Sonix Media API

openapi: 3.2.0
info:
  title: Sonix AI Analysis Media API
  description: The Sonix API lets you programmatically upload audio and video media for automated transcription, retrieve the resulting transcripts, export subtitles and captions (SRT, VTT, TXT, JSON, DOCX, PDF), translate transcripts into other languages, and run AI analysis (summaries, chapters, sentiment, entities). Sonix transcribes in 54+ languages and translates into 55+ languages. The API is available to Sonix subscribers; trial accounts can request an API key from Sonix support. All requests are authorized with a Bearer API key. This description was modeled by API Evangelist from Sonix's public API documentation at https://sonix.ai/docs/api; request and response schemas are honestly modeled where the public docs do not enumerate every field.
  version: '1.0'
  contact:
    name: Sonix
    url: https://sonix.ai
  x-modeled-by: API Evangelist
  x-source: https://sonix.ai/docs/api
servers:
- url: https://api.sonix.ai/v1
  description: Sonix API v1
security:
- bearerAuth: []
tags:
- name: Media
  description: Upload and manage audio and video media files for transcription.
paths:
  /media:
    get:
      operationId: listMedia
      tags:
      - Media
      summary: List media files
      description: Lists media files in your account, paginated at 100 per page. The response includes total_pages for iteration.
      parameters:
      - name: page
        in: query
        required: false
        schema:
          type: integer
          default: 1
        description: Page number to retrieve.
      responses:
        '200':
          description: A paginated list of media files.
          content:
            application/json:
              schema:
                type: object
                properties:
                  media:
                    type: array
                    items:
                      $ref: '#/components/schemas/Media'
                  total_pages:
                    type: integer
        '401':
          $ref: '#/components/responses/Unauthorized'
    post:
      operationId: createMedia
      tags:
      - Media
      summary: Upload media for transcription
      description: Uploads a new media file for transcription, either as a multipart file upload (up to 100MB) or by passing a file_url for larger or remote files. Specify the spoken language so Sonix transcribes it correctly. An optional callback_url receives a webhook when transcription completes.
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/MediaInput'
          application/json:
            schema:
              $ref: '#/components/schemas/MediaInput'
      responses:
        '200':
          description: The created media resource.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Media'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '422':
          $ref: '#/components/responses/ValidationError'
  /media/{id}:
    parameters:
    - $ref: '#/components/parameters/MediaId'
    get:
      operationId: getMedia
      tags:
      - Media
      summary: Retrieve media status
      description: Retrieves a media file and its transcription status. Status values include preparing, transcribing, aligning, completed, blocked, failed, and duplicate.
      responses:
        '200':
          description: The requested media resource.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Media'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '404':
          $ref: '#/components/responses/NotFound'
    put:
      operationId: updateMedia
      tags:
      - Media
      summary: Update media
      description: Updates a media file's name, label, or folder assignment.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/MediaUpdate'
      responses:
        '200':
          description: The updated media resource.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Media'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '404':
          $ref: '#/components/responses/NotFound'
    delete:
      operationId: deleteMedia
      tags:
      - Media
      summary: Delete media
      description: Permanently deletes a media file and its transcript.
      responses:
        '200':
          description: The media file was deleted.
        '401':
          $ref: '#/components/responses/Unauthorized'
        '404':
          $ref: '#/components/responses/NotFound'
components:
  responses:
    ValidationError:
      description: The request was invalid.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    Unauthorized:
      description: The API key is missing or invalid.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    NotFound:
      description: The requested resource was not found.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
  schemas:
    Error:
      type: object
      properties:
        error:
          type: string
        message:
          type: string
    MediaInput:
      type: object
      properties:
        file:
          type: string
          format: binary
          description: The media file to upload (multipart, up to 100MB).
        file_url:
          type: string
          description: URL of a remote media file to transcribe (for large or remote files).
        name:
          type: string
        language:
          type: string
          description: Spoken language code of the media (e.g. en, es, fr).
        folder_id:
          type: string
        callback_url:
          type: string
          description: Webhook URL called when transcription completes.
    Media:
      type: object
      properties:
        id:
          type: string
        name:
          type: string
        status:
          type: string
          description: One of preparing, transcribing, aligning, completed, blocked, failed, duplicate.
        language:
          type: string
        folder_id:
          type: string
        created_at:
          type: string
          format: date-time
    MediaUpdate:
      type: object
      properties:
        name:
          type: string
        label:
          type: string
        folder_id:
          type: string
  parameters:
    MediaId:
      name: id
      in: path
      required: true
      schema:
        type: string
      description: The unique identifier of the media file.
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: 'Sonix API key passed as `Authorization: Bearer <API Key>`. Subscribers find their key at https://my.sonix.ai/api; trial accounts request one from Sonix support.'