Smallest AI Text to Speech API

Synthesize speech from text.

OpenAPI Specification

smallest-ai-text-to-speech-api-openapi.yml Raw ↑
openapi: 3.0.1
info:
  title: Smallest AI Waves Streaming Text to Speech API
  description: The Smallest AI Waves text-to-speech API. Generates natural speech from text using the Lightning family of models with sub-100ms latency, streams audio in realtime over Server-Sent Events, lists prebuilt voices, and clones custom voices from short audio samples. All endpoints are authenticated with a Bearer API key. The realtime bidirectional WebSocket transport for streaming TTS is modeled in the companion AsyncAPI document (asyncapi/smallest-ai-asyncapi.yml).
  termsOfService: https://smallest.ai/terms
  contact:
    name: Smallest AI Support
    url: https://smallest.ai/
    email: support@smallest.ai
  version: '1.0'
servers:
- url: https://waves-api.smallest.ai/api/v1
  description: Waves production API
security:
- bearerAuth: []
tags:
- name: Text to Speech
  description: Synthesize speech from text.
paths:
  /lightning/get_speech:
    post:
      operationId: getSpeech
      tags:
      - Text to Speech
      summary: Synthesize speech from text.
      description: Generates an audio file from the input text using a Lightning TTS model and the specified voice. Returns the synthesized audio as a binary response.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/GetSpeechRequest'
      responses:
        '200':
          description: Synthesized audio.
          content:
            audio/wav:
              schema:
                type: string
                format: binary
        '401':
          $ref: '#/components/responses/Unauthorized'
        '422':
          $ref: '#/components/responses/ValidationError'
        '429':
          $ref: '#/components/responses/RateLimited'
components:
  responses:
    RateLimited:
      description: Too many requests; the account rate limit was exceeded.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    ValidationError:
      description: The request body failed validation.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    Unauthorized:
      description: Missing or invalid API key.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
  schemas:
    Error:
      type: object
      properties:
        status:
          type: string
          description: Error status indicator.
        message:
          type: string
          description: Human-readable error message.
        error:
          type: string
          description: Error code or detail, when present.
    GetSpeechRequest:
      type: object
      required:
      - text
      - voice_id
      properties:
        text:
          type: string
          description: The text to convert to speech.
          example: Modern problems require modern solutions.
        voice_id:
          type: string
          description: Identifier of the voice to synthesize with.
          example: meher
        model:
          type: string
          description: The Lightning TTS model pool to use.
          default: lightning
          example: lightning-v2
        sample_rate:
          type: integer
          description: Output audio sample rate in Hz.
          default: 24000
          example: 24000
        speed:
          type: number
          format: float
          description: Speech rate multiplier; 1.0 is normal speed.
          default: 1.0
          minimum: 0.5
          maximum: 2.0
        language:
          type: string
          description: Language code for synthesis.
          default: en
          example: en
        output_format:
          type: string
          description: Encoding of the returned audio.
          default: wav
          enum:
          - wav
          - pcm
          - mp3
        add_wav_header:
          type: boolean
          description: Whether to prepend a WAV header to the returned audio. Set false to receive raw PCM.
          default: true
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: 'Pass your Waves API key as a Bearer token in the Authorization header: `Authorization: Bearer <SMALLEST_API_KEY>`.'