elevenlabs-voices

Server path: /elevenlabs-voices | Type: Application | PCID required: Yes

Tools

Tool	Description
`elevenlabs_voices_add_sharing_voice`	Add Shared Voice
`elevenlabs_voices_add_voice`	Add Voice
`elevenlabs_voices_create_voice`	Create A New Voice From Voice Preview
`elevenlabs_voices_delete_sample`	Delete Sample
`elevenlabs_voices_delete_voice`	Delete Voice
`elevenlabs_voices_edit_voice`	Edit Voice
`elevenlabs_voices_edit_voice_settings`	Edit Voice Settings
`elevenlabs_voices_get_audio_from_sample`	Get Audio From Sample
`elevenlabs_voices_get_library_voices`	Get Voices
`elevenlabs_voices_get_models`	Get Models
`elevenlabs_voices_get_similar_library_voices`	Get Similar Library Voices
`elevenlabs_voices_get_user_info`	Get User Info
`elevenlabs_voices_get_user_subscription_info`	Get User Subscription Info
`elevenlabs_voices_get_user_voices_v2`	Get Voices V2
`elevenlabs_voices_get_voice_by_id`	Get Voice
`elevenlabs_voices_get_voice_settings`	Get Voice Settings
`elevenlabs_voices_get_voice_settings_default`	Get Default Voice Settings.
`elevenlabs_voices_get_voices`	List Voices
`elevenlabs_voices_text_to_voice`	Generate A Voice Preview From Description
`elevenlabs_voices_text_to_voice_design`	Design A Voice.
`elevenlabs_voices_text_to_voice_preview_stream`	Text To Voice Preview Streaming
`elevenlabs_voices_text_to_voice_remix`	Remix A Voice.

elevenlabs_voices_add_sharing_voice

Add Shared Voice Parameters:

Parameter	Type	Required	Default	Description
`public_user_id`	string	Yes	—	Public user ID used to publicly identify ElevenLabs users.
`voice_id`	string	Yes	—	Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices.
`bookmarked`	boolean	No	—	The bookmarked value
`new_name`	string	Yes	—	The name that identifies this voice. This will be displayed in the dropdown of the website.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "public_user_id": {
      "type": "string",
      "description": "Public user ID used to publicly identify ElevenLabs users."
    },
    "voice_id": {
      "type": "string",
      "description": "Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices."
    },
    "bookmarked": {
      "type": "boolean",
      "description": "The bookmarked value"
    },
    "new_name": {
      "type": "string",
      "description": "The name that identifies this voice. This will be displayed in the dropdown of the website."
    }
  },
  "required": [
    "PCID",
    "public_user_id",
    "voice_id",
    "new_name"
  ]
}

elevenlabs_voices_add_voice

Add Voice Parameters:

Parameter	Type	Required	Default	Description
`description`	object	No	—	A description of the voice.
`files`	any[]	Yes	—	A list of file paths to audio recordings intended for voice cloning.
`labels`	object	No	—	Labels for the voice. Keys can be language, accent, gender, or age.
`name`	string	Yes	—	The name that identifies this voice. This will be displayed in the dropdown of the website.
`remove_background_noise`	boolean	No	—	If set will remove background noise for voice samples using our audio isolation model. If the samples do not include background noise, it can make the quality worse.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "description": {
      "description": "A description of the voice."
    },
    "files": {
      "type": "array",
      "description": "A list of file paths to audio recordings intended for voice cloning."
    },
    "labels": {
      "description": "Labels for the voice. Keys can be language, accent, gender, or age."
    },
    "name": {
      "type": "string",
      "description": "The name that identifies this voice. This will be displayed in the dropdown of the website."
    },
    "remove_background_noise": {
      "type": "boolean",
      "description": "If set will remove background noise for voice samples using our audio isolation model. If the samples do not include background noise, it can make the quality worse."
    }
  },
  "required": [
    "PCID",
    "files",
    "name"
  ]
}

elevenlabs_voices_create_voice

Create A New Voice From Voice Preview Parameters:

