Piper TTS
Piper TTS reads out the text you give it and returns a WAV audio file. You pick the voice from a list where each option shows its language, the voice’s name and its quality. It doesn’t need a credential.
When to use it
- Send a voice note confirming an appointment or an order.
- Produce short voice-overs for announcements or welcome messages.
- Turn text into audio in a language for which you have a voice available.
- Let an agent answer with audio, using the component as a tool.
Configuration
| Field | What it does |
|---|---|
| Language | The voice to use. Each option shows the language, the voice’s name and its quality, for example Language: Spanish (Spain) | Voice: … | Quality: …. The first one in the list is selected by default. Use the refresh button to reload the list. |
| Text to Speech | The text to read out. You can type it or connect it from another component. |
Output
The Data output returns a WAV audio file with the text read out. Its name is the first ten characters of the text.
Connect it to a component that stores or sends files. An agent can also use the component as a tool to create audio when it needs to; see what Tool Mode is in Key concepts.
Example
Every afternoon your reminders flow writes the text “Le recordamos su cita mañana a las diez”. You pick a Spanish voice in Language, connect the text to Text to Speech and send the audio to the patient.
Related components
- Supertonic TTS and Kokoro TTS: other voices to turn text into audio.
- To speak during a call, use the Voice Agent’s Piper node.