openapi: 3.0.1
x-mcp:
  enabled: true
info:
  title: LMNT
  version: 1.0.0
servers:
  - url: https://api.lmnt.com
components:
  responses:
    BadRequest:
      description: Bad Request
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: string
            required:
              - error
    Unauthorized:
      description: Unauthorized
      content:
        application/json:
          schema:
            type: object
            properties:
              message:
                type: string
              status:
                type: integer
            required:
              - message
              - status
  schemas:
    voice:
      description: Voice details
      properties:
        description:
          description: A text description of this voice.
          nullable: true
          type: string
        gender:
          description: A tag describing the gender of this voice, e.g. `male`, `female`, `nonbinary`.
          type: string
        id:
          description: The unique identifier of this voice.
          type: string
        name:
          description: The display name of this voice.
          type: string
        owner:
          description: The owner of this voice.
          enum:
            - system
            - me
            - other
          type: string
        starred:
          description: Whether this voice has been starred by you or not.
          type: boolean
        state:
          description: The state of this voice in the training pipeline (e.g., `ready`, `training`).
          type: string
        type:
          description: 'The method by which this voice was created: `instant` or `professional`.'
          enum:
            - instant
            - professional
          type: string
        preview_url:
          description: >-
            A URL that returns a preview speech sample of this voice. The file can be played directly in a
            browser or audio player.
          type: string
      required:
        - owner
        - name
        - id
        - state
      type: object
    voiceId:
      type: string
      description: >-
        The voice id of the voice to use; voice ids can be retrieved by calls to `List voices` or `Voice
        info`.
      example: leah
    outputFormat:
      type: string
      enum:
        - aac
        - mp3
        - ulaw
        - wav
        - webm
        - pcm_s16le
        - pcm_f32le
      default: mp3
      description: >
        The desired output format of the audio. If you are using a streaming endpoint, you'll generate audio
        faster by selecting a streamable format since chunks are encoded and returned as they're generated.
        For non-streamable formats, the entire audio will be synthesized before encoding.


        Streamable formats:

        - `mp3`: 96kbps MP3 audio.

        - `ulaw`: 8-bit G711 µ-law audio with a WAV header.

        - `webm`: WebM format with Opus audio codec.

        - `pcm_s16le`: PCM signed 16-bit little-endian audio.

        - `pcm_f32le`: PCM 32-bit floating-point little-endian audio.


        Non-streamable formats:

        - `aac`: AAC audio codec.