Parameter	Type	Required	Default	Description
`generated_voice_id`	string	Yes	—	The generated_voice_id to create, call POST /v1/text-to-voice/create-previews and fetch the generated_voice_id from the response header if don’t have one yet.
`labels`	object	No	—	Optional, metadata to add to the created voice. Defaults to None.
`played_not_selected_voice_ids`	object	No	—	List of voice ids that the user has played but not selected. Used for RLHF.
`voice_description`	string	Yes	—	Description to use for the created voice.
`voice_name`	string	Yes	—	Name to use for the created voice.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "generated_voice_id": {
      "type": "string",
      "description": "The generated_voice_id to create, call POST /v1/text-to-voice/create-previews and fetch the generated_voice_id from the response header if don't have one yet."
    },
    "labels": {
      "description": "Optional, metadata to add to the created voice. Defaults to None."
    },
    "played_not_selected_voice_ids": {
      "description": "List of voice ids that the user has played but not selected. Used for RLHF."
    },
    "voice_description": {
      "type": "string",
      "description": "Description to use for the created voice."
    },
    "voice_name": {
      "type": "string",
      "description": "Name to use for the created voice."
    }
  },
  "required": [
    "PCID",
    "generated_voice_id",
    "voice_description",
    "voice_name"
  ]
}

elevenlabs_voices_delete_sample

Delete Sample Parameters:

Parameter	Type	Required	Default	Description
`voice_id`	string	Yes	—	Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices.
`sample_id`	string	Yes	—	Sample ID to be used, you can use GET https://api.elevenlabs.io/v1/voices/{voice_id} to list all the available samples for a voice.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "voice_id": {
      "type": "string",
      "description": "Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices."
    },
    "sample_id": {
      "type": "string",
      "description": "Sample ID to be used, you can use GET https://api.elevenlabs.io/v1/voices/{voice_id} to list all the available samples for a voice."
    }
  },
  "required": [
    "PCID",
    "voice_id",
    "sample_id"
  ]
}

elevenlabs_voices_delete_voice

Delete Voice Parameters:

Parameter	Type	Required	Default	Description
`voice_id`	string	Yes	—	Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "voice_id": {
      "type": "string",
      "description": "Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices."
    }
  },
  "required": [
    "PCID",
    "voice_id"
  ]
}

elevenlabs_voices_edit_voice

Edit Voice Parameters:

Parameter	Type	Required	Default	Description
`voice_id`	string	Yes	—	Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices.
`description`	object	No	—	A description of the voice.
`files`	any[]	No	—	Audio files to add to the voice
`labels`	object	No	—	Labels for the voice. Keys can be language, accent, gender, or age.
`name`	string	Yes	—	The name that identifies this voice. This will be displayed in the dropdown of the website.
`remove_background_noise`	boolean	No	—	If set will remove background noise for voice samples using our audio isolation model. If the samples do not include background noise, it can make the quality worse.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "voice_id": {
      "type": "string",
      "description": "Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices."
    },
    "description": {
      "description": "A description of the voice."
    },
    "files": {
      "type": "array",
      "description": "Audio files to add to the voice"
    },
    "labels": {
      "description": "Labels for the voice. Keys can be language, accent, gender, or age."
    },
    "name": {
      "type": "string",
      "description": "The name that identifies this voice. This will be displayed in the dropdown of the website."
    },
    "remove_background_noise": {
      "type": "boolean",
      "description": "If set will remove background noise for voice samples using our audio isolation model. If the samples do not include background noise, it can make the quality worse."
    }
  },
  "required": [
    "PCID",
    "voice_id",
    "name"
  ]
}

elevenlabs_voices_edit_voice_settings

Edit Voice Settings Parameters:

Parameter	Type	Required	Default	Description
`voice_id`	string	Yes	—	Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices.
`similarity_boost`	object	No	—	Determines how closely the AI should adhere to the original voice when attempting to replicate it.
`speed`	object	No	—	Adjusts the speed of the voice. A value of 1.0 is the default speed, while values less than 1.0 slow down the speech, and values greater than 1.0 speed it up.
`stability`	object	No	—	Determines how stable the voice is and the randomness between each generation. Lower values introduce broader emotional range for the voice. Higher values can result in a monotonous voice with limited emotion.
`style`	object	No	—	Determines the style exaggeration of the voice. This setting attempts to amplify the style of the original speaker. It does consume additional computational resources and might increase latency if set to anything other than 0.
`use_speaker_boost`	object	No	—	This setting boosts the similarity to the original speaker. Using this setting requires a slightly higher computational load, which in turn increases latency.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "voice_id": {
      "type": "string",
      "description": "Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices."
    },
    "similarity_boost": {
      "description": "Determines how closely the AI should adhere to the original voice when attempting to replicate it."
    },
    "speed": {
      "description": "Adjusts the speed of the voice. A value of 1.0 is the default speed, while values less than 1.0 slow down the speech, and values greater than 1.0 speed it up."
    },
    "stability": {
      "description": "Determines how stable the voice is and the randomness between each generation. Lower values introduce broader emotional range for the voice. Higher values can result in a monotonous voice with limited emotion."
    },
    "style": {
      "description": "Determines the style exaggeration of the voice. This setting attempts to amplify the style of the original speaker. It does consume additional computational resources and might increase latency if set to anything other than 0."
    },
    "use_speaker_boost": {
      "description": "This setting boosts the similarity to the original speaker. Using this setting requires a slightly higher computational load, which in turn increases latency."
    }
  },
  "required": [
    "PCID",
    "voice_id"
  ]
}

elevenlabs_voices_get_audio_from_sample

Get Audio From Sample Parameters:

