheme.

curl -X POST https://api.indigenius.ai/v1/agents \
  -H "X-API-Key: $INDIGENIUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Sales Agent",
    "company_name": "Acme Inc",
    "industry": "ecommerce",
    "language": "English",
    "voice": "female",
    "task_type": "lead_qualification"
  }'

const response = await fetch('https://api.indigenius.ai/v1/agents', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'X-API-Key': process.env.INDIGENIUS_API_KEY,
  },
  body: JSON.stringify({
    name: 'Sales Agent',
    company_name: 'Acme Inc',
    industry: 'ecommerce',
    language: 'English',
    voice: 'female',
    task_type: 'lead_qualification',
  }),
});
console.log(await response.json());

import requests, os

response = requests.post(
    "https://api.indigenius.ai/v1/agents",
    headers={
        "X-API-Key": os.environ["INDIGENIUS_API_KEY"],
        "Content-Type": "application/json",
    },
    json={
        "name": "Sales Agent",
        "company_name": "Acme Inc",
        "industry": "ecommerce",
        "language": "English",
        "voice": "female",
        "task_type": "lead_qualification",
    },
    timeout=30,
)
print(response.json())

201 Created

{
  "success": true,
  "message": "Agent created successfully",
  "data": null,
  "meta": {
    "requestId": "f3c9b29a-9f4d-4b71-8b3b-2cb77f4e9cf1",
    "timestamp": "2026-06-02T10:30:45.123Z",
    "version": "v1"
  }
}

Common errors: 400 validation error (missing required fields) · 403 missing agents:write scope

`GET /v1/agents/{id}`

Returns a single agent by ID.

curl https://api.indigenius.ai/v1/agents/665e4a34c65bb95f2f2d72e1 \
  -H "X-API-Key: $INDIGENIUS_API_KEY"

const agentId = '665e4a34c65bb95f2f2d72e1';
const response = await fetch(`https://api.indigenius.ai/v1/agents/${agentId}`, {
  headers: { 'X-API-Key': process.env.INDIGENIUS_API_KEY },
});
console.log(await response.json());

import requests, os

agent_id = "665e4a34c65bb95f2f2d72e1"
response = requests.get(
    f"https://api.indigenius.ai/v1/agents/{agent_id}",
    headers={"X-API-Key": os.environ["INDIGENIUS_API_KEY"]},
    timeout=30,
)
print(response.json())

200 OK

{
  "success": true,
  "message": "Assistant details fetched",
  "data": {
    "id": "665e4a34c65bb95f2f2d72e1",
    "name": "Sales Agent",
    "language": "English",
    "first_message": "Hello, how can I help you today?",
    "system_prompt": "You are a helpful sales agent.",
    "provider": "indigenius_reasoning_model_1",
    "model": "gpt4o",
    "voice_provider": "indigenius_voice_model_1",
    "voice_model": "multilingual_v2",
    "voice": "Sarah",
    "hipaa": false
  },
  "meta": {
    "requestId": "f3c9b29a-9f4d-4b71-8b3b-2cb77f4e9cf1",
    "timestamp": "2026-06-02T10:30:45.123Z",
    "version": "v1"
  }
}

Common errors: 403 missing agents:read scope · 404 agent not found

`PATCH /v1/agents/{id}`

Replaces an agent’s prompt, name, language, and reasoning model. Unlike POST /v1/agents, this takes the finished system_prompt and first_message directly rather than generating them — fetch the agent first with GET /v1/agents/{id} if you want to edit its existing prompt rather than overwrite it blind.

This endpoint requires the agent id in both the URL path and the request body. Omitting it from the body will return a 400 validation error.

Request body

Field	Type	Required	Description
`id`	string	yes	Agent id — must match the `{id}` in the URL path.
`name`	string	yes	Agent’s display name.
`language`	string	yes	Language the agent speaks. One of `Spanish`, `French`, `English`, `Mandarin`, `Swahili`, `Portuguese`, `Arabic`, `German`, `Chinese`, `Igbo`, `Hausa`, `Yoruba`, `Pidgin`.
`first_message`	string	yes	The agent’s opening line when a call connects.
`system_prompt`	string	yes	Full system prompt controlling the agent’s behavior. Fully replaces the existing prompt.
`provider`	string	no	Reasoning provider to use. Currently only `indigenius_reasoning_model_1`.
`model`	string	no	Reasoning model identifier stored alongside `provider`. Leave unset unless you’ve been told a specific value to use.
`hipaa`	boolean	yes	Marks the agent as handling HIPAA-covered conversations.