        - `wav`: 16-bit PCM audio in WAV container.
    sampleRate:
      type: number
      enum:
        - 8000
        - 16000
        - 24000
      default: 24000
      description: >-
        The desired output sample rate in Hz. Defaults to `24000` for all formats except `mulaw` which
        defaults to `8000`.
    languageCode:
      type: string
      enum:
        - auto
        - ar
        - de
        - en
        - es
        - fr
        - hi
        - id
        - it
        - ja
        - ko
        - nl
        - pl
        - pt
        - ru
        - sv
        - th
        - tr
        - uk
        - ur
        - vi
        - zh
      default: auto
      description: The desired language. Two letter ISO 639-1 code. Defaults to auto language detection, but specifying the language is recommended for faster generation.
    model:
      type: string
      enum:
        - blizzard
      default: blizzard
      description: The model to use for synthesis. Learn more about models [here](https://docs.lmnt.com/guides/models).
    seed:
      type: integer
      description: Seed used to specify a different take; defaults to random
    text:
      type: string
      description: The text to synthesize; max 5000 characters per request (including spaces).
      example: hello world.
    debug:
      description: When set to true, the generated speech will also be saved to your [clip library](https://app.lmnt.com/clips) in the LMNT playground.
      type: boolean
      default: false
    speechRequest:
      allOf:
        - $ref: '#/components/schemas/streamSpeechRequest'
        - type: object
          properties:
            return_durations:
              description: If set as `true`, response will contain a durations object.
              example: true
              type: boolean
              default: false
    streamSpeechRequest:
      type: object
      required:
        - voice
        - text
      properties:
        voice:
          $ref: '#/components/schemas/voiceId'
        text:
          $ref: '#/components/schemas/text'
        model:
          $ref: '#/components/schemas/model'
        language:
          $ref: '#/components/schemas/languageCode'
        format:
          $ref: '#/components/schemas/outputFormat'
        sample_rate:
          $ref: '#/components/schemas/sampleRate'
        seed:
          $ref: '#/components/schemas/seed'
        debug:
          $ref: '#/components/schemas/debug'
        top_p:
          type: number
          minimum: 0
          maximum: 1
          default: 0.8
          description: >-
            Controls the stability of the generated speech. A lower value (like 0.3) produces more consistent,
            reliable speech. A higher value (like 0.9) gives more flexibility in how words are spoken, but
            might occasionally produce unusual intonations or speech patterns.
        temperature:
          type: number
          minimum: 0
          default: 1
          description: >-
            Influences how expressive and emotionally varied the speech becomes. Lower values (like 0.3)
            create more neutral, consistent speaking styles. Higher values (like 1.0) allow for more dynamic
            emotional range and speaking styles.
    durationObject:
      type: object
      required:
        - text
        - duration
        - start
      properties:
        text:
          description: The synthesized input elements; beginning and ending with a short silence.
          type: string
        duration:
          description: The spoken duration of each synthesized input element, in seconds.
          type: number
        start:
          description: The start time of each synthsized input element, in seconds.
          type: number
  securitySchemes:
    ApiKeyHeader:
      type: apiKey
      in: header
      name: X-API-Key
      description: Your API key; get it from your [LMNT account page](https://app.lmnt.com/account).
  parameters:
    VoiceIdPathParam:
      name: id
      in: path
      required: true
      description: The `id` of the voice, which can be retrieved by a call to `List voices`.
      example: '123'
      schema:
        type: string
paths:
  /v1/account:
    get:
      security:
        - ApiKeyHeader: []
      deprecated: false
      description: Returns details about your account.
      responses:
        '200':
          content:
            application/json:
              schema:
                properties:
                  plan:
                    properties:
                      character_limit:
                        description: The number of characters you are allowed to synthesize in this billing period.
                        type: integer
                      commercial_use_allowed:
                        type: boolean
                      instant_voice_limit:
                        description: The number of instant voices you are allowed to create.
                        type: integer
                      professional_voice_limit:
                        description: The number of professional voices you are allowed to create.
                        nullable: true
                        type: integer
                      type:
                        description: The type of plan you are subscribed to.
                        type: string
                    required:
                      - character_limit
                      - professional_voice_limit
                      - type
                      - commercial_use_allowed
                    type: object
                  usage:
                    properties:
                      characters:
                        description: The number of characters you have synthesized in this billing period.
                        type: integer
                      instant_voices:
                        description: The number of instant voices you have created.
                        type: integer
                      professional_voices:
                        description: The number of professional voices you have created.
                        type: integer
                    required:
                      - characters
                      - professional_voices
                    type: object
                required:
                  - usage
                  - plan
                type: object
          description: OK
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
      summary: Account info
      tags: []
      x-codeSamples:
        - lang: JavaScript
          source: |-
            import Lmnt from 'lmnt-node';

            const client = new Lmnt({
              apiKey: 'My API Key',
            });

            const account = await client.accounts.retrieve();

            console.log(account.plan);
        - lang: Python
          source: |-
            from lmnt import Lmnt

            client = Lmnt(
                api_key="My API Key",
            )
            account = client.accounts.retrieve()
            print(account.plan)
  /v1/ai/speech:
    post:
      security:
        - ApiKeyHeader: []
      deprecated: false
      description: >
        Generates speech from text and returns a JSON object that contains a **base64-encoded audio string**
        and optionally word-level durations (timestamps).