Parameter	Type	Required	Default	Description
`voice_id`	string	Yes	—	Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices.
`sample_id`	string	Yes	—	Sample ID to be used, you can use GET https://api.elevenlabs.io/v1/voices/{voice_id} to list all the available samples for a voice.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "voice_id": {
      "type": "string",
      "description": "Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices."
    },
    "sample_id": {
      "type": "string",
      "description": "Sample ID to be used, you can use GET https://api.elevenlabs.io/v1/voices/{voice_id} to list all the available samples for a voice."
    }
  },
  "required": [
    "PCID",
    "voice_id",
    "sample_id"
  ]
}

elevenlabs_voices_get_library_voices

Get Voices Parameters:

Parameter	Type	Required	Default	Description
`page_size`	integer	No	—	How many shared voices to return at maximum. Can not exceed 100, defaults to 30.
`category`	object	No	—	Voice category used for filtering
`gender`	object	No	—	Gender used for filtering
`age`	object	No	—	Age used for filtering
`accent`	object	No	—	Accent used for filtering
`language`	object	No	—	Language used for filtering
`locale`	object	No	—	Locale used for filtering
`search`	object	No	—	Search term used for filtering
`use_cases`	object	No	—	Use-case used for filtering
`descriptives`	object	No	—	Search term used for filtering
`featured`	boolean	No	—	Filter featured voices
`min_notice_period_days`	object	No	—	Filter voices with a minimum notice period of the given number of days.
`include_custom_rates`	object	No	—	Include/exclude voices with custom rates
`include_live_moderated`	object	No	—	Include/exclude voices that are live moderated
`reader_app_enabled`	boolean	No	—	Filter voices that are enabled for the reader app
`owner_id`	object	No	—	Filter voices by public owner ID
`sort`	object	No	—	Sort criteria
`page`	integer	No	—	Page number for pagination

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "page_size": {
      "type": "integer",
      "description": "How many shared voices to return at maximum. Can not exceed 100, defaults to 30."
    },
    "category": {
      "description": "Voice category used for filtering",
      "enum": [
        "professional",
        "famous",
        "high_quality"
      ]
    },
    "gender": {
      "description": "Gender used for filtering"
    },
    "age": {
      "description": "Age used for filtering"
    },
    "accent": {
      "description": "Accent used for filtering"
    },
    "language": {
      "description": "Language used for filtering"
    },
    "locale": {
      "description": "Locale used for filtering"
    },
    "search": {
      "description": "Search term used for filtering"
    },
    "use_cases": {
      "description": "Use-case used for filtering"
    },
    "descriptives": {
      "description": "Search term used for filtering"
    },
    "featured": {
      "type": "boolean",
      "description": "Filter featured voices"
    },
    "min_notice_period_days": {
      "description": "Filter voices with a minimum notice period of the given number of days."
    },
    "include_custom_rates": {
      "description": "Include/exclude voices with custom rates"
    },
    "include_live_moderated": {
      "description": "Include/exclude voices that are live moderated"
    },
    "reader_app_enabled": {
      "type": "boolean",
      "description": "Filter voices that are enabled for the reader app"
    },
    "owner_id": {
      "description": "Filter voices by public owner ID"
    },
    "sort": {
      "description": "Sort criteria"
    },
    "page": {
      "type": "integer",
      "description": "Page number for pagination"
    }
  },
  "required": [
    "PCID"
  ]
}

elevenlabs_voices_get_models

Get Models

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    }
  },
  "required": [
    "PCID"
  ]
}

elevenlabs_voices_get_similar_library_voices

Get Similar Library Voices Parameters:

Parameter	Type	Required	Default	Description
`audio_file`	string	No	—	Audio File
`similarity_threshold`	object	No	—	Threshold for voice similarity between provided sample and library voices. Values range from 0 to 2. The smaller the value the more similar voices will be returned.
`top_k`	object	No	—	Number of most similar voices to return. If similarity_threshold is provided, less than this number of voices may be returned. Values range from 1 to 100.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "audio_file": {
      "type": "string",
      "description": "Audio File"
    },
    "similarity_threshold": {
      "description": "Threshold for voice similarity between provided sample and library voices. Values range from 0 to 2. The smaller the value the more similar voices will be returned."
    },
    "top_k": {
      "description": "Number of most similar voices to return. If similarity_threshold is provided, less than this number of voices may be returned. Values range from 1 to 100."
    }
  },
  "required": [
    "PCID"
  ]
}

elevenlabs_voices_get_user_info

Get User Info

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    }
  },
  "required": [
    "PCID"
  ]
}

elevenlabs_voices_get_user_subscription_info

Get User Subscription Info

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    }
  },
  "required": [
    "PCID"
  ]
}

elevenlabs_voices_get_user_voices_v2

Get Voices V2 Parameters:

Parameter	Type	Required	Default	Description
`next_page_token`	object	No	—	The next page token to use for pagination. Returned from the previous request. Use this in combination with the has_more flag for reliable pagination.
`page_size`	integer	No	—	How many voices to return at maximum. Can not exceed 100, defaults to 10. Page 0 may include more voices due to default voices being included.
`search`	object	No	—	Search term to filter voices by. Searches in name, description, labels, category.
`sort`	object	No	—	Which field to sort by, one of ‘created_at_unix’ or ‘name’. ‘created_at_unix’ may not be available for older voices.
`sort_direction`	object	No	—	Which direction to sort the voices in. ‘asc’ or ‘desc’.
`voice_type`	object	No	—	Type of the voice to filter by. One of ‘personal’, ‘community’, ‘default’, ‘workspace’, ‘non-default’, ‘saved’. ‘non-default’ is equal to all but ‘default’. ‘saved’ is equal to non-default, but includes default voices if they have been added to a collection.
`category`	object	No	—	Category of the voice to filter by. One of ‘premade’, ‘cloned’, ‘generated’, ‘professional’
`fine_tuning_state`	object	No	—	State of the voice’s fine tuning to filter by. Applicable only to professional voices clones. One of ‘draft’, ‘not_verified’, ‘not_started’, ‘queued’, ‘fine_tuning’, ‘fine_tuned’, ‘failed’, ‘delayed’
`collection_id`	object	No	—	Collection ID to filter voices by.
`include_total_count`	boolean	No	—	Whether to include the total count of voices found in the response. NOTE: The total_count value is a live snapshot and may change between requests as users create, modify, or delete voices. For pagination, rely on the has_more flag instead. Only enable this when you actually need the total count (e.g., for display purposes), as it incurs a performance cost.
`voice_ids`	object	No	—	Voice IDs to lookup by. Maximum 100 voice IDs.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "next_page_token": {
      "description": "The next page token to use for pagination. Returned from the previous request. Use this in combination with the has_more flag for reliable pagination."
    },
    "page_size": {
      "type": "integer",
      "description": "How many voices to return at maximum. Can not exceed 100, defaults to 10. Page 0 may include more voices due to default voices being included."
    },
    "search": {
      "description": "Search term to filter voices by. Searches in name, description, labels, category."
    },
    "sort": {
      "description": "Which field to sort by, one of 'created_at_unix' or 'name'. 'created_at_unix' may not be available for older voices."
    },
    "sort_direction": {
      "description": "Which direction to sort the voices in. 'asc' or 'desc'."
    },
    "voice_type": {
      "description": "Type of the voice to filter by. One of 'personal', 'community', 'default', 'workspace', 'non-default', 'saved'. 'non-default' is equal to all but 'default'. 'saved' is equal to non-default, but includes default voices if they have been added to a collection."
    },
    "category": {
      "description": "Category of the voice to filter by. One of 'premade', 'cloned', 'generated', 'professional'"
    },
    "fine_tuning_state": {
      "description": "State of the voice's fine tuning to filter by. Applicable only to professional voices clones. One of 'draft', 'not_verified', 'not_started', 'queued', 'fine_tuning', 'fine_tuned', 'failed', 'delayed'"
    },
    "collection_id": {
      "description": "Collection ID to filter voices by."
    },
    "include_total_count": {
      "type": "boolean",
      "description": "Whether to include the total count of voices found in the response. NOTE: The total_count value is a live snapshot and may change between requests as users create, modify, or delete voices. For pagination, rely on the has_more flag instead. Only enable this when you actually need the total count (e.g., for display purposes), as it incurs a performance cost."
    },
    "voice_ids": {
      "description": "Voice IDs to lookup by. Maximum 100 voice IDs."
    }
  },
  "required": [
    "PCID"
  ]
}

elevenlabs_voices_get_voice_by_id

Get Voice Parameters:

