elevenlabs · Schema

ElevenLabs Voice

Represents a voice in the ElevenLabs platform, including pre-built, cloned, and designed voices with their associated metadata, settings, and audio samples.

Properties

Name Type Description
voice_id string Unique identifier for the voice.
name string Display name of the voice.
category string The category indicating how the voice was created.
description string Human-readable description of the voice characteristics and intended use.
labels object Key-value labels describing voice characteristics such as accent, age, gender, and use case.
preview_url string URL to a preview audio sample of the voice.
settings object
samples array Audio samples associated with the voice, used for cloning and preview.
sharing object Sharing and publication status of the voice.
high_quality_base_model_ids array List of model identifiers that produce the best results with this voice.
View JSON Schema on GitHub

JSON Schema

elevenlabs-voice-schema.json Raw ↑
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://elevenlabs.io/schemas/elevenlabs/voice.json",
  "title": "ElevenLabs Voice",
  "description": "Represents a voice in the ElevenLabs platform, including pre-built, cloned, and designed voices with their associated metadata, settings, and audio samples.",
  "type": "object",
  "required": ["voice_id", "name"],
  "properties": {
    "voice_id": {
      "type": "string",
      "description": "Unique identifier for the voice."
    },
    "name": {
      "type": "string",
      "description": "Display name of the voice.",
      "minLength": 1,
      "maxLength": 200
    },
    "category": {
      "type": "string",
      "description": "The category indicating how the voice was created.",
      "enum": ["premade", "cloned", "designed", "professional"]
    },
    "description": {
      "type": "string",
      "description": "Human-readable description of the voice characteristics and intended use."
    },
    "labels": {
      "type": "object",
      "description": "Key-value labels describing voice characteristics such as accent, age, gender, and use case.",
      "additionalProperties": {
        "type": "string"
      }
    },
    "preview_url": {
      "type": "string",
      "format": "uri",
      "description": "URL to a preview audio sample of the voice."
    },
    "settings": {
      "$ref": "#/$defs/VoiceSettings"
    },
    "samples": {
      "type": "array",
      "description": "Audio samples associated with the voice, used for cloning and preview.",
      "items": {
        "$ref": "#/$defs/VoiceSample"
      }
    },
    "sharing": {
      "type": "object",
      "description": "Sharing and publication status of the voice.",
      "properties": {
        "status": {
          "type": "string",
          "description": "Whether the voice is shared publicly.",
          "enum": ["enabled", "disabled"]
        },
        "public_owner_id": {
          "type": "string",
          "description": "Public identifier of the voice owner."
        },
        "cloned_by_count": {
          "type": "integer",
          "description": "Number of users who have cloned or added this voice.",
          "minimum": 0
        }
      }
    },
    "high_quality_base_model_ids": {
      "type": "array",
      "description": "List of model identifiers that produce the best results with this voice.",
      "items": {
        "type": "string"
      }
    }
  },
  "$defs": {
    "VoiceSettings": {
      "type": "object",
      "description": "Configuration parameters that control the voice's speech synthesis characteristics.",
      "properties": {
        "stability": {
          "type": "number",
          "description": "Controls the consistency of the voice output. Higher values produce more stable, predictable speech. Lower values introduce more variation.",
          "minimum": 0,
          "maximum": 1
        },
        "similarity_boost": {
          "type": "number",
          "description": "Controls how closely the generated speech matches the original voice. Higher values increase fidelity to the target voice.",
          "minimum": 0,
          "maximum": 1
        },
        "style": {
          "type": "number",
          "description": "Controls the expressiveness and stylistic variation of the speech delivery.",
          "minimum": 0,
          "maximum": 1,
          "default": 0
        },
        "use_speaker_boost": {
          "type": "boolean",
          "description": "Enables speaker boost processing to increase voice clarity and reduce artifacts.",
          "default": true
        }
      }
    },
    "VoiceSample": {
      "type": "object",
      "description": "An audio sample associated with a voice, used for cloning and demonstration.",
      "properties": {
        "sample_id": {
          "type": "string",
          "description": "Unique identifier for the audio sample."
        },
        "file_name": {
          "type": "string",
          "description": "Original file name of the uploaded sample."
        },
        "mime_type": {
          "type": "string",
          "description": "MIME type of the audio sample.",
          "pattern": "^audio/"
        },
        "size_bytes": {
          "type": "integer",
          "description": "Size of the audio sample file in bytes.",
          "minimum": 0
        },
        "hash": {
          "type": "string",
          "description": "Hash of the audio sample content for integrity verification."
        }
      }
    }
  }
}