curl -X PATCH https://api.indigenius.ai/v1/agents/665e4a34c65bb95f2f2d72e1 \
  -H "X-API-Key: $INDIGENIUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "id": "665e4a34c65bb95f2f2d72e1",
    "name": "Sales Agent",
    "language": "English",
    "first_message": "Hello, I can help with product questions.",
    "system_prompt": "You are a concise, helpful sales agent.",
    "provider": "indigenius_reasoning_model_1",
    "hipaa": false
  }'

const agentId = '665e4a34c65bb95f2f2d72e1';
const response = await fetch(`https://api.indigenius.ai/v1/agents/${agentId}`, {
  method: 'PATCH',
  headers: {
    'Content-Type': 'application/json',
    'X-API-Key': process.env.INDIGENIUS_API_KEY,
  },
  body: JSON.stringify({
    id: agentId,
    name: 'Sales Agent',
    language: 'English',
    first_message: 'Hello, I can help with product questions.',
    system_prompt: 'You are a concise, helpful sales agent.',
    provider: 'indigenius_reasoning_model_1',
    hipaa: false,
  }),
});
console.log(await response.json());

import requests, os

agent_id = "665e4a34c65bb95f2f2d72e1"
response = requests.patch(
    f"https://api.indigenius.ai/v1/agents/{agent_id}",
    headers={
        "X-API-Key": os.environ["INDIGENIUS_API_KEY"],
        "Content-Type": "application/json",
    },
    json={
        "id": agent_id,
        "name": "Sales Agent",
        "language": "English",
        "first_message": "Hello, I can help with product questions.",
        "system_prompt": "You are a concise, helpful sales agent.",
        "provider": "indigenius_reasoning_model_1",
        "hipaa": False,
    },
    timeout=30,
)
print(response.json())

200 OK

{
  "success": true,
  "message": "Agent settings saved",
  "data": null,
  "meta": {
    "requestId": "f3c9b29a-9f4d-4b71-8b3b-2cb77f4e9cf1",
    "timestamp": "2026-06-02T10:30:45.123Z",
    "version": "v1"
  }
}

Common errors: 400 validation error (check id is in body) · 403 missing agents:write scope · 404 agent not found

PATCH field reference

Field	Type	Description
`id`	`string`	Required. Must match the URL path parameter.
`name`	`string`	Display name for the agent.
`language`	`string`	Spoken language (e.g. `"English"`, `"French"`).
`first_message`	`string`	Greeting spoken at the start of each call.
`system_prompt`	`string`	Full persona instructions for the LLM.
`provider`	`string`	LLM provider alias from `GET /v1/agents/voices` (e.g. `indigenius_reasoning_model_1`).
`model`	`string`	Optional model identifier.
`hipaa`	`boolean`	Enable HIPAA-compliant mode (disables call recording).

Announcer agents

An announcer agent is a one-way broadcast agent: it dials out, speaks a message (text-to-speech or pre-recorded audio), and hangs up — it never listens for or acts on caller audio. Announcer agents are created and configured with the endpoints below, then allocated to a purchased number and dialed out with the Phone API (POST /v1/phone/allocate-assistant, POST /v1/phone/announce, POST /v1/phone/schedule-announcer-campaign). Announcer agents are a distinct agent mode — they aren’t created or updated through POST /v1/agents / PATCH /v1/agents/{id} above, and a regular conversational agent can’t be converted into one.

`POST /v1/agents/announcer`

Creates a new announcer agent. Pass templateId to seed it from a built-in or custom template (see GET /v1/agents/announcer-templates below); omit it to start blank and configure the message yourself.

curl -X POST https://api.indigenius.ai/v1/agents/announcer \
  -H "X-API-Key: $INDIGENIUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"name": "Renewal Reminder"}'

const response = await fetch('https://api.indigenius.ai/v1/agents/announcer', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'X-API-Key': process.env.INDIGENIUS_API_KEY,
  },
  body: JSON.stringify({ name: 'Renewal Reminder' }),
});
console.log(await response.json());

import requests, os

response = requests.post(
    "https://api.indigenius.ai/v1/agents/announcer",
    headers={
        "X-API-Key": os.environ["INDIGENIUS_API_KEY"],
        "Content-Type": "application/json",
    },
    json={"name": "Renewal Reminder"},
    timeout=30,
)
print(response.json())