Parameter	Type	Required	Default	Description
`voice_id`	string	Yes	—	Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices.
`with_settings`	boolean	No	—	This parameter is now deprecated. It is ignored and will be removed in a future version.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "voice_id": {
      "type": "string",
      "description": "Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices."
    },
    "with_settings": {
      "type": "boolean",
      "description": "This parameter is now deprecated. It is ignored and will be removed in a future version."
    }
  },
  "required": [
    "PCID",
    "voice_id"
  ]
}

elevenlabs_voices_get_voice_settings

Get Voice Settings Parameters:

Parameter	Type	Required	Default	Description
`voice_id`	string	Yes	—	Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "voice_id": {
      "type": "string",
      "description": "Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices."
    }
  },
  "required": [
    "PCID",
    "voice_id"
  ]
}

elevenlabs_voices_get_voice_settings_default

Get Default Voice Settings.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    }
  },
  "required": [
    "PCID"
  ]
}

elevenlabs_voices_get_voices

List Voices Parameters:

Parameter	Type	Required	Default	Description
`show_legacy`	object	No	—	If set to true, legacy premade voices will be included in responses from /v1/voices

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "show_legacy": {
      "description": "If set to true, legacy premade voices will be included in responses from /v1/voices"
    }
  },
  "required": [
    "PCID"
  ]
}

elevenlabs_voices_text_to_voice

Generate A Voice Preview From Description Parameters:

Parameter	Type	Required	Default	Description
`output_format`	string	No	—	Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs.
`auto_generate_text`	boolean	No	—	Whether to automatically generate a text suitable for the voice description.
`guidance_scale`	number	No	—	Controls how closely the AI follows the prompt. Lower numbers give the AI more freedom to be creative, while higher numbers force it to stick more to the prompt. High numbers can cause voice to sound artificial or robotic. We recommend to use longer, more detailed prompts at lower Guidance Scale.
`loudness`	number	No	—	Controls the volume level of the generated voice. -1 is quietest, 1 is loudest, 0 corresponds to roughly -24 LUFS.
`quality`	number	No	—	Higher quality results in better voice output but less variety.
`seed`	object	No	—	Random number that controls the voice generation. Same seed with same inputs produces same voice.
`should_enhance`	boolean	No	—	Whether to enhance the voice description using AI to add more detail and improve voice generation quality. When enabled, the system will automatically expand simple prompts into more detailed voice descriptions. Defaults to False
`text`	object	No	—	Text to generate, text length has to be between 100 and 1000.
`voice_description`	string	Yes	—	Description to use for the created voice.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "output_format": {
      "type": "string",
      "description": "Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs.",
      "enum": [
        "mp3_22050_32",
        "mp3_24000_48",
        "mp3_44100_32",
        "mp3_44100_64",
        "mp3_44100_96",
        "mp3_44100_128",
        "mp3_44100_192",
        "pcm_8000",
        "pcm_16000",
        "pcm_22050",
        "pcm_24000",
        "pcm_32000",
        "pcm_44100",
        "pcm_48000",
        "ulaw_8000",
        "alaw_8000",
        "opus_48000_32",
        "opus_48000_64",
        "opus_48000_96",
        "opus_48000_128",
        "opus_48000_192"
      ]
    },
    "auto_generate_text": {
      "type": "boolean",
      "description": "Whether to automatically generate a text suitable for the voice description."
    },
    "guidance_scale": {
      "type": "number",
      "description": "Controls how closely the AI follows the prompt. Lower numbers give the AI more freedom to be creative, while higher numbers force it to stick more to the prompt. High numbers can cause voice to sound artificial or robotic. We recommend to use longer, more detailed prompts at lower Guidance Scale."
    },
    "loudness": {
      "type": "number",
      "description": "Controls the volume level of the generated voice. -1 is quietest, 1 is loudest, 0 corresponds to roughly -24 LUFS."
    },
    "quality": {
      "type": "number",
      "description": "Higher quality results in better voice output but less variety."
    },
    "seed": {
      "description": "Random number that controls the voice generation. Same seed with same inputs produces same voice."
    },
    "should_enhance": {
      "type": "boolean",
      "description": "Whether to enhance the voice description using AI to add more detail and improve voice generation quality. When enabled, the system will automatically expand simple prompts into more detailed voice descriptions. Defaults to False"
    },
    "text": {
      "description": "Text to generate, text length has to be between 100 and 1000."
    },
    "voice_description": {
      "type": "string",
      "description": "Description to use for the created voice."
    }
  },
  "required": [
    "PCID",
    "voice_description"
  ]
}

elevenlabs_voices_text_to_voice_design

Design A Voice. Parameters:

