> ## Documentation Index
> Fetch the complete documentation index at: https://composio-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# LMNT

> LMNT focuses on voice and audio manipulation, possibly leveraging AI to generate or transform sound for various creative and technical use cases

![LMNT logo](https://mintcdn.com/composio-preview/ufpARLIsio16odJB/images/toolkits/lmnt.svg?fit=max\&auto=format\&n=ufpARLIsio16odJB\&q=85\&s=31c96f097671c612e5eeae0bad90bec5)

* **Category:** audio & speech
* **Auth:** API\_KEY
* **Composio-managed OAuth available?** N/A
* **Tools:** 8
* **Triggers:** 0
* **Slug:** `LMNT`
* **Version:** 20261101\_00

## Tools

> [accordion] Create Voice
>
> **Slug:** `LMNT_CREATE_VOICE`
>
> Creates a custom LMNT voice from uploaded audio, returning the voice ID and metadata; the voice may initially be in training before becoming ready. LMNT has shut down.
>
> #### Input Parameters
>
> **name** `string` *required*
>
> The display name for this voice.
>
> **type** `string ("instant" | "professional")`
>
> The type of voice to create. Use 'instant' for quick voice cloning or 'professional' for higher quality. Defaults to 'instant'.
>
> **files** `object` *required*
>
> Audio file to train the voice. Supported formats: WAV, MP3, MP4, M4A, WebM. Maximum file size: 250 MB.
>
> **gender** `string`
>
> Optional gender tag for this voice (e.g., 'male', 'female', 'nonbinary'). This is metadata only and does not affect voice generation.
>
> **enhance** `boolean`
>
> Whether to apply audio processing to reduce background noise. Set to true for unclean audio, but note this may degrade quality in some cases. Defaults to false.
>
> **description** `string`
>
> Optional text description of this voice for organizational purposes.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete Voice Info
>
> **Slug:** `LMNT_DELETE_VOICE_INFO`
>
> Deletes a custom voice by ID from your LMNT account to manage your voice library. Only voices you own can be deleted; system voices cannot be deleted. LMNT has shut down.
>
> #### Input Parameters
>
> **id** `string` *required*
>
> The unique identifier of the voice to delete. This must be a voice owned by you (voices with owner='me'). System voices cannot be deleted.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Generate Speech With Metadata
>
> **Slug:** `LMNT_GENERATE_SPEECH_WITH_METADATA`
>
> Generates speech from text and returns base64-encoded audio, a seed, and optional word-level timing metadata. LMNT has shut down.
>
> #### Input Parameters
>
> **seed** `integer`
>
> Integer seed for reproducible speech variations. Use the same seed to replicate a specific output.
>
> **text** `string` *required*
>
> The text to synthesize into speech (max 5000 characters including spaces).
>
> **debug** `boolean`
>
> When true, saves the synthesis clip to your clip library for debugging purposes.
>
> **model** `string`
>
> The synthesis model to use (default: 'blizzard').
>
> **top\_p** `number`
>
> Controls speech stability (0-1 range, default: 0.8). Lower values produce more consistent speech.
>
> **voice** `string` *required*
>
> The voice ID to use for speech synthesis (e.g., 'lily', 'leah', 'daniel'). Use the List Voices action to get available voice IDs.
>
> **format** `string`
>
> Output audio format. Streamable formats (generate faster): mp3 (default), ulaw, webm, pcm\_s16le, pcm\_f32le. Non-streamable: aac, wav.
>
> **language** `string`
>
> ISO 639-1 two-letter language code (e.g., 'en', 'es', 'fr'). Auto-detected by default, but specifying language improves generation speed.
>
> **sample\_rate** `integer`
>
> Audio sample rate in Hz. Options: 8000, 16000, or 24000.
>
> **temperature** `number`
>
> Controls speech expressiveness (numeric value, default: 1.0). Higher values increase variation.
>
> **return\_durations** `boolean`
>
> When true, returns word-level duration timestamps in the response. Useful for synchronizing subtitles or animations with speech.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Account
>
> **Slug:** `LMNT_GET_ACCOUNT`
>
> Retrieves account information including subscription plan details and current usage statistics.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Voice Info
>
> **Slug:** `LMNT_GET_VOICE_INFO`
>
> Gets metadata for a specific LMNT voice, including its ID, name, owner, and training state. LMNT has shut down.
>
> #### Input Parameters
>
> **id** `string` *required*
>
> The ID of the voice to retrieve. Can be obtained from the list voices endpoint.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Voices List
>
> **Slug:** `LMNT_GET_VOICES_LIST`
>
> Retrieves available LMNT voices, with ownership and starred filters and details such as ID, name, state, and optional preview URL. LMNT has shut down.
>
> #### Input Parameters
>
> **owner** `string ("all" | "system" | "me")`
>
> Filter voices by owner. Options: 'all' (default, shows all voices), 'system' (only LMNT preset voices), 'me' (only your custom voices).
>
> **starred** `boolean`
>
> Filter to show only starred voices. Set to true to return only voices you have starred, false (default) to show all voices.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Synthesize Speech
>
> **Slug:** `LMNT_SYNTHESIZE_SPEECH`
>
> Synthesizes speech from text of up to 5,000 characters using a specified LMNT voice. Returns base64-encoded audio to decode before use, with a choice of audio formats and quality settings. LMNT has shut down.
>
> #### Input Parameters
>
> **seed** `integer`
>
> Integer seed for reproducible speech variations. Use the same seed to replicate a specific output.
>
> **text** `string` *required*
>
> The text to synthesize into speech (max 5000 characters including spaces). For texts exceeding 5000 characters, split into chunks and call separately, keeping `voice`, `model`, `format`, and `sample_rate` identical across all chunks to avoid audible seams.
>
> **debug** `boolean`
>
> When true, saves the synthesis clip to your clip library for debugging purposes.
>
> **model** `string`
>
> The synthesis model to use (default: 'blizzard').
>
> **top\_p** `number`
>
> Controls speech stability (0-1 range, default: 0.8). Lower values produce more consistent speech.
>
> **voice** `string` *required*
>
> The voice ID to use for speech synthesis (e.g., 'lily', 'leah', 'daniel'). Use the List Voices action to get available voice IDs.
>
> **format** `string`
>
> Output audio format. Streamable formats (generate faster): mp3 (default), ulaw, webm, pcm\_s16le, pcm\_f32le. Non-streamable: aac, wav.
>
> **language** `string`
>
> ISO 639-1 two-letter language code (e.g., 'en', 'es', 'fr'). Auto-detected by default, but specifying language improves generation speed.
>
> **sample\_rate** `integer`
>
> Audio sample rate in Hz. Options: 8000, 16000, or 24000 (default).
>
> **temperature** `number`
>
> Controls speech expressiveness (numeric value, default: 1.0). Higher values increase variation.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Update Voice Info
>
> **Slug:** `LMNT_UPDATE_VOICE`
>
> Updates a specific LMNT voice's name, description, gender, starred status, or unfreeze state; only user-owned voices can have their name, description, and gender updated, and system voices can only be starred or unstarred. LMNT has shut down.
>
> #### Input Parameters
>
> **id** `string` *required*
>
> The unique identifier of the voice to update
>
> **name** `string`
>
> The display name for this voice.
>
> **gender** `string`
>
> A tag describing the gender of this voice, e.g. male, female, nonbinary.
>
> **starred** `boolean`
>
> If true, adds this voice to your starred list. If false, removes it from your starred list.
>
> **unfreeze** `boolean`
>
> If true, unfreezes this voice and upgrades it to the latest model.
>
> **description** `string`
>
> A description of this voice.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not