        This endpoint waits for the entire synthesis before responding, so it is not ideal for
        latency-sensitive applications.
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/speechRequest'
      responses:
        '200':
          content:
            application/json:
              schema:
                properties:
                  audio:
                    description: The base64-encoded audio file; the format is determined by the `format` parameter.
                    type: string
                  durations:
                    description: >-
                      A JSON object outlining the spoken duration of each synthesized input element (words and
                      non-words like spaces, punctuation, etc.). See an [example of this
                      object](https://imgur.com/Uw6qNzY.png) for the input string "Hello world!"
                    type: array
                    items:
                      $ref: '#/components/schemas/durationObject'
                  seed:
                    description: >-
                      The seed used to generate this speech; can be used to replicate this output take
                      (assuming the same text is resynthsized with this seed number, [see
                      here](http://docs.lmnt.com/speech/seed) for more details).
                    type: integer
                required:
                  - audio
                  - seed
                type: object
          description: OK
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
      summary: Generate speech (JSON with metadata)
      tags:
        - speech
      x-codeSamples:
        - lang: JavaScript
          source: |-
            import Lmnt from 'lmnt-node';

            const client = new Lmnt({
              apiKey: 'My API Key',
            });

            const response = await client.speech.generateDetailed({ text: 'hello world.', voice: 'leah' });

            console.log(response.audio);
        - lang: Python
          source: |-
            from lmnt import Lmnt

            client = Lmnt(
                api_key="My API Key",
            )
            response = client.speech.generate_detailed(
                text="hello world.",
                voice="leah",
            )
            print(response.audio)
  /v1/ai/speech/bytes:
    post:
      security:
        - ApiKeyHeader: []
      deprecated: false
      description: >
        Generates speech from text and streams the audio as binary data chunks in real-time as they are
        generated.


        This is the recommended endpoint for most text-to-speech use cases. You can either stream the chunks
        for low-latency playback or collect all chunks to get the complete audio file.
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/streamSpeechRequest'
      responses:
        '200':
          content:
            application/octet-stream:
              schema:
                type: string
                format: binary
          description: OK
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
      summary: Generate speech (binary stream)
      tags:
        - speech
      x-codeSamples:
        - lang: JavaScript
          source: |-
            import Lmnt from 'lmnt-node';

            const client = new Lmnt({
              apiKey: 'My API Key',
            });

            const response = await client.speech.generate({ text: 'hello world.', voice: 'leah' });

            console.log(response);

            const content = await response.blob();
            console.log(content);
        - lang: Python
          source: |-
            from lmnt import Lmnt

            client = Lmnt(
                api_key="My API Key",
            )
            response = client.speech.generate(
                text="hello world.",
                voice="leah",
            )
            print(response)
            content = response.read()
            print(content)
  /v1/ai/voice:
    post:
      security:
        - ApiKeyHeader: []
      deprecated: false
      description: >-
        Submits a request to create a voice with a supplied voice configuration and a batch of input audio
        data.
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                name:
                  description: The display name for this voice
                  type: string
                  example: new-voice
                enhance:
                  description: >-
                    For unclean audio with background noise, applies processing to attempt to improve quality.
                    Default is `false` as this can also degrade quality in some circumstances.
                  type: boolean
                  example: false
                gender:
                  description: A tag describing the gender of this voice. Has no effect on voice creation.
                  type: string
                description:
                  description: A text description of this voice.
                  type: string
                files:
                  description: >-
                    One or more input audio files to train the voice in the form of binary `wav`, `mp3`,
                    `mp4`, `m4a`, or `webm` attachments.

                    - Max attached files: 20.

