Skip to content
Nappai Documentation

Gemini STT

Gemini 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 Google’s Gemini live transcription.

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

  • The agent’s model is already Gemini and you want to use the same Google key for hearing.
  • You want Google’s cloud recognition for calls in Spanish or English.
  • Callers switch language and you want the agent to follow them among a list of languages.

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.
LanguageCode of the language the caller is expected to speak, for example es or en. Default: es.
Detect LanguageWhen on, Gemini recognises the caller’s language among those in Supported Languages. Adds a little wait to each turn. Off by default.
ModelThe live transcription model. Default: gemini-3.5-transcribe-live; also gemini-2.5-flash. Leave the default unless Google publishes a newer one.

Advanced options

FieldWhat it does
Supported LanguagesLanguages detection can switch between. Default: es and en. Only used when Detect Language is on.

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

An online shop already uses Gemini as its voice agent’s model.

  1. Add Gemini STT and connect it to the STT connector of the Voice Agent.
  2. In Credential, choose the same Google Gemini credential the model uses.
  3. Leave Language as es and Model at its default.
  4. Test the agent in the playground.

Good practices

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