201 Created

{
  "success": true,
  "message": "Announcer agent created successfully",
  "data": {
    "agent": {
      "id": "665e4a34c65bb95f2f2d72e1",
      "name": "Renewal Reminder"
    }
  },
  "meta": {
    "requestId": "f3c9b29a-9f4d-4b71-8b3b-2cb77f4e9cf1",
    "timestamp": "2026-06-02T10:30:45.123Z",
    "version": "v1"
  }
}

Common errors: 400 validation error · 403 missing agents:write scope

`GET /v1/agents/announcer-templates`

Returns built-in and organization-accessible announcer templates, each with a preconfigured message, voice, and language.

curl https://api.indigenius.ai/v1/agents/announcer-templates \
  -H "X-API-Key: $INDIGENIUS_API_KEY"

const response = await fetch(
  'https://api.indigenius.ai/v1/agents/announcer-templates',
  { headers: { 'X-API-Key': process.env.INDIGENIUS_API_KEY } },
);
console.log(await response.json());

import requests, os

response = requests.get(
    "https://api.indigenius.ai/v1/agents/announcer-templates",
    headers={"X-API-Key": os.environ["INDIGENIUS_API_KEY"]},
    timeout=30,
)
print(response.json())

200 OK

{
  "success": true,
  "message": "Templates fetched successfully",
  "data": [
    {
      "id": "665e4a34c65bb95f2f2d72e9",
      "name": "Payment Reminder",
      "announcerMessage": "Hi {name}, your payment of {amount} is due."
    }
  ],
  "meta": {
    "requestId": "f3c9b29a-9f4d-4b71-8b3b-2cb77f4e9cf1",
    "timestamp": "2026-06-02T10:30:45.123Z",
    "version": "v1"
  }
}

Common errors: 403 missing agents:read scope

`POST /v1/agents/{id}/announcer-template`

Applies a template’s message, voice, and language configuration to an existing announcer agent, replacing its current configuration.

curl -X POST https://api.indigenius.ai/v1/agents/665e4a34c65bb95f2f2d72e1/announcer-template \
  -H "X-API-Key: $INDIGENIUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"templateId": "665e4a34c65bb95f2f2d72e9"}'

const agentId = '665e4a34c65bb95f2f2d72e1';
const response = await fetch(
  `https://api.indigenius.ai/v1/agents/${agentId}/announcer-template`,
  {
    method: 'POST',
    headers: {
      'Content-Type': 'application/json',
      'X-API-Key': process.env.INDIGENIUS_API_KEY,
    },
    body: JSON.stringify({ templateId: '665e4a34c65bb95f2f2d72e9' }),
  },
);
console.log(await response.json());

import requests, os

agent_id = "665e4a34c65bb95f2f2d72e1"
response = requests.post(
    f"https://api.indigenius.ai/v1/agents/{agent_id}/announcer-template",
    headers={
        "X-API-Key": os.environ["INDIGENIUS_API_KEY"],
        "Content-Type": "application/json",
    },
    json={"templateId": "665e4a34c65bb95f2f2d72e9"},
    timeout=30,
)
print(response.json())

200 OK

{
  "success": true,
  "message": "Template applied successfully",
  "data": null,
  "meta": {
    "requestId": "f3c9b29a-9f4d-4b71-8b3b-2cb77f4e9cf1",
    "timestamp": "2026-06-02T10:30:45.123Z",
    "version": "v1"
  }
}

Common errors: 400 invalid or inaccessible templateId, or id is not an announcer agent · 403 missing agents:write scope · 404 agent not found

`PUT /v1/agents/{id}/announcer-message`

Sets the announcer message for an agent. Set personalized: true and include {placeholders} in the message (e.g. {name}, {amount}) to enable personalized campaigns via POST /v1/phone/schedule-announcer-campaign — the placeholders become the columns of that campaign’s contact sheet. The message and the uploaded audio are stored separately, and saving one never changes the other. Send source (message or upload) to choose which one the agent uses on calls; when source is upload, message is optional, so you can switch to an already-uploaded file without resending it. If source is omitted, the agent keeps using whichever it used before, except that a personalized: true message makes the message active.

