Skip to content
Nappai Documentation

Pocket TTS (local)

Pocket TTS (local) is one of the components that give a voice agent its voice: it turns the agent’s answers into audio for the caller to hear. It runs on the NappAI server: no credential, the text is not sent to any outside provider and there is no per-word cost. It is the local voice that starts speaking soonest. It only speaks Spanish, and reads amounts, times, dates and phone numbers out in words.

It plugs into the TTS connector of the Voice Agent node. It holds the voice settings the agent uses on every call.

When to use it

  • The agent’s first sentence takes long to sound and you want it to answer sooner.
  • Your calls are in Spanish only.
  • You do not want the agent’s answers to leave the NappAI server.

Configuration

FieldWhat it does
VoiceThe voice. lola (default) was recorded in Spanish and sounds like neutral Latin American Spanish. The others are speakers of other languages talking Spanish, each with their own accent.

This component has no speed field.

Output

The TTS output holds the voice settings. It connects to the TTS connector of the Voice Agent node, or to Fallback TTS when you turn on Fallback Engines and want it as a backup. The editor will not let you plug it into an STT connector by mistake.

Example

A dental clinic wants its agent to answer without long pauses when confirming appointments.

  1. Add Pocket TTS (local) and connect it to the TTS connector of the Voice Agent.
  2. Leave Voice as lola.
  3. Use es as the language in the STT.
  4. Test the agent in the playground and listen to how it sounds.

Good practices

  • Do not use it if the agent may need to speak another language: it only speaks Spanish.
  • The differences between local and cloud voices are explained in Quality, noise and latency.