Skip to content
Nappai Documentation

Inworld TTS

Inworld 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 Inworld service.

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 want to use a specific voice from your Inworld console.
  • You use Inworld STT and want one provider and one credential.
  • You want to choose between a voice that answers sooner and a more expressive one.

Configuration

You need an Inworld API credential with your Inworld account key. See Credentials.

FieldWhat it does
Credential (required)The Inworld API credential used to connect to the service.
VoiceThe Inworld voice name, as the Inworld console shows it. Empty, a default voice is used.
Modelinworld-tts-2-flash (default) answers soonest; inworld-tts-2 is the most expressive. inworld-tts-1.5-max and inworld-tts-1.5-mini, tuned for English, are also available.
SpeedSpeaking pace. 1.0 is the voice’s natural pace; higher is faster and lower is slower. 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 game studio supports its players with an agent that uses the voice of one of its characters, created in Inworld.

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

Good practices

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