curl -X PUT https://api.indigenius.ai/v1/agents/665e4a34c65bb95f2f2d72e1/announcer-message \
  -H "X-API-Key: $INDIGENIUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "message": "Hi {name}, your payment of {amount} is due on {due_date}.",
    "personalized": true
  }'

const agentId = '665e4a34c65bb95f2f2d72e1';
const response = await fetch(
  `https://api.indigenius.ai/v1/agents/${agentId}/announcer-message`,
  {
    method: 'PUT',
    headers: {
      'Content-Type': 'application/json',
      'X-API-Key': process.env.INDIGENIUS_API_KEY,
    },
    body: JSON.stringify({
      message: 'Hi {name}, your payment of {amount} is due on {due_date}.',
      personalized: true,
    }),
  },
);
console.log(await response.json());

import requests, os

agent_id = "665e4a34c65bb95f2f2d72e1"
response = requests.put(
    f"https://api.indigenius.ai/v1/agents/{agent_id}/announcer-message",
    headers={
        "X-API-Key": os.environ["INDIGENIUS_API_KEY"],
        "Content-Type": "application/json",
    },
    json={
        "message": "Hi {name}, your payment of {amount} is due on {due_date}.",
        "personalized": True,
    },
    timeout=30,
)
print(response.json())

200 OK

{
  "success": true,
  "message": "Announcer message updated successfully",
  "data": null,
  "meta": {
    "requestId": "f3c9b29a-9f4d-4b71-8b3b-2cb77f4e9cf1",
    "timestamp": "2026-06-02T10:30:45.123Z",
    "version": "v1"
  }
}

Common errors: 400 validation error, message exceeds the length allowed on the organization’s plan, source is upload but no audio has been uploaded, or source is message but no message is saved · 403 missing agents:write scope · 404 agent not found

`POST /v1/agents/{id}/announcer-audio/generate`

Synthesizes the announcer message to speech with the given voice and sets it as the agent’s announcement audio. Also sets the message and personalized flag, same as the endpoint above, and makes the message the agent’s active configuration — use this instead when you want to hear/preview the generated audio in the same call. Any uploaded audio is kept.

curl -X POST https://api.indigenius.ai/v1/agents/665e4a34c65bb95f2f2d72e1/announcer-audio/generate \
  -H "X-API-Key: $INDIGENIUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "message": "Hi {name}, your payment of {amount} is due.",
    "personalized": true,
    "language": "English",
    "voiceGender": "female",
    "voiceId": "EXAVITQu4vr4xnSDxMaL",
    "voiceName": "Sarah",
    "voiceProvider": "indigenius_voice_model_1",
    "speed": 1
  }'

const agentId = '665e4a34c65bb95f2f2d72e1';
const response = await fetch(
  `https://api.indigenius.ai/v1/agents/${agentId}/announcer-audio/generate`,
  {
    method: 'POST',
    headers: {
      'Content-Type': 'application/json',
      'X-API-Key': process.env.INDIGENIUS_API_KEY,
    },
    body: JSON.stringify({
      message: 'Hi {name}, your payment of {amount} is due.',
      personalized: true,
      language: 'English',
      voiceGender: 'female',
      voiceId: 'EXAVITQu4vr4xnSDxMaL',
      voiceName: 'Sarah',
      voiceProvider: 'indigenius_voice_model_1',
      speed: 1,
    }),
  },
);
console.log(await response.json());

import requests, os

agent_id = "665e4a34c65bb95f2f2d72e1"
response = requests.post(
    f"https://api.indigenius.ai/v1/agents/{agent_id}/announcer-audio/generate",
    headers={
        "X-API-Key": os.environ["INDIGENIUS_API_KEY"],
        "Content-Type": "application/json",
    },
    json={
        "message": "Hi {name}, your payment of {amount} is due.",
        "personalized": True,
        "language": "English",
        "voiceGender": "female",
        "voiceId": "EXAVITQu4vr4xnSDxMaL",
        "voiceName": "Sarah",
        "voiceProvider": "indigenius_voice_model_1",
        "speed": 1,
    },
    timeout=30,
)
print(response.json())

200 OK

{
  "success": true,
  "message": "Announcer audio generated successfully",
  "data": {
    "assistant": {
      "id": "665e4a34c65bb95f2f2d72e1"
    }
  },
  "meta": {
    "requestId": "f3c9b29a-9f4d-4b71-8b3b-2cb77f4e9cf1",
    "timestamp": "2026-06-02T10:30:45.123Z",
    "version": "v1"
  }
}

voiceProvider uses the same aliases as GET /v1/agents/voices (e.g. indigenius_voice_model_1, indigenius_voice_model_2) — never the internal provider name. Common errors: 400 validation error, or message exceeds the length allowed on the organization’s plan · 403 missing agents:write scope · 404 agent not found

`POST /v1/agents/{id}/announcer-audio/upload`

Uploads a pre-recorded audio file (.mp3, .wav, .ogg, or .m4a) and makes it the audio the agent plays. The uploaded file is stored separately from the message; call PUT /v1/agents/{id}/announcer-message with source: "message" to switch back to the message. Personalized campaigns use the message, so they require the message to be the active configuration.

