Skip to content
Nappai Documentation

Azure Speech STT

Azure Speech 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 Microsoft’s Azure Speech recognition service. It transcribes while the caller speaks, so the word-based interruption settings of the Voice Agent, such as Minimum Words To Interrupt, work with it.

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

  • Your company already works with Microsoft Azure and you want the audio processed in your own Azure resource.
  • You take calls in Catalan, Galician or Basque, languages NappAI’s local STTs do not understand.
  • Callers switch language mid-call and you want the agent to follow them.
  • You want callers to be able to interrupt the agent with a few words.

Configuration

You need an Azure Speech credential with your Azure speech resource key and its region. See Credentials.

FieldWhat it does
Credential (required)The Azure Speech credential used to connect to the service.
LanguageCode of the language the caller is expected to speak, for example es, en or ca. Default: es.
Detect LanguageWhen on, Azure keeps identifying the caller’s language among those in Supported Languages and the agent switches language with them. Adds a little wait to each turn. Off by default.

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

A Catalan cooperative takes its members’ calls in Catalan and Spanish.

  1. Add Azure Speech STT and connect it to the STT connector of the Voice Agent.
  2. In Credential, choose the cooperative’s Azure Speech credential.
  3. Type ca in Language, turn on Detect Language and leave ca and es in Supported Languages.
  4. Test the agent in the playground speaking both languages.

Good practices

  • Turn on Detect Language only if you really get calls in several languages: every turn takes a little longer.
  • Azure bills the usage to your own Azure account. Check your usage there.