Audioscrape Episodes API

openapi: 3.2.0
info:
  title: Audioscrape Com Episodes API
  version: '2026-05-16'
  contact:
    name: Audioscrape
    url: https://www.audioscrape.com
    email: lukas@audioscrape.com
  license:
    name: ''
  description: 'Operations tagged Episodes across 2 of this provider''s published API definitions: audioscrape-com-openapi.json, audioscrape-com-openapi.json. Each path carries the servers of the definition it was published in.'
servers:
- url: https://www.audioscrape.com
  description: Production
tags:
- name: Episodes
  description: Convenience alias for podcast-episode items. For multi-format integrations, prefer `/api/items`.
paths:
  /api/episodes:
    get:
      tags:
      - Episodes
      summary: List recent episodes
      description: Returns the most recently published episodes across all podcasts. Convenience alias for items where `source_type = 'podcast_episode'` — for multi-format integrations, prefer `/api/items`.
      operationId: list_recent_episodes_v1
      parameters:
      - name: limit
        in: query
        description: Max results (default 20, max 100)
        required: false
        schema:
          type: integer
          format: int64
      - name: offset
        in: query
        description: Result offset for pagination
        required: false
        schema:
          type: integer
          format: int64
      responses:
        '200':
          description: Episodes ordered by publish date descending
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/EpisodeList'
        '401':
          description: Missing or invalid API key
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiErrorBody'
        '402':
          description: No active subscription (paid endpoint requires a subscription)
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiErrorBody'
        '403':
          description: Endpoint not available on the caller's plan
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiErrorBody'
        '429':
          description: 'Monthly quota exhausted (response includes `usage: { current, limit }`)'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiErrorBody'
      security:
      - BearerAuth: []
    servers:
    - url: https://www.audioscrape.com
      description: Production
  /api/episodes/{episode_id}:
    get:
      tags:
      - Episodes
      summary: Get episode metadata
      description: Returns the episode + its parent podcast. Heavy fields are opt-in via `?include=` — pass `transcript`, `entities`, or both to load them in the same response. Useful when you want details without paying the cost of fetching a 500KB+ transcript by default.
      operationId: get_public_episode
      parameters:
      - name: episode_id
        in: path
        description: Numeric episode ID
        required: true
        schema:
          type: string
      - name: include
        in: query
        description: 'Comma-separated optional fields: `transcript`, `entities`.'
        required: false
        schema:
          type: string
      responses:
        '200':
          description: Episode + podcast, plus any requested optional fields
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/EpisodeDetail'
        '401':
          description: Missing or invalid API key
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiErrorBody'
        '402':
          description: No active subscription (paid endpoint requires a subscription)
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiErrorBody'
        '403':
          description: Endpoint not available on the caller's plan
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiErrorBody'
        '404':
          description: Episode not found
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiErrorBody'
        '429':
          description: 'Monthly quota exhausted (response includes `usage: { current, limit }`)'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiErrorBody'
      security:
      - BearerAuth: []
    servers:
    - url: https://www.audioscrape.com
      description: Production
  /api/episodes/{episode_id}/transcript:
    get:
      tags:
      - Episodes
      summary: Get episode transcript
      description: Returns the transcript on its own (segments + speaker list). Equivalent to the `transcript` field on `GET /api/episodes/{id}?include=transcript`. Use this endpoint when you don't need the metadata envelope.
      operationId: get_episode_transcript
      parameters:
      - name: episode_id
        in: path
        description: Numeric episode ID
        required: true
        schema:
          type: string
      responses:
        '200':
          description: Transcript segments + speaker list
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Transcript'
        '206':
          description: 'Recording still being transcribed in parts: the finished parts, with `partial` set (speaker labels provisional)'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Transcript'
        '401':
          description: Missing or invalid API key
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiErrorBody'
        '402':
          description: No active subscription (paid endpoint requires a subscription)
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiErrorBody'
        '403':
          description: Endpoint not available on the caller's plan
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiErrorBody'
        '404':
          description: Episode not found or has no transcript
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiErrorBody'
        '429':
          description: 'Monthly quota exhausted (response includes `usage: { current, limit }`)'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiErrorBody'
      security:
      - BearerAuth: []
    servers:
    - url: https://www.audioscrape.com
      description: Production
components:
  schemas:
    EpisodeSummary:
      type: object
      required:
      - id
      - title
      - slug
      - publish_date
      - has_transcript
      properties:
        duration_seconds:
          type:
          - integer
          - 'null'
          format: int32
        has_transcript:
          type: boolean
        id:
          type: integer
          format: int64
        podcast_title:
          type:
          - string
          - 'null'
        publish_date:
          type: string
        slug:
          type: string
        title:
          type: string
    EntityRef:
      type: object
      required:
      - name
      - entity_type
      - slug
      - mention_count
      properties:
        entity_type:
          type: string
        mention_count:
          type: integer
          format: int64
        name:
          type: string
        slug:
          type: string
    EpisodeList:
      type: object
      required:
      - episodes
      - total
      - limit
      - offset
      properties:
        episodes:
          type: array
          items:
            $ref: '#/components/schemas/EpisodeSummary'
        limit:
          type: integer
          format: int64
        offset:
          type: integer
          format: int64
        total:
          type: integer
          format: int64
    EpisodeDetail:
      type: object
      required:
      - episode
      - entities
      properties:
        entities:
          type: array
          items:
            $ref: '#/components/schemas/EntityRef'
        episode:
          $ref: '#/components/schemas/EpisodeFull'
        podcast:
          oneOf:
          - type: 'null'
          - $ref: '#/components/schemas/PodcastRef'
            description: 'Present for podcast episodes; `null` for uploaded items (which have no

