Skip to content
Nappai Documentation

Gemini TTS

Gemini 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 Google’s Gemini voices. There are thirty voices and all of them speak any language: the language comes from the text the agent says.

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

  • The agent’s model is already Gemini and you want to use the same Google key for the voice.
  • You want to describe in words how the agent should sound, for example warm and unhurried.
  • You take calls in several languages and want the same voice in all of them.

Configuration

You need a Google Gemini credential with your Google AI key, the same one the Gemini model uses. See Credentials.

FieldWhat it does
Credential (required)The Google Gemini credential used to connect to the service.
VoiceOne of the Gemini voices, such as Kore (default), Puck or Zephyr.
Modelgemini-2.5-flash-tts (default) is the stable one; also available are gemini-3.1-flash-tts-preview, newer and subject to change, gemini-2.5-flash-lite-preview-tts and gemini-2.5-pro-tts.

Advanced options

FieldWhat it does
Voice StyleHow the voice should sound, in plain words: for example “warm and unhurried” or “brisk and professional”. It also sets the pace, since this component has no speed field.

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 hotel wants a calm, friendly voice for its phone reception.

  1. Add Gemini TTS and connect it to the TTS connector of the Voice Agent.
  2. In Credential, choose the Google Gemini credential.
  3. Pick a voice in Voice and write in Voice Style: “warm, friendly and unhurried”.
  4. Test the agent in the playground and listen to how it sounds.

Good practices

  • Try several voices in the playground before deciding: all of them speak your language, but each has its own tone.
  • Google bills the usage to your own Google account. Check your usage there.