← All nodes
Transforms a_tts

Text to Speech

Synthesises speech audio from text via Deepgram / OpenAI / ElevenLabs.

What does it do?

Converts text to speech (Text-to-Speech) creating an audio file.

How does it work?

Takes the bot's reply and processes it with ultra-realistic synthetic voices, returning an MP3 or OGG file.

Why use it?

So your bot can send voice notes on WhatsApp. Surprise your customers by talking back to them!

Inputs

nametype
text string

Outputs

nametype
url string
provider string
model string
duration_sec number
bytes number
chars number

Branches

Fixed branches

  • out — Output

Configuration

model string optional
voice string optional
text_field string required default: "text"
format "mp3" | "wav" | "opus" | "linear16" required default: "mp3"
persist_to_r2 boolean required default: true
memory_key string optional

Default configuration

{
  "text_field": "text",
  "format": "mp3",
  "persist_to_r2": true
}

Emitted events

This node does not publish events on the pubsub channel.