elevenlabs · Schema

TextToSpeechRequest

Properties

Name Type Description
text string The text to convert to speech. Maximum length varies by model.
model_id string The identifier of the model to use. Use GET /v1/models to list available models. The model must support text to speech.
voice_settings object
pronunciation_dictionary_locators array A list of pronunciation dictionary locators to apply to the text. Applied in order, with a maximum of 3 locators per request.
seed integer A seed value for deterministic generation. Using the same seed with the same parameters produces the same audio output.
previous_text string Text that came before the current text for context continuity.
next_text string Text that comes after the current text for context continuity.
language_code string Language code for the text, in ISO 639-1 format. Helps the model produce more accurate pronunciation for the specified language.
View JSON Schema on GitHub

JSON Schema

elevenlabs-texttospeechrequest-schema.json Raw ↑ 
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "#/components/schemas/TextToSpeechRequest",
  "title": "TextToSpeechRequest",
  "type": "object",
  "required": [
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "description": "The text to convert to speech. Maximum length varies by model."
    },
    "model_id": {
      "type": "string",
      "description": "The identifier of the model to use. Use GET /v1/models to list available models. The model must support text to speech.",
      "default": "eleven_monolingual_v1"
    },
    "voice_settings": {
      "$ref": "#/components/schemas/VoiceSettings"
    },
    "pronunciation_dictionary_locators": {
      "type": "array",
      "description": "A list of pronunciation dictionary locators to apply to the text. Applied in order, with a maximum of 3 locators per request.",
      "items": {
        "$ref": "#/components/schemas/PronunciationDictionaryLocator"
      },
      "maxItems": 3
    },
    "seed": {
      "type": "integer",
      "description": "A seed value for deterministic generation. Using the same seed with the same parameters produces the same audio output."
    },
    "previous_text": {
      "type": "string",
      "description": "Text that came before the current text for context continuity."
    },
    "next_text": {
      "type": "string",
      "description": "Text that comes after the current text for context continuity."
    },
    "language_code": {
      "type": "string",
      "description": "Language code for the text, in ISO 639-1 format. Helps the model produce more accurate pronunciation for the specified language."
    }
  }
}