Cartesia

Initialize the voice for the TTS service. Select any voice from the available Cartesia voices.

{
  "service_options": {
    "cartesia": {
      "voice": "820a3788-2b37-4d21-847a-b65d8a68c99a"
    }
  }
}

The audio output sample rate in Hz for the TTS audio.

The sample rate must be one of these values: 8000, 16000, 22050, 24000, 44100, 48000.

{
  "service_options": {
    "cartesia": {
      "sample_rate": 24000
    }
  }
}

Select from the available Cartesia models.

For the best performance for English, we recommend using the "sonic-english" model. For multilingual, we recommend using the "sonic-multilingual" model.

{
  "name": "model",
  "value": "sonic-english"
}

The voice you want your TTS service to use. Select any voice from the available Cartesia voices.

You can click the “Try it out” button on https://cartesia.ai/sonic to sign up for a free account and sample the built-in voices. You can also find voice IDs from their playground page.

{
  "name": "voice",
  "value": "820a3788-2b37-4d21-847a-b65d8a68c99a"
}

The language you want your TTS service to use. To select a non-English language, select the sonic-mulitlingual model and specify the language. Learn more.

{
  "name": "model",
  "value": "sonic-mulitlingual"
},
{
  "name": "language",
  "value": "es"
}

The rate at which the text is spoken. Learn more.

Speed options include slowest, slow, normal, fast, and fastest.

For more granular control, you can define speed as a number within the range [-1.0, 1.0]. A value of 0 represents the default speed, while negative values slow down the speech and positive values speed it up.

{
  "name": "speed",
  "value": "fast"
}

The emotion parameter is an array of “tags” in the form emotion_name:level. For example, positivity:high or curiosity. Learn more.

Emotion names: anger, positivity, surprise, sadness, curiosity.

Emotion levels: lowest, low, (omit for moderate addition of emotion), high, highest.

{
  "name": "emotion",
  "value": ["positivity:high", "curiosity"]
}

Control whether the TTS service filters out markdown, code blocks, or tables from its output.

Basic markdown filtering is enabled by default. Enable code and table filtering as needed. Filtering code and tables can help the TTS avoid mistakes.

{
  "name": "text_filter",
  "value": {
    "enable_text_filter": true,
    "filter_code": true,
    "filter_tables": true
  }
}