                    - Max total file size: 250 MB.
                  type: array
                  minItems: 1
                  maxItems: 20
                  items:
                    type: string
                    format: binary
                  example: '@/Users/user/file.wav'
              required:
                - name
                - enhance
                - files
      responses:
        '200':
          content:
            application/json:
              examples:
                '1':
                  summary: Success
                  value:
                    description: a newly created voice
                    gender: male
                    id: 123456789abcdef
                    name: new-voice
                    owner: me
                    starred: false
                    state: ready
                    type: instant
              schema:
                $ref: '#/components/schemas/voice'
          description: OK
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
      summary: Create voice
      tags:
        - voice
      x-codeSamples:
        - lang: JavaScript
          source: |-
            import Lmnt from 'lmnt-node';

            const client = new Lmnt({
              apiKey: 'My API Key',
            });

            const voice = await client.voices.create({
              enhance: false,
              files: [fs.createReadStream('path/to/file')],
              name: 'new-voice',
            });

            console.log(voice.id);
        - lang: Python
          source: |-
            from lmnt import Lmnt

            client = Lmnt(
                api_key="My API Key",
            )
            voice = client.voices.create(
                enhance=False,
                files=[b"raw file contents"],
                name="new-voice",
            )
            print(voice.id)
  /v1/ai/voice/list:
    get:
      security:
        - ApiKeyHeader: []
      deprecated: false
      description: Returns a list of voices available to you.
      parameters:
        - description: If true, only returns voices that you have starred.
          example: 'true'
          in: query
          name: starred
          required: false
          schema:
            type: string
            default: 'false'
        - description: Which owner's voices to return. Choose from `system`, `me`, or `all`.
          example: system,me
          in: query
          name: owner
          required: false
          schema:
            type: string
            default: all
      responses:
        '200':
          content:
            application/json:
              examples:
                '1':
                  summary: Success
                  value:
                    - description: UK. Young adult. Conversational
                      gender: F
                      id: morgan (for user-created voices, the id is an alphanumeric string)
                      name: Morgan
                      owner: system
                      starred: true
                      type: professional
                      state: ready
                      preview_url: https://api.lmnt.com/v1/ai/morgan/preview
              schema:
                items:
                  $ref: '#/components/schemas/voice'
                type: array
          description: OK
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
      summary: List voices
      tags:
        - voice
      x-codeSamples:
        - lang: JavaScript
          source: |-
            import Lmnt from 'lmnt-node';

            const client = new Lmnt({
              apiKey: 'My API Key',
            });

            const voices = await client.voices.list();

            console.log(voices);
        - lang: Python
          source: |-
            from lmnt import Lmnt

            client = Lmnt(
                api_key="My API Key",
            )
            voices = client.voices.list()
            print(voices)
  /v1/ai/voice/{id}:
    delete:
      security:
        - ApiKeyHeader: []
      deprecated: false
      description: Deletes a voice and cancels any pending operations on it. Cannot be undone.
      parameters:
        - $ref: '#/components/parameters/VoiceIdPathParam'
      responses:
        '200':
          content:
            application/json:
              schema:
                properties:
                  success:
                    type: boolean
                required:
                  - success
                type: object
          description: OK
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
      summary: Delete voice
      tags:
        - voice
      x-codeSamples:
        - lang: JavaScript
          source: |-
            import Lmnt from 'lmnt-node';

            const client = new Lmnt({
              apiKey: 'My API Key',
            });

            const voice = await client.voices.delete('123');

            console.log(voice.success);
        - lang: Python
          source: |-
            from lmnt import Lmnt

            client = Lmnt(
                api_key="My API Key",
            )
            voice = client.voices.delete(
                "id",
            )
            print(voice.success)
    get:
      security:
        - ApiKeyHeader: []
      deprecated: false
      description: Returns details of a specific voice.
      parameters:
        - $ref: '#/components/parameters/VoiceIdPathParam'
      responses:
        '200':
          content:
            application/json:
              examples:
                '1':
                  summary: Success
                  value:
                    description: UK. Young adult. Conversational
                    gender: F
                    id: morgan (for user-created voices, the id is an alphanumeric string)
                    name: Morgan
                    owner: system
                    starred: true
                    type: instant
                    state: ready
                    preview_url: https://api.lmnt.com/v1/ai/morgan/preview
              schema:
                $ref: '#/components/schemas/voice'
          description: OK
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
      summary: Voice info
      tags:
        - voice
      x-codeSamples:
        - lang: JavaScript
          source: |-
            import Lmnt from 'lmnt-node';

