Models

Get Models

Retrieve a list of all available text-to-speech models.

Request

curl -X GET "https://api.elevenlabs8.com/api/tts/models/" \
  -H "X-API-KEY: your_api_key_here"

Response

Response

[
  {
    "model_id": "eleven_v3",
    "name": "Eleven Multilingual v3",
    "can_be_finetuned": false,
    "can_do_text_to_speech": true,
    "can_do_voice_conversion": false,
    "can_use_style": true,
    "can_use_speaker_boost": true,
    "serves_pro_voices": true,
    "token_cost_factor": 1,
    "description": "Latest multilingual model with improved quality",
    "requires_alpha_access": false,
    "max_characters_request_free_user": 2500,
    "max_characters_request_subscribed_user": 5000,
    "maximum_text_length_per_request": 5000,
    "languages": [
      {
        "language_id": "en",
        "name": "English"
      },
      {
        "language_id": "es",
        "name": "Spanish"
      },
      {
        "language_id": "fr",
        "name": "French"
      },
      {
        "language_id": "de",
        "name": "German"
      },
      {
        "language_id": "it",
        "name": "Italian"
      },
      {
        "language_id": "pt",
        "name": "Portuguese"
      },
      {
        "language_id": "pl",
        "name": "Polish"
      },
      {
        "language_id": "hi",
        "name": "Hindi"
      },
      {
        "language_id": "ja",
        "name": "Japanese"
      },
      {
        "language_id": "ko",
        "name": "Korean"
      },
      {
        "language_id": "zh",
        "name": "Chinese"
      }
    ],
    "model_rates": {
      "character_cost_multiplier": 1
    },
    "concurrency_group": "standard"
  },
  {
    "model_id": "eleven_flash_v2_5",
    "name": "Eleven Flash v2.5",
    "can_be_finetuned": false,
    "can_do_text_to_speech": true,
    "can_do_voice_conversion": false,
    "can_use_style": false,
    "can_use_speaker_boost": true,
    "serves_pro_voices": false,
    "token_cost_factor": 0.5,
    "description": "Fast and efficient model for quick generation",
    "requires_alpha_access": false,
    "max_characters_request_free_user": 1000,
    "max_characters_request_subscribed_user": 2500,
    "maximum_text_length_per_request": 2500,
    "languages": [
      {
        "language_id": "en",
        "name": "English"
      }
    ],
    "model_rates": {
      "character_cost_multiplier": 0.5
    },
    "concurrency_group": "fast"
  }
]

Model Properties

Property	Type	Description
model_id	string	Unique model identifier
name	string	Human-readable model name
can_be_finetuned	boolean	Whether the model can be fine-tuned
can_do_text_to_speech	boolean	Whether the model supports TTS
can_do_voice_conversion	boolean	Whether the model supports voice conversion
can_use_style	boolean	Whether the model supports style control
can_use_speaker_boost	boolean	Whether the model supports speaker boost
serves_pro_voices	boolean	Whether the model serves pro voices
token_cost_factor	integer	Cost multiplier for token usage
description	string	Model description
requires_alpha_access	boolean	Whether alpha access is required
max_characters_request_free_user	integer	Max characters for free users
max_characters_request_subscribed_user	integer	Max characters for subscribed users
maximum_text_length_per_request	integer	Maximum text length per request
languages	array	Supported languages
model_rates	object	Model pricing information
concurrency_group	string	Concurrency group (standard, fast, etc.)

Language Object

Property	Type	Description
language_id	string	Language code (e.g., “en”, “es”)
name	string	Language name (e.g., “English”, “Spanish”)

Model Rates Object

Property	Type	Description
character_cost_multiplier	integer	Cost multiplier for character usage

Concurrency Groups

Group	Description
standard	Standard processing speed
fast	Fast processing speed
premium	Premium processing speed

Model Capabilities

Capability	Description
can_be_finetuned	Model can be customized with custom training
can_do_text_to_speech	Model can convert text to speech
can_do_voice_conversion	Model can convert between voices
can_use_style	Model supports style control parameters
can_use_speaker_boost	Model supports speaker boost enhancement
serves_pro_voices	Model can use professional voice quality

View Detailed Model Information

For detailed information about each model, visit the Models page which provides comprehensive documentation about model capabilities, usage examples, and best practices.