Skip to content

Cartesia Text to Speech

Cartesia Text to Speech reads out the text you give it with a Cartesia Sonic voice and returns an audio file: MP3 by default or WAV if you choose. If you don’t pick a voice, it uses a Spanish one. If the text is long, it splits it at the end of sentences, reads each part and joins them into a single file.

You need a Cartesia API credential with your Cartesia account key. See Credentials. The text is sent to Cartesia to produce the audio.

This is not the voice node for calls: to speak to a caller during a live call, the Voice Agent uses the Cartesia TTS node. This component returns a finished file.

When to use it

  • Send your customers a voice note confirming an appointment or an order.
  • Use in your audio files the same Cartesia voice your voice agent already speaks with.
  • Let an agent answer with audio, using the component as a tool.
  • Produce the audio for a list of texts in one go with Batch Mode.

Configuration

FieldWhat it does
API Key (required)Your Cartesia key. The key is filled in for you when you choose your Cartesia credential.
Text to Speech (required)The text to read out. You can type it or connect it from another component.
Voice IDThe voice’s identifier, as the Cartesia console shows it. Empty by default: a Spanish voice is used.
LanguageThe language of the text, for example es or en. Default: es. It must match the text and the voice.
ModelThe voice model. Default: sonic-3.6, the latest. sonic-3.5, sonic-3 and sonic-latest are also available. If a saved flow has a model Cartesia has retired, such as sonic-2, it is read with sonic-3.6.

Advanced options

FieldWhat it does
SpeedThe reading speed, from 0.6 to 1.5. Default: 1, the voice’s natural pace.
Audio formatThe file format: mp3 (default) or wav. Cartesia does not produce OGG.

Output

The Data output returns an audio file with the text read out, in the chosen format. Its name is the first words of the text, without accents or punctuation (for example, Hola_buenos_dias_Su.mp3 or .wav).

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 tools are in Key concepts.

Example

A garage answers the phone with a voice agent that uses a Cartesia voice. So that WhatsApp notices sound the same, the flow that tells customers their car is ready uses Cartesia Text to Speech with the same Voice ID as the agent and sends the audio to the customer.

Tips

  • If you change Language, also pick a voice that speaks that language: the default voice is Spanish.
  • Measured in our test environment on 3 November 2026: the WAV of the sentence “Hola, buenos días. Su cita está confirmada para el martes a las diez y media.” was produced in 0.7 s.