Skip to content
Nappai Documentation

Wit.ai STT

Wit.ai 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 the Wit.ai speech recognition service.

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 have a Wit.ai app and want to reuse it for the voice agent.
  • You are running simple tests of an agent in a single language.

Configuration

You need a WitAi credential with your Wit.ai app access token. See Credentials.

FieldWhat it does
Credential (required)The WitAi credential used to connect to the service.
LanguageCode of the language the caller is expected to speak, for example es or en. Default: es.

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 team wants to test a voice agent with the Spanish Wit.ai app it already has.

  1. Add Wit.ai STT and connect it to the STT connector of the Voice Agent.
  2. In Credential, choose the WitAi credential with the app token.
  3. Test the agent in the playground.

Good practices