Parameter	Type	Required	Default	Description
`output_format`	string	No	—	Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs.
`auto_generate_text`	boolean	No	—	Whether to automatically generate a text suitable for the voice description.
`guidance_scale`	number	No	—	Controls how closely the AI follows the prompt. Lower numbers give the AI more freedom to be creative, while higher numbers force it to stick more to the prompt. High numbers can cause voice to sound artificial or robotic. We recommend to use longer, more detailed prompts at lower Guidance Scale.
`loudness`	number	No	—	Controls the volume level of the generated voice. -1 is quietest, 1 is loudest, 0 corresponds to roughly -24 LUFS.
`model_id`	string	No	—	Model to use for the voice generation. Possible values: eleven_multilingual_ttv_v2, eleven_ttv_v3.
`prompt_strength`	object	No	—	Controls the balance of prompt versus reference audio when generating voice samples. 0 means almost no prompt influence, 1 means almost no reference audio influence. Only supported when using the eleven_ttv_v3 model.
`quality`	object	No	—	Higher quality results in better voice output but less variety.
`reference_audio_base64`	object	No	—	Reference audio to use for the voice generation. The audio should be base64 encoded. Only supported when using the eleven_ttv_v3 model.
`remixing_session_id`	object	No	—	The remixing session id.
`remixing_session_iteration_id`	object	No	—	The id of the remixing session iteration where these generations should be attached to. If not provided, a new iteration will be created.
`seed`	object	No	—	Random number that controls the voice generation. Same seed with same inputs produces same voice.
`should_enhance`	boolean	No	—	Whether to enhance the voice description using AI to add more detail and improve voice generation quality. When enabled, the system will automatically expand simple prompts into more detailed voice descriptions. Defaults to False
`stream_previews`	boolean	No	—	Determines whether the Text to Voice previews should be included in the response. If true, only the generated IDs will be returned which can then be streamed via the /v1/text-to-voice/:generated_voice_id/stream endpoint.
`text`	object	No	—	Text to generate, text length has to be between 100 and 1000.
`voice_description`	string	Yes	—	Description to use for the created voice.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "output_format": {
      "type": "string",
      "description": "Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs.",
      "enum": [
        "mp3_22050_32",
        "mp3_24000_48",
        "mp3_44100_32",
        "mp3_44100_64",
        "mp3_44100_96",
        "mp3_44100_128",
        "mp3_44100_192",
        "pcm_8000",
        "pcm_16000",
        "pcm_22050",
        "pcm_24000",
        "pcm_32000",
        "pcm_44100",
        "pcm_48000",
        "ulaw_8000",
        "alaw_8000",
        "opus_48000_32",
        "opus_48000_64",
        "opus_48000_96",
        "opus_48000_128",
        "opus_48000_192"
      ]
    },
    "auto_generate_text": {
      "type": "boolean",
      "description": "Whether to automatically generate a text suitable for the voice description."
    },
    "guidance_scale": {
      "type": "number",
      "description": "Controls how closely the AI follows the prompt. Lower numbers give the AI more freedom to be creative, while higher numbers force it to stick more to the prompt. High numbers can cause voice to sound artificial or robotic. We recommend to use longer, more detailed prompts at lower Guidance Scale."
    },
    "loudness": {
      "type": "number",
      "description": "Controls the volume level of the generated voice. -1 is quietest, 1 is loudest, 0 corresponds to roughly -24 LUFS."
    },
    "model_id": {
      "type": "string",
      "description": "Model to use for the voice generation. Possible values: eleven_multilingual_ttv_v2, eleven_ttv_v3.",
      "enum": [
        "eleven_multilingual_ttv_v2",
        "eleven_ttv_v3"
      ]
    },
    "prompt_strength": {
      "description": "Controls the balance of prompt versus reference audio when generating voice samples. 0 means almost no prompt influence, 1 means almost no reference audio influence. Only supported when using the eleven_ttv_v3 model."
    },
    "quality": {
      "description": "Higher quality results in better voice output but less variety."
    },
    "reference_audio_base64": {
      "description": "Reference audio to use for the voice generation. The audio should be base64 encoded. Only supported when using the  eleven_ttv_v3 model."
    },
    "remixing_session_id": {
      "description": "The remixing session id."
    },
    "remixing_session_iteration_id": {
      "description": "The id of the remixing session iteration where these generations should be attached to. If not provided, a new iteration will be created."
    },
    "seed": {
      "description": "Random number that controls the voice generation. Same seed with same inputs produces same voice."
    },
    "should_enhance": {
      "type": "boolean",
      "description": "Whether to enhance the voice description using AI to add more detail and improve voice generation quality. When enabled, the system will automatically expand simple prompts into more detailed voice descriptions. Defaults to False"
    },
    "stream_previews": {
      "type": "boolean",
      "description": "Determines whether the Text to Voice previews should be included in the response. If true, only the generated IDs will be returned which can then be streamed via the /v1/text-to-voice/:generated_voice_id/stream endpoint."
    },
    "text": {
      "description": "Text to generate, text length has to be between 100 and 1000."
    },
    "voice_description": {
      "type": "string",
      "description": "Description to use for the created voice."
    }
  },
  "required": [
    "PCID",
    "voice_description"
  ]
}

elevenlabs_voices_text_to_voice_preview_stream

Text To Voice Preview Streaming Parameters:

Parameter	Type	Required	Default	Description
`generated_voice_id`	string	Yes	—	The generated_voice_id to stream.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "generated_voice_id": {
      "type": "string",
      "description": "The generated_voice_id to stream."
    }
  },
  "required": [
    "PCID",
    "generated_voice_id"
  ]
}

elevenlabs_voices_text_to_voice_remix

Remix A Voice. Parameters:

Parameter	Type	Required	Default	Description
`voice_id`	string	Yes	—	Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices.
`output_format`	string	No	—	Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs.
`auto_generate_text`	boolean	No	—	Whether to automatically generate a text suitable for the voice description.
`guidance_scale`	number	No	—	Controls how closely the AI follows the prompt. Lower numbers give the AI more freedom to be creative, while higher numbers force it to stick more to the prompt. High numbers can cause voice to sound artificial or robotic. We recommend to use longer, more detailed prompts at lower Guidance Scale.
`loudness`	number	No	—	Controls the volume level of the generated voice. -1 is quietest, 1 is loudest, 0 corresponds to roughly -24 LUFS.
`prompt_strength`	object	No	—	Controls the balance of prompt versus reference audio when generating voice samples. 0 means almost no prompt influence, 1 means almost no reference audio influence. Only supported when using the eleven_ttv_v3 model.
`remixing_session_id`	object	No	—	The remixing session id.
`remixing_session_iteration_id`	object	No	—	The id of the remixing session iteration where these generations should be attached to. If not provided, a new iteration will be created.
`seed`	object	No	—	Random number that controls the voice generation. Same seed with same inputs produces same voice.
`stream_previews`	boolean	No	—	Determines whether the Text to Voice previews should be included in the response. If true, only the generated IDs will be returned which can then be streamed via the /v1/text-to-voice/:generated_voice_id/stream endpoint.
`text`	object	No	—	Text to generate, text length has to be between 100 and 1000.
`voice_description`	string	Yes	—	Description of the changes to make to the voice.

Show inputSchema

{
  "type": "object",
  "properties": {
    "PCID": {
      "type": "string",
      "description": "Pink Connect ID for the authenticated connection"
    },
    "voice_id": {
      "type": "string",
      "description": "Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices."
    },
    "output_format": {
      "type": "string",
      "description": "Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs.",
      "enum": [
        "mp3_22050_32",
        "mp3_24000_48",
        "mp3_44100_32",
        "mp3_44100_64",
        "mp3_44100_96",
        "mp3_44100_128",
        "mp3_44100_192",
        "pcm_8000",
        "pcm_16000",
        "pcm_22050",
        "pcm_24000",
        "pcm_32000",
        "pcm_44100",
        "pcm_48000",
        "ulaw_8000",
        "alaw_8000",
        "opus_48000_32",
        "opus_48000_64",
        "opus_48000_96",
        "opus_48000_128",
        "opus_48000_192"
      ]
    },
    "auto_generate_text": {
      "type": "boolean",
      "description": "Whether to automatically generate a text suitable for the voice description."
    },
    "guidance_scale": {
      "type": "number",
      "description": "Controls how closely the AI follows the prompt. Lower numbers give the AI more freedom to be creative, while higher numbers force it to stick more to the prompt. High numbers can cause voice to sound artificial or robotic. We recommend to use longer, more detailed prompts at lower Guidance Scale."
    },
    "loudness": {
      "type": "number",
      "description": "Controls the volume level of the generated voice. -1 is quietest, 1 is loudest, 0 corresponds to roughly -24 LUFS."
    },
    "prompt_strength": {
      "description": "Controls the balance of prompt versus reference audio when generating voice samples. 0 means almost no prompt influence, 1 means almost no reference audio influence. Only supported when using the eleven_ttv_v3 model."
    },
    "remixing_session_id": {
      "description": "The remixing session id."
    },
    "remixing_session_iteration_id": {
      "description": "The id of the remixing session iteration where these generations should be attached to. If not provided, a new iteration will be created."
    },
    "seed": {
      "description": "Random number that controls the voice generation. Same seed with same inputs produces same voice."
    },
    "stream_previews": {
      "type": "boolean",
      "description": "Determines whether the Text to Voice previews should be included in the response. If true, only the generated IDs will be returned which can then be streamed via the /v1/text-to-voice/:generated_voice_id/stream endpoint."
    },
    "text": {
      "description": "Text to generate, text length has to be between 100 and 1000."
    },
    "voice_description": {
      "type": "string",
      "description": "Description of the changes to make to the voice."
    }
  },
  "required": [
    "PCID",
    "voice_id",
    "voice_description"
  ]
}

