Skip to content
Nappai Documentation

Cartesia STT

Cartesia STT is one of the components that act as the hearing of a voice agent: it turns what the caller says into text so the agent can understand it. It uses Cartesia’s speech recognition service. It transcribes while the caller speaks, so the word-based interruption settings of the Voice Agent, such as Minimum Words To Interrupt, work with it.

It plugs into the STT connector of the Voice Agent node. It holds the speech recognition settings the agent uses on every call.

When to use it

  • You already use Cartesia TTS as the agent’s voice and want one provider and one credential.
  • You want cloud recognition that transcribes while the caller speaks.
  • Your callers may speak different languages and you want the agent to follow them without fixing a list.

Configuration

You need a Cartesia API credential with your Cartesia account key. See Credentials.

FieldWhat it does
Credential (required)The Cartesia API credential used to connect to the service.
LanguageCode of the language the caller is expected to speak, for example es or en. Default: es.
Detect LanguageWhen on, Cartesia detects on its own the language the caller speaks, without limiting itself to a list. Off by default.
ModelThe Cartesia model that transcribes: ink-whisper (default) or ink-2, Cartesia’s newer one.

Output

The STT output holds the speech recognition settings. It connects to the STT connector of the Voice Agent node, or to Fallback STT when you turn on Fallback Engines and want it as a backup. The editor will not let you plug it into a TTS connector by mistake.

Example

A language school gets calls from students in several languages.

  1. Add Cartesia STT and connect it to the STT connector of the Voice Agent.
  2. In Credential, choose the Cartesia API credential.
  3. Turn on Detect Language and leave Model as ink-whisper.
  4. Use Cartesia TTS with the same credential as the agent’s voice.

Good practices

  • Cartesia bills the usage to your own Cartesia account. Check your usage there.
  • The differences between local and cloud engines are explained in Quality, noise and latency.