Transcriber tab

Fields

All fields live under transcriber in the agent object. Some fields apply to one provider only.

Field	Type	Default	Allowed	Provider	What it does
provider	string	cartesia	cartesia, deepgram	both	The speech-to-text service.
model	string	ink-2	ink-2 (Cartesia), nova-3 (Deepgram)	both	The model. If it doesn’t match the provider, Voxa replaces it: ink-2 for Cartesia, nova-3 for Deepgram.
turn_detection	string	balanced	responsive, balanced, patient	Cartesia	How quickly the agent answers once the caller pauses.
language	string	hi	hi, multi, en-IN, en	Deepgram	The language the caller speaks. Cartesia ignores it and detects the language itself.
endpointing_ms	integer	300	10 to 3000	Deepgram	Milliseconds of silence that end the caller’s turn.
keyterms	array of strings	[]	up to 100	both	Words the recogniser should expect, such as doctor or product names. Cartesia uses up to 100, Deepgram the first 50.

Cartesia example

{
  "transcriber": {
    "provider": "cartesia",
    "model": "ink-2",
    "turn_detection": "patient",
    "keyterms": ["Dr. Kulkarni", "Aundh", "physiotherapy"]
  }
}

Deepgram example

{
  "transcriber": {
    "provider": "deepgram",
    "model": "nova-3",
    "language": "multi",
    "endpointing_ms": 400,
    "keyterms": ["Dr. Kulkarni"]
  }
}

Cartesia or Deepgram

	Cartesia ink-2	Deepgram nova-3
Language	Detects it on its own (en, hi, fr, ja, es)	You set it: hi, multi (switches between languages), en-IN, en
End of turn	A turn-detection model, tuned with turn_detection	A fixed silence, endpointing_ms
Good for	Callers who mix Hindi and English; natural pauses	A known single language; strict control of the pause length

Your workspace may not be allowed to use both. GET /api/v1/providers shows which providers your workspace can use; saving an agent with a provider it can’t use returns 422.

Turn detection

The agent starts its reply when the caller’s turn ends, so this setting trades speed against cutting the caller off.

turn_detection	Behaviour
responsive	Answers quickly. Good for short answers (“yes”, “no”, a date).
balanced	The default.
patient	Waits longer. Good for slow speakers, elderly callers, or callers who think aloud.

On Deepgram, raise endpointing_ms (for example to 500) if the agent talks over callers who pause mid-sentence, and lower it if replies feel slow.

If a caller pauses mid-sentence and the turn ends early, Voxa joins the two parts into one message for the LLM when the agent has not spoken in between. The transcript still shows them as two turns.

Usage

The seconds of caller audio sent to the transcriber are counted in the call’s usage.stt_seconds.