> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pinkfish.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# lmnt

> LMNT Text-to-Speech

**Server path:** `/lmnt` | **Type:** Application | **PCID required:** Yes

## Tools

| Tool                                                        | Description                          |
| ----------------------------------------------------------- | ------------------------------------ |
| [`lmnt_delete_voice`](#lmnt_delete_voice)                   | Delete voice                         |
| [`lmnt_generate_speech`](#lmnt_generate_speech)             | Generate speech (JSON with metadata) |
| [`lmnt_generate_speech_bytes`](#lmnt_generate_speech_bytes) | Generate speech (binary stream)      |
| [`lmnt_get_account`](#lmnt_get_account)                     | Account info                         |
| [`lmnt_get_voice`](#lmnt_get_voice)                         | Voice info                           |
| [`lmnt_list_voices`](#lmnt_list_voices)                     | List voices                          |
| [`lmnt_update_voice`](#lmnt_update_voice)                   | Update voice                         |

***

## lmnt\_delete\_voice

Delete voice

**Parameters:**

| Parameter | Type   | Required | Default | Description          |
| --------- | ------ | -------- | ------- | -------------------- |
| `id`      | string | Yes      | —       | The id of the voice. |

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "PCID": {
        "type": "string",
        "description": "Pink Connect ID for the authenticated connection"
      },
      "id": {
        "type": "string",
        "description": "The id of the voice."
      }
    },
    "required": [
      "PCID",
      "id"
    ]
  }
  ```
</Expandable>

***

## lmnt\_generate\_speech

Generate speech (JSON with metadata)

**Parameters:**

| Parameter          | Type    | Required | Default | Description                                                                                                                                           |
| ------------------ | ------- | -------- | ------- | ----------------------------------------------------------------------------------------------------------------------------------------------------- |
| `debug`            | boolean | No       | —       | When set to true, the generated speech will also be saved to your clip library in the LMNT playground.                                                |
| `format`           | string  | No       | —       | The desired output format of the audio.                                                                                                               |
| `language`         | string  | No       | —       | The desired language. Two letter ISO 639-1 code. Defaults to auto language detection.                                                                 |
| `model`            | string  | No       | —       | The model to use for synthesis.                                                                                                                       |
| `return_durations` | boolean | No       | —       | If set as true, response will contain a durations object.                                                                                             |
| `sample_rate`      | number  | No       | —       | The desired output sample rate in Hz. Defaults to 24000 for all formats except mulaw which defaults to 8000.                                          |
| `seed`             | integer | No       | —       | Seed used to specify a different take; defaults to random                                                                                             |
| `temperature`      | number  | No       | —       | Influences how expressive and emotionally varied the speech becomes. Lower values create more neutral styles, higher values allow more dynamic range. |
| `text`             | string  | Yes      | —       | The text to synthesize; max 5000 characters per request (including spaces).                                                                           |
| `top_p`            | number  | No       | —       | Controls the stability of the generated speech. Lower values produce more consistent speech, higher values give more flexibility.                     |
| `voice`            | string  | Yes      | —       | The voice id of the voice to use; voice ids can be retrieved by calls to List voices or Voice info.                                                   |

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "PCID": {
        "type": "string",
        "description": "Pink Connect ID for the authenticated connection"
      },
      "debug": {
        "type": "boolean",
        "description": "When set to true, the generated speech will also be saved to your clip library in the LMNT playground."
      },
      "format": {
        "type": "string",
        "description": "The desired output format of the audio.",
        "enum": [
          "aac",
          "mp3",
          "ulaw",
          "wav",
          "webm",
          "pcm_s16le",
          "pcm_f32le"
        ]
      },
      "language": {
        "type": "string",
        "description": "The desired language. Two letter ISO 639-1 code. Defaults to auto language detection.",
        "enum": [
          "auto",
          "ar",
          "de",
          "en",
          "es",
          "fr",
          "hi",
          "id",
          "it",
          "ja",
          "ko",
          "nl",
          "pl",
          "pt",
          "ru",
          "sv",
          "th",
          "tr",
          "uk",
          "ur",
          "vi",
          "zh"
        ]
      },
      "model": {
        "type": "string",
        "description": "The model to use for synthesis.",
        "enum": [
          "blizzard"
        ]
      },
      "return_durations": {
        "type": "boolean",
        "description": "If set as true, response will contain a durations object."
      },
      "sample_rate": {
        "type": "number",
        "description": "The desired output sample rate in Hz. Defaults to 24000 for all formats except mulaw which defaults to 8000.",
        "enum": [
          8000,
          16000,
          24000
        ]
      },
      "seed": {
        "type": "integer",
        "description": "Seed used to specify a different take; defaults to random"
      },
      "temperature": {
        "type": "number",
        "description": "Influences how expressive and emotionally varied the speech becomes. Lower values create more neutral styles, higher values allow more dynamic range."
      },
      "text": {
        "type": "string",
        "description": "The text to synthesize; max 5000 characters per request (including spaces)."
      },
      "top_p": {
        "type": "number",
        "description": "Controls the stability of the generated speech. Lower values produce more consistent speech, higher values give more flexibility."
      },
      "voice": {
        "type": "string",
        "description": "The voice id of the voice to use; voice ids can be retrieved by calls to List voices or Voice info."
      }
    },
    "required": [
      "PCID",
      "text",
      "voice"
    ]
  }
  ```
</Expandable>

***

## lmnt\_generate\_speech\_bytes

Generate speech (binary stream)

**Parameters:**

| Parameter     | Type    | Required | Default | Description                                                                                                                                           |
| ------------- | ------- | -------- | ------- | ----------------------------------------------------------------------------------------------------------------------------------------------------- |
| `debug`       | boolean | No       | —       | When set to true, the generated speech will also be saved to your clip library in the LMNT playground.                                                |
| `format`      | string  | No       | —       | The desired output format of the audio.                                                                                                               |
| `language`    | string  | No       | —       | The desired language. Two letter ISO 639-1 code. Defaults to auto language detection.                                                                 |
| `model`       | string  | No       | —       | The model to use for synthesis.                                                                                                                       |
| `sample_rate` | number  | No       | —       | The desired output sample rate in Hz. Defaults to 24000 for all formats except mulaw which defaults to 8000.                                          |
| `seed`        | integer | No       | —       | Seed used to specify a different take; defaults to random                                                                                             |
| `temperature` | number  | No       | —       | Influences how expressive and emotionally varied the speech becomes. Lower values create more neutral styles, higher values allow more dynamic range. |
| `text`        | string  | Yes      | —       | The text to synthesize; max 5000 characters per request (including spaces).                                                                           |
| `top_p`       | number  | No       | —       | Controls the stability of the generated speech. Lower values produce more consistent speech, higher values give more flexibility.                     |
| `voice`       | string  | Yes      | —       | The voice id of the voice to use; voice ids can be retrieved by calls to List voices or Voice info.                                                   |

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "PCID": {
        "type": "string",
        "description": "Pink Connect ID for the authenticated connection"
      },
      "debug": {
        "type": "boolean",
        "description": "When set to true, the generated speech will also be saved to your clip library in the LMNT playground."
      },
      "format": {
        "type": "string",
        "description": "The desired output format of the audio.",
        "enum": [
          "aac",
          "mp3",
          "ulaw",
          "wav",
          "webm",
          "pcm_s16le",
          "pcm_f32le"
        ]
      },
      "language": {
        "type": "string",
        "description": "The desired language. Two letter ISO 639-1 code. Defaults to auto language detection.",
        "enum": [
          "auto",
          "ar",
          "de",
          "en",
          "es",
          "fr",
          "hi",
          "id",
          "it",
          "ja",
          "ko",
          "nl",
          "pl",
          "pt",
          "ru",
          "sv",
          "th",
          "tr",
          "uk",
          "ur",
          "vi",
          "zh"
        ]
      },
      "model": {
        "type": "string",
        "description": "The model to use for synthesis.",
        "enum": [
          "blizzard"
        ]
      },
      "sample_rate": {
        "type": "number",
        "description": "The desired output sample rate in Hz. Defaults to 24000 for all formats except mulaw which defaults to 8000.",
        "enum": [
          8000,
          16000,
          24000
        ]
      },
      "seed": {
        "type": "integer",
        "description": "Seed used to specify a different take; defaults to random"
      },
      "temperature": {
        "type": "number",
        "description": "Influences how expressive and emotionally varied the speech becomes. Lower values create more neutral styles, higher values allow more dynamic range."
      },
      "text": {
        "type": "string",
        "description": "The text to synthesize; max 5000 characters per request (including spaces)."
      },
      "top_p": {
        "type": "number",
        "description": "Controls the stability of the generated speech. Lower values produce more consistent speech, higher values give more flexibility."
      },
      "voice": {
        "type": "string",
        "description": "The voice id of the voice to use; voice ids can be retrieved by calls to List voices or Voice info."
      }
    },
    "required": [
      "PCID",
      "text",
      "voice"
    ]
  }
  ```
</Expandable>

***

## lmnt\_get\_account

Account info

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "PCID": {
        "type": "string",
        "description": "Pink Connect ID for the authenticated connection"
      }
    },
    "required": [
      "PCID"
    ]
  }
  ```
</Expandable>

***

## lmnt\_get\_voice

Voice info

**Parameters:**

| Parameter | Type   | Required | Default | Description          |
| --------- | ------ | -------- | ------- | -------------------- |
| `id`      | string | Yes      | —       | The id of the voice. |

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "PCID": {
        "type": "string",
        "description": "Pink Connect ID for the authenticated connection"
      },
      "id": {
        "type": "string",
        "description": "The id of the voice."
      }
    },
    "required": [
      "PCID",
      "id"
    ]
  }
  ```
</Expandable>

***

## lmnt\_list\_voices

List voices

**Parameters:**

| Parameter | Type   | Required | Default | Description                                                     |
| --------- | ------ | -------- | ------- | --------------------------------------------------------------- |
| `starred` | string | No       | —       | If true, only returns voices that you have starred.             |
| `owner`   | string | No       | —       | Which owner's voices to return. Choose from system, me, or all. |

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "PCID": {
        "type": "string",
        "description": "Pink Connect ID for the authenticated connection"
      },
      "starred": {
        "type": "string",
        "description": "If true, only returns voices that you have starred."
      },
      "owner": {
        "type": "string",
        "description": "Which owner's voices to return. Choose from system, me, or all."
      }
    },
    "required": [
      "PCID"
    ]
  }
  ```
</Expandable>

***

## lmnt\_update\_voice

Update voice

**Parameters:**

| Parameter     | Type    | Required | Default | Description                                    |
| ------------- | ------- | -------- | ------- | ---------------------------------------------- |
| `id`          | string  | Yes      | —       | The id of the voice.                           |
| `description` | string  | No       | —       | A description of this voice.                   |
| `gender`      | string  | No       | —       | A tag describing the gender of this voice.     |
| `name`        | string  | No       | —       | The display name for this voice.               |
| `starred`     | boolean | No       | —       | If true, adds this voice to your starred list. |

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "PCID": {
        "type": "string",
        "description": "Pink Connect ID for the authenticated connection"
      },
      "id": {
        "type": "string",
        "description": "The id of the voice."
      },
      "description": {
        "type": "string",
        "description": "A description of this voice."
      },
      "gender": {
        "type": "string",
        "description": "A tag describing the gender of this voice."
      },
      "name": {
        "type": "string",
        "description": "The display name for this voice."
      },
      "starred": {
        "type": "boolean",
        "description": "If true, adds this voice to your starred list."
      }
    },
    "required": [
      "PCID",
      "id"
    ]
  }
  ```
</Expandable>