              parent podcast).'
        transcript:
          oneOf:
          - type: 'null'
          - $ref: '#/components/schemas/Transcript'
    ApiErrorBody:
      type: object
      required:
      - code
      - message
      properties:
        code:
          type: string
          description: Stable machine-readable error code (UPPERCASE_SNAKE_CASE).
          example: SEARCH_LIMIT_EXCEEDED
        message:
          type: string
          description: Human-readable error message.
          example: Monthly search limit reached
        usage:
          oneOf:
          - type: 'null'
          - $ref: '#/components/schemas/UsageInfo'
            description: Present on rate-limit / quota errors. Omitted otherwise.
    UsageInfo:
      type: object
      required:
      - current
      - limit
      properties:
        current:
          type: integer
          format: int64
          description: Current usage value (e.g., calls consumed this period).
        limit:
          type: integer
          format: int64
          description: Configured limit for the period.
    PodcastRef:
      type: object
      required:
      - id
      - title
      - slug
      properties:
        id:
          type: integer
          format: int64
        image_url:
          type:
          - string
          - 'null'
        slug:
          type: string
        title:
          type: string
    EpisodeFull:
      type: object
      required:
      - id
      - title
      - slug
      - description
      - publish_date
      - processing_status
      properties:
        description:
          type: string
        duration_seconds:
          type:
          - integer
          - 'null'
          format: int32
        enclosure_url:
          type:
          - string
          - 'null'
        id:
          type: integer
          format: int64
        processing_status:
          type: string
          description: 'Pipeline lifecycle of this item: `queued` | `processing` |

            `completed` | `completed_no_speech` | `failed` | `cancelled`, or

            `not_transcribed` for catalog items never queued for transcription.

            `completed_no_speech` means processing finished and the audio

            contained no speech, so no transcript will ever exist: stop polling

            for one (GH#435).'
        publish_date:
          type: string
        slug:
          type: string
        title:
          type: string
    TranscriptPartial:
      type: object
      required:
      - pieces_done
      - pieces_total
      - seconds_transcribed
      - seconds_total
      - speakers_final
      properties:
        pieces_done:
          type: integer
          format: int32
        pieces_total:
          type: integer
          format: int32
        seconds_total:
          type: integer
          format: int64
        seconds_transcribed:
          type: integer
          format: int64
        speakers_final:
          type: boolean
    TranscriptSegment:
      type: object
      required:
      - text
      - start
      - end
      properties:
        end:
          type: number
          format: double
        speaker:
          type:
          - string
          - 'null'
        start:
          type: number
          format: double
        text:
          type: string
    Transcript:
      type: object
      required:
      - segments
      - speakers
      - total_segments
      properties:
        partial:
          oneOf:
          - type: 'null'
          - $ref: '#/components/schemas/TranscriptPartial'
            description: 'Present (with HTTP 206) when the recording is still being

              transcribed in parts and `segments` covers only the finished ones.

              Speaker labels are provisional until the response is a plain 200.'
        segments:
          type: array
          items:
            $ref: '#/components/schemas/TranscriptSegment'
        speakers:
          type: array
          items:
            type: string
        total_segments:
          type: integer
          minimum: 0
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      bearerFormat: API key, format `sk_<base64(32 random bytes)>`
      description: 'Workspace-scoped API key. Pass as `Authorization: Bearer <key>`. The `?api_key=<key>` query parameter is deprecated: a key in a URL ends up in browser history, proxy logs and Referer headers.'
x-refined-from:
- audioscrape-com-openapi.json
- audioscrape-com-openapi.json