openapi: 3.0.0
info:
  title: AIMLAPI AI/ML API Documentation API Key Management Voice API
  description: "=K Welcome to the [AI/ML API](https://aimlapi.com/) docs! AI/ML API makes integrating state-of-the-art AI models into your applications effortless, offering seamless compatibility with OpenAI-like interfaces.\n\n**Features Include:**\n\n- **Inference**: Easily evaluate models for text, images, and more using our API.\n    \n- **API Key Management**: Securely manage your API keys for controlled access.\n    \n- **Broad Model Selection**: Access a diverse range of models for various AI tasks.\n    \n\nSee Quickstart"
  version: 1.0.0
servers:
- url: http://{{baseurl}}
security:
- bearerAuth: []
tags:
- name: Voice
paths:
  /stt:
    post:
      tags:
      - Voice
      summary: AIMLAPI Speech to Text
      requestBody:
        content:
          application/json:
            schema:
              type: object
              example:
                model: '{{sstModel}}'
                url: https://audio-samples.github.io/samples/mp3/blizzard_unconditional/sample-0.mp3
      responses:
        '201':
          description: Created
          headers:
            Access-Control-Allow-Origin:
              schema:
                type: string
                example: '*'
            Content-Length:
              schema:
                type: integer
                example: '2821'
            Content-Type:
              schema:
                type: string
                example: application/json; charset=utf-8
            Date:
              schema:
                type: string
                example: Wed, 08 May 2024 10:18:53 GMT
            Etag:
              schema:
                type: string
                example: W/"b05-3s5wbmIwoFQ7Zpi3CB62q8npC00"
            X-Powered-By:
              schema:
                type: string
                example: Express
          content:
            application/json:
              schema:
                type: object
              example:
                metadata:
                  transaction_key: deprecated
                  request_id: a6318d7e-b9ad-438a-99cd-c5a26044ad7b
                  sha256: fbdd3587f273e3bd0d826e36a3868ca05dedc1a3f349faa5f28e52b5370b656f
                  created: '2024-05-08T10:18:52.928Z'
                  duration: 10.109375
                  channels: 1
                  models:
                  - 1abfe86b-e047-4eed-858a-35e5625b41ee
                  model_info:
                    1abfe86b-e047-4eed-858a-35e5625b41ee:
                      name: 2-general-nova
                      version: 2024-01-06.5664
                      arch: nova-2
                results:
                  channels:
                  - alternatives:
                    - transcript: my thought i have nobody by a beauty and will as you toward mister rochester is served in that so don't find simpus and devoted to bowed to that might in a
                      confidence: 0.9334016
                      words:
                      - word: my
                        start: 0.24
                        end: 0.48
                        confidence: 0.7677139
                      - word: thought
                        start: 0.48
                        end: 0.88
                        confidence: 0.860146
                      - word: i
                        start: 0.88
                        end: 0.96
                        confidence: 0.9993
                      - word: have
                        start: 0.96
                        end: 1.1999999
                        confidence: 0.9975178
                      - word: nobody
                        start: 1.1999999
                        end: 1.5999999
                        confidence: 0.9981421
                      - word: by
                        start: 1.5999999
                        end: 1.7199999
                        confidence: 0.89347184
                      - word: a
                        start: 1.7199999
                        end: 1.8399999
                        confidence: 0.9539643
                      - word: beauty
                        start: 1.8399999
                        end: 2.1599998
                        confidence: 0.99679714
                      - word: and
                        start: 2.1599998
                        end: 2.32
                        confidence: 0.86830604
                      - word: will
                        start: 2.32
                        end: 2.48
                        confidence: 0.9836391
                      - word: as
                        start: 2.48
                        end: 2.6399999
                        confidence: 0.86166006
                      - word: you
                        start: 2.6399999
                        end: 2.8
                        confidence: 0.96505886
                      - word: toward
                        start: 2.8
                        end: 3.3
                        confidence: 0.57675695
                      - word: mister
                        start: 3.84
                        end: 4.16
                        confidence: 0.9973658
                      - word: rochester
                        start: 4.16
                        end: 4.66
                        confidence: 0.9987276
                      - word: is
                        start: 4.7999997
                        end: 4.96
                        confidence: 0.5949601
                      - word: served
                        start: 4.96
                        end: 5.2
                        confidence: 0.35592097
                      - word: in
                        start: 5.2
                        end: 5.3599997
                        confidence: 0.74498737
                      - word: that
                        start: 5.3599997
                        end: 5.6
                        confidence: 0.99769324
                      - word: so
                        start: 5.6
                        end: 5.8399997
                        confidence: 0.49508306
                      - word: don't
                        start: 5.8399997
                        end: 6.08
                        confidence: 0.9334016
                      - word: find
                        start: 6.08
                        end: 6.3999996
                        confidence: 0.97570974
                      - word: simpus
                        start: 6.3999996
                        end: 6.8999996
                        confidence: 0.7262915
                      - word: and
                        start: 7.2
                        end: 7.44
                        confidence: 0.9856228
                      - word: devoted
                        start: 7.44
                        end: 7.94
                        confidence: 0.99713933
                      - word: to
                        start: 8
                        end: 8.16
                        confidence: 0.9038218
                      - word: bowed
                        start: 8.16
                        end: 8.66
                        confidence: 0.68124074
                      - word: to
                        start: 9.084375
                        end: 9.164375
                        confidence: 0.9726658
                      - word: that
                        start: 9.164375
                        end: 9.484375
                        confidence: 0.22552642
                      - word: might
                        start: 9.484375
                        end: 9.644376
                        confidence: 0.9740415
                      - word: in
                        start: 9.644376
                        end: 9.876875
                        confidence: 0.88410664
                      - word: a
                        start: 9.876875
                        end: 10.109375
                        confidence: 0.5427023
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
  /tts:
    post:
      tags:
      - Voice
      summary: AIMLAPI Text to Speech
      description: This request returns an audio file.
      requestBody:
        content:
          application/json:
            schema:
              type: object
              example:
                model: '{{ttsModel}}'
                text: Hi! I'm your friendly assistant.
      responses:
        '200':
          description: Successful response
          content:
            application/json: {}
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer