Skip to content
Nappai Documentation

ElevenLabs STT

ElevenLabs 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 ElevenLabs’ 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

  • You already use ElevenLabs TTS as the agent’s voice and want one provider and one credential.
  • You need accurate cloud recognition for calls in many languages.
  • You mostly expect one language, but some callers use another and you want the agent to understand them.

Configuration

You need an Eleven Labs API credential with your ElevenLabs account key. See Credentials.

FieldWhat it does
Credential (required)The Eleven Labs API credential used to connect to the service.
LanguageThe caller’s main language, for example es or en. Default: es.
Detect LanguageWhen on, besides the main language the agent understands the other languages in Supported Languages. Off by default.
ModelThe ElevenLabs model that transcribes in real time. Default and only option: scribe_v2_realtime.

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 travel agency works in Spanish but gets calls from English customers.

  1. Add ElevenLabs STT and connect it to the STT connector of the Voice Agent.
  2. In Credential, choose the Eleven Labs API credential.
  3. Leave Language as es, turn on Detect Language and leave es and en in Supported Languages.
  4. Test in the playground with one sentence in each language.

Good practices

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