Create new assistant

Creates a new AI assistant with configuration. Requires appropriate permissions.

Authorization

access-token

X-Access-Token<token>

Enter your Access Token (format: happ_...)

In: header

Request Body

application/json

TypeScript Definitions

Use the request body type in TypeScript.

name*string

Assistant display name

firstMessage?string

Greeting the assistant sends when a conversation starts

promptText*string

System prompt defining the assistant behavior and knowledge

companyId*string

ID of the company the assistant belongs to

Formatuuid

providerId?string

Provider ID for voice assistant integration

Formatuuid

language?string

Primary conversation language of the assistant

assistantOutputAudioFormat?string

Audio format of the assistant voice output

Value in

"pcm_8000"
"pcm_16000"
"pcm_22050"
"pcm_24000"
"pcm_44100"
"pcm_48000"
"ulaw_8000"

userInputAudioFormat?string

Audio format expected for user voice input

Value in

"pcm_8000"
"pcm_16000"
"pcm_22050"
"pcm_24000"
"pcm_44100"
"pcm_48000"
"ulaw_8000"

textLlmModelId?string

FK to llm_models (type=text) — chat LLM selection

Formatuuid

voiceLlmModelId?string

FK to llm_models (type=voice) — voice agent LLM selection

Formatuuid

disableFirstMessageInterruption?boolean

Disable interruption of the first message

ttsModel?string

Text-to-speech model identifier

voiceAssistantId?string

External voice assistant ID at the voice provider

elevenLabsVoiceId?string

ElevenLabs voice ID used for speech synthesis

vaVoice?string

Voice name used by the voice assistant

eagerness?string

How eagerly the voice agent takes its conversational turn

Default"normal"

Value in

"eager"
"normal"
"patient"

softTimeout?number

Seconds of user silence before the soft-timeout message is spoken. A value of -1 disables it.

Default-1

softTimeoutMessage?string

Message the assistant speaks when the soft timeout fires

streamingLatency?number

Streaming latency optimization (0-4)

Range0 <= value <= 4

Default2

turnAfterSilence?number

The maximum number of seconds since the user last spoke. If exceeded, the agent will respond and force a turn. A value of -1 means the agent will wait indefinitely for user input.

Range-1 <= value <= 300

Default7

silenceEndCallTimeout?number

Seconds of silence after which the call ends automatically. A value of -1 disables this. Maximum 2 hours (7200 seconds).

Range-1 <= value <= 7200

Default-1

Response Body

`application/json`

curl -X POST "https://example.com/api/assistants" \  -H "Content-Type: application/json" \  -d '{    "name": "Sales Assistant",    "promptText": "You are a helpful sales assistant for Acme Corp. Answer questions about our products.",    "companyId": "a1b2c3d4-e5f6-7890-abcd-ef1234567890"  }'

{  "id": "string",  "name": "string",  "firstMessage": "string",  "promptText": "string",  "companyId": "string",  "createdAt": "2019-08-24T14:15:22Z"}

Empty

Create new assistant

Authorization

Request Body

Response Body

201application/json

400

401

`application/json`