            const client = new Lmnt({
              apiKey: 'My API Key',
            });

            const voice = await client.voices.retrieve('123');

            console.log(voice.id);
        - lang: Python
          source: |-
            from lmnt import Lmnt

            client = Lmnt(
                api_key="My API Key",
            )
            voice = client.voices.retrieve(
                "id",
            )
            print(voice.id)
    put:
      security:
        - ApiKeyHeader: []
      deprecated: false
      description: Updates metadata for a specific voice. Only provided fields will be changed.
      parameters:
        - $ref: '#/components/parameters/VoiceIdPathParam'
      requestBody:
        content:
          application/json:
            schema:
              properties:
                description:
                  description: 'A description of this voice. '
                  type: string
                gender:
                  description: A tag describing the gender of this voice, e.g. `male`, `female`, `nonbinary`.
                  type: string
                name:
                  description: The display name for this voice.
                  type: string
                starred:
                  description: If `true`, adds this voice to your starred list.
                  type: boolean
              type: object
      responses:
        '200':
          content:
            application/json:
              schema:
                properties:
                  voice:
                    $ref: '#/components/schemas/voice'
                required:
                  - voice
                type: object
          description: OK
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
      summary: Update voice
      tags:
        - voice
      x-codeSamples:
        - lang: JavaScript
          source: |-
            import Lmnt from 'lmnt-node';

            const client = new Lmnt({
              apiKey: 'My API Key',
            });

            const voice = await client.voices.update('123');

            console.log(voice.voice);
        - lang: Python
          source: |-
            from lmnt import Lmnt

            client = Lmnt(
                api_key="My API Key",
            )
            voice = client.voices.update(
                id="123",
            )
            print(voice.voice)
  /v1/ai/speech/convert:
    post:
      security:
        - ApiKeyHeader: []
      deprecated: false
      description: Converts speech from one voice to another.
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required:
                - audio
                - voice
              properties:
                audio:
                  description: >-
                    The audio file to be converted into a new voice. Specify source language using the
                    `language` parameter. Acceptable formats: `wav`, `mp3`. Max file size: 1 MB.
                  type: string
                  format: binary
                  example: '@/Users/user/file1.wav'
                voice:
                  $ref: '#/components/schemas/voiceId'
                  description: >-
                    The voice id to convert the speech into. Voice ids can be retrieved by calls to `List
                    voices` or `Voice info`.
                format:
                  $ref: '#/components/schemas/outputFormat'
                sample_rate:
                  $ref: '#/components/schemas/sampleRate'
                language:
                  $ref: '#/components/schemas/languageCode'
                  description: The language of the source audio. Two letter ISO 639-1 code.
      responses:
        '200':
          content:
            application/octet-stream:
              schema:
                type: string
                format: binary
          description: OK
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
      summary: Convert audio using a specific voice
      tags:
        - speech
      x-codeSamples:
        - lang: JavaScript
          source: >-
            import Lmnt from 'lmnt-node';


            const client = new Lmnt({
              apiKey: 'My API Key',
            });


            const response = await client.speech.convert({ audio: fs.createReadStream('path/to/file'), voice:
            'leah' });


            console.log(response);


            const content = await response.blob();

            console.log(content);
        - lang: Python
          source: |-
            from lmnt import Lmnt

            client = Lmnt(
                api_key="My API Key",
            )
            response = client.speech.convert(
                audio=b"raw file contents",
                voice="leah",
            )
            print(response)
            content = response.read()
            print(content)
tags:
  - name: voice
  - name: speech