Skip to content

Inworld Text to Speech

Inworld Text to Speech reads out the text you give it with an Inworld voice and returns an audio file: MP3 by default, WAV or OGG if you choose. 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 an Inworld API credential with your Inworld account key. See Credentials. The text is sent to Inworld 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 Inworld TTS node. This component returns a finished file.

When to use it

  • Send your customers a voice note confirming an appointment or an order.
  • Turn an agent’s answer into audio for a messaging channel.
  • 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 Inworld key. The key is filled in for you when you choose your Inworld credential.
Text to Speech (required)The text to read out. You can type it or connect it from another component.
VoiceThe name of the Inworld voice, as the Inworld console shows it. Default: Ashley. You can type the name of a voice of your own that you created there.
ModelThe voice model. Default: inworld-tts-2-flash, the fastest. inworld-tts-2 is the most expressive. inworld-tts-1.5-max and inworld-tts-1.5-mini are also available; the latter is tuned for English.

Advanced options

FieldWhat it does
SpeedThe reading speed, from 0.5 to 1.5. Default: 1, the voice’s natural pace. Inworld recommends not going below 0.8.
Audio formatThe file format: mp3 (default), wav or ogg. MP3 is small and plays everywhere (WhatsApp, email, browser); WAV is uncompressed; OGG suits voice notes.

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).

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 dental clinic confirms appointments over WhatsApp. When a booking is made, the flow writes “Hola, buenos días. Su cita está confirmada para el martes a las diez y media.” and connects it to Text to Speech. With Audio format set to ogg, the resulting audio is sent to the patient as a voice note.

Tips

  • Write the text the way it would be said aloud: short sentences and no abbreviations the voice cannot read.
  • Measured in our test environment on 3 November 2026: the MP3 of the sentence “Hola, buenos días. Su cita está confirmada para el martes a las diez y media.” was produced in 0.7 s.