Gladia STT
Gladia 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 Gladia’s 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 need the call audio processed inside the European Union.
- Your callers mix languages, even within the same sentence.
- You want cloud recognition that transcribes while the caller speaks.
Configuration
You need a Gladia API credential with your Gladia account key. See Credentials.
| Field | What it does |
|---|---|
| Credential (required) | The Gladia API credential used to connect to the service. |
| Language | Code of the language the caller is expected to speak, for example es or en. Default: es. |
| Detect Language | When on, Gladia follows the caller among the languages in Supported Languages, even if they switch mid-sentence. Off by default. |
| Model | The Gladia model. Default and only option: solaria-1. |
| Region | Where the audio is processed: eu-west (default), which keeps it in the European Union, or us-west. |
Advanced options
| Field | What it does |
|---|---|
| Supported Languages | Languages 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 insurer with customers in Spain wants the call audio to stay in Europe.
- Add Gladia STT and connect it to the STT connector of the Voice Agent.
- In Credential, choose the Gladia API credential.
- Leave Region as
eu-westand Language ases. - Test the agent in the playground.
Good practices
- Gladia bills the usage to your own Gladia account. Check your usage there.
- If you prefer the audio never to leave the NappAI server, use a local STT such as Parakeet (local, multilingual).
Related components
- Voice Agent: the node this component connects to.
- Parakeet (local, multilingual): local speech recognition, no credential needed.
- Azure Speech STT: cloud recognition that also understands Catalan, Galician and Basque.