Triggers API

Platform API

Embedded MCP Servers

Application MCP Servers

Tools

elevenlabs_voices_add_sharing_voice

elevenlabs_voices_add_voice

elevenlabs_voices_create_voice

elevenlabs_voices_delete_sample

elevenlabs_voices_delete_voice

elevenlabs_voices_edit_voice

elevenlabs_voices_edit_voice_settings

elevenlabs_voices_get_audio_from_sample

elevenlabs_voices_get_library_voices

elevenlabs_voices_get_models

elevenlabs_voices_get_similar_library_voices

elevenlabs_voices_get_user_info

elevenlabs_voices_get_user_subscription_info

elevenlabs_voices_get_user_voices_v2

elevenlabs_voices_get_voice_by_id

elevenlabs_voices_get_voice_settings

elevenlabs_voices_get_voice_settings_default

elevenlabs_voices_get_voices

elevenlabs_voices_text_to_voice

elevenlabs_voices_text_to_voice_design

elevenlabs_voices_text_to_voice_preview_stream

elevenlabs_voices_text_to_voice_remix

Triggers API

Platform API

Embedded MCP Servers

Application MCP Servers

​Tools

​elevenlabs_voices_add_sharing_voice

​elevenlabs_voices_add_voice

​elevenlabs_voices_create_voice

​elevenlabs_voices_delete_sample

​elevenlabs_voices_delete_voice

​elevenlabs_voices_edit_voice

​elevenlabs_voices_edit_voice_settings

​elevenlabs_voices_get_audio_from_sample

​elevenlabs_voices_get_library_voices

​elevenlabs_voices_get_models

​elevenlabs_voices_get_similar_library_voices

​elevenlabs_voices_get_user_info

​elevenlabs_voices_get_user_subscription_info

​elevenlabs_voices_get_user_voices_v2

​elevenlabs_voices_get_voice_by_id

​elevenlabs_voices_get_voice_settings

​elevenlabs_voices_get_voice_settings_default

​elevenlabs_voices_get_voices

​elevenlabs_voices_text_to_voice

​elevenlabs_voices_text_to_voice_design

​elevenlabs_voices_text_to_voice_preview_stream

​elevenlabs_voices_text_to_voice_remix

Tools

elevenlabs_voices_add_sharing_voice

elevenlabs_voices_add_voice

elevenlabs_voices_create_voice

elevenlabs_voices_delete_sample

elevenlabs_voices_delete_voice

elevenlabs_voices_edit_voice

elevenlabs_voices_edit_voice_settings

elevenlabs_voices_get_audio_from_sample

elevenlabs_voices_get_library_voices

elevenlabs_voices_get_models

elevenlabs_voices_get_similar_library_voices

elevenlabs_voices_get_user_info

elevenlabs_voices_get_user_subscription_info

elevenlabs_voices_get_user_voices_v2

elevenlabs_voices_get_voice_by_id

elevenlabs_voices_get_voice_settings

elevenlabs_voices_get_voice_settings_default

elevenlabs_voices_get_voices

elevenlabs_voices_text_to_voice

elevenlabs_voices_text_to_voice_design

elevenlabs_voices_text_to_voice_preview_stream

elevenlabs_voices_text_to_voice_remix