Skip to content
Nappai Documentation

Piper (local)

Piper (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. Its voice is plainer than the cloud services.

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

  • You want a local voice in Spanish, English, French, German or Italian.
  • You do not want the agent’s answers to leave the NappAI server.
  • You want to choose between a female and a male voice in Spanish.

Configuration

FieldWhat it does
VoiceThe voice. The list offers one per language: es_ES-sharvard-medium (Spanish, default), en_US-lessac-medium (English), fr_FR-siwis-medium (French), de_DE-thorsten-medium (German) and it_IT-riccardo-medium (Italian). You can type the name of another Piper voice; the first call that uses it will take longer to start.
SpeakerWhich speaker to use, for voices that have more than one. The Spanish voice has F (female, default) and M (male). Empty, the voice’s default speaker is used.
SpeedSpeaking pace. 1.0 is the voice’s natural pace; higher is faster and lower is slower. Default: 1.0.

Advanced options

FieldWhat it does
Voice PathLeave it empty. Only needed if your installation’s technical team gives you another location for the voice.

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 school wants an agent that gives out timetables in French.

  1. Add Piper (local) and connect it to the TTS connector of the Voice Agent.
  2. Choose fr_FR-siwis-medium in Voice and leave Speaker empty.
  3. Set fr as the language in the STT.
  4. Test the agent in the playground and listen to how it sounds.

Good practices

  • Choose a voice in the same language the STT expects: each Piper voice speaks one language.
  • The differences between local and cloud voices are explained in Quality, noise and latency.