Skip to content
Nappai Documentation

Cartesia TTS

Cartesia TTS is one of the components that give a voice agent its voice: it turns the agent’s answers into audio for the caller to hear. It uses voices from the Cartesia service. The voice speaks in the call’s language, which comes from the STT connected to the Voice Agent.

It plugs into the TTS connector of the Voice Agent node. It holds the voice settings the agent uses on every call.

When to use it

  • You already chose or created a voice in Cartesia and want the agent to use it.
  • You use Cartesia STT and want one provider and one credential.
  • You want to adjust how fast the agent speaks.

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.
Voice IDThe Cartesia voice ID, as your Cartesia account shows it. Empty, a default voice is used.
ModelThe Cartesia voice model. Default: sonic-3.6, which always points to the latest stable Sonic 3.6. To keep the voice from ever changing, enter a dated version such as sonic-3.6-2026-08-27. Models Cartesia has retired, such as sonic-2 or sonic-turbo, speak with sonic-3.6.
SpeedSpeaking pace. 1.0 is the voice’s natural pace; higher is faster and lower is slower. Accepts 0.6 to 1.5. Default: 1.0.

Output

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

Example

A cosmetics brand wants its agent to sound like the voice it already uses in its ads, created in Cartesia.

  1. Add Cartesia TTS and connect it to the TTS connector of the Voice Agent.
  2. In Credential, choose the Cartesia API credential.
  3. Paste the brand voice’s ID into Voice ID.
  4. Test the agent in the playground and listen to how it sounds.

Good practices

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