curl -X POST https://api.indigenius.ai/v1/agents/665e4a34c65bb95f2f2d72e1/announcer-audio/upload \
  -H "X-API-Key: $INDIGENIUS_API_KEY" \
  -F "file=@announcement.mp3"

const agentId = '665e4a34c65bb95f2f2d72e1';
const form = new FormData();
form.append('file', audioBlob, 'announcement.mp3');

const response = await fetch(
  `https://api.indigenius.ai/v1/agents/${agentId}/announcer-audio/upload`,
  {
    method: 'POST',
    headers: { 'X-API-Key': process.env.INDIGENIUS_API_KEY },
    body: form,
  },
);
console.log(await response.json());

import requests, os

agent_id = "665e4a34c65bb95f2f2d72e1"
files = {"file": open("announcement.mp3", "rb")}
response = requests.post(
    f"https://api.indigenius.ai/v1/agents/{agent_id}/announcer-audio/upload",
    headers={"X-API-Key": os.environ["INDIGENIUS_API_KEY"]},
    files=files,
    timeout=60,
)
print(response.json())

200 OK

{
  "success": true,
  "message": "Audio uploaded successfully",
  "data": {
    "assistant": {
      "id": "665e4a34c65bb95f2f2d72e1"
    }
  },
  "meta": {
    "requestId": "f3c9b29a-9f4d-4b71-8b3b-2cb77f4e9cf1",
    "timestamp": "2026-06-02T10:30:45.123Z",
    "version": "v1"
  }
}

Common errors: 400 no file uploaded, unsupported file type, or file exceeds the size allowed on the organization’s plan · 403 missing agents:write scope · 404 agent not found

Personalized campaign flow

To run a personalized announcer campaign end-to-end:

POST /v1/agents/announcer — create the agent.
PUT /v1/agents/{id}/announcer-message (or announcer-audio/generate) with personalized: true and {placeholders} in the message.
POST /v1/phone/allocate-assistant — allocate the agent as the number’s outboundAssistantId. An inboundAssistantId is still required by that endpoint even for an announcer-only number; use any conversational agent you don’t otherwise route inbound calls to.
GET /v1/phone/announcer/{phoneId}/campaign-template — download the contact sheet template; its columns are generated from the placeholders set in step 2.
POST /v1/phone/schedule-announcer-campaign — upload the filled sheet to schedule the campaign.

See the Phone API for details on steps 3–5.

Recommended integration flow

Create an agent with your base persona (POST /v1/agents).
Copy the returned id.
List available voices with GET /v1/agents/voices to get valid provider and model aliases.
Use the id when creating widgets, calls, or workflows.
Update prompts and model settings over time with PATCH /v1/agents/{id}.

Getting Started

Core APIs

Platform APIs

Overview

`GET /v1/agents/voices`

`GET /v1/agents`

`POST /v1/agents`

`GET /v1/agents/{id}`

`PATCH /v1/agents/{id}`

PATCH field reference

Announcer agents

`POST /v1/agents/announcer`

`GET /v1/agents/announcer-templates`

`POST /v1/agents/{id}/announcer-template`

`PUT /v1/agents/{id}/announcer-message`

`POST /v1/agents/{id}/announcer-audio/generate`

`POST /v1/agents/{id}/announcer-audio/upload`

Personalized campaign flow

Recommended integration flow

​Overview

​GET /v1/agents/voices

​GET /v1/agents

​POST /v1/agents

​GET /v1/agents/{id}

​PATCH /v1/agents/{id}

​PATCH field reference

​Announcer agents

​POST /v1/agents/announcer

​GET /v1/agents/announcer-templates

​POST /v1/agents/{id}/announcer-template

​PUT /v1/agents/{id}/announcer-message

​POST /v1/agents/{id}/announcer-audio/generate

​POST /v1/agents/{id}/announcer-audio/upload

​Personalized campaign flow

​Recommended integration flow

Overview

`GET /v1/agents/voices`

`GET /v1/agents`

`POST /v1/agents`

`GET /v1/agents/{id}`

`PATCH /v1/agents/{id}`

PATCH field reference

Announcer agents

`POST /v1/agents/announcer`

`GET /v1/agents/announcer-templates`

`POST /v1/agents/{id}/announcer-template`

`PUT /v1/agents/{id}/announcer-message`

`POST /v1/agents/{id}/announcer-audio/generate`

`POST /v1/agents/{id}/announcer-audio/upload`

Personalized campaign flow

Recommended integration flow