Resemble AI subpackage_speechToText API

openapi: 3.1.0
info:
  title: API Reference subpackage_account subpackage_speechToText API
  version: 1.0.0
servers:
- url: https://f.cluster.resemble.ai
- url: https://app.resemble.ai/api/v2
tags:
- name: subpackage_speechToText
paths:
  /speech-to-text:
    get:
      operationId: list-transcripts
      summary: List transcripts
      description: Retrieve paginated list of transcript jobs
      tags:
      - subpackage_speechToText
      parameters:
      - name: page
        in: query
        required: true
        schema:
          type: integer
          default: 1
      - name: per_page
        in: query
        required: false
        schema:
          type: integer
          default: 25
      - name: Authorization
        in: header
        description: API token from https://app.resemble.ai/account/api
        required: true
        schema:
          type: string
      responses:
        '200':
          description: List of transcripts
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Speech-to-Text_listTranscripts_Response_200'
    post:
      operationId: create-transcript
      summary: Create transcript job
      description: Submit audio or video for transcription
      tags:
      - subpackage_speechToText
      parameters:
      - name: Authorization
        in: header
        description: API token from https://app.resemble.ai/account/api
        required: true
        schema:
          type: string
      responses:
        '200':
          description: Transcript job created
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Speech-to-Text_createTranscript_Response_200'
        '400':
          description: Bad request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
      requestBody:
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                file:
                  type: string
                  format: binary
                  description: Audio or video file (max 500 MB, 20 minutes)
                query:
                  type: string
                  description: Optional intelligence question to evaluate after transcription
  /speech-to-text/{uuid}:
    get:
      operationId: get-transcript
      summary: Get transcript
      description: Retrieve transcript status, text, and timestamps
      tags:
      - subpackage_speechToText
      parameters:
      - name: uuid
        in: path
        required: true
        schema:
          type: string
          format: uuid
      - name: Authorization
        in: header
        description: API token from https://app.resemble.ai/account/api
        required: true
        schema:
          type: string
      responses:
        '200':
          description: Transcript details
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Speech-to-Text_getTranscript_Response_200'
  /speech-to-text/{uuid}/ask:
    post:
      operationId: ask-transcript-question
      summary: Ask intelligence question
      description: Submit a question about a completed transcript
      tags:
      - subpackage_speechToText
      parameters:
      - name: uuid
        in: path
        required: true
        schema:
          type: string
          format: uuid
      - name: Authorization
        in: header
        description: API token from https://app.resemble.ai/account/api
        required: true
        schema:
          type: string
      responses:
        '200':
          description: Question submitted
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Speech-to-Text_askTranscriptQuestion_Response_200'
      requestBody:
        content:
          application/json:
            schema:
              type: object
              properties:
                query:
                  type: string
                  description: Question to ask about the transcript
              required:
              - query
  /speech-to-text/{uuid}/questions:
    get:
      operationId: list-transcript-questions
      summary: List intelligence questions
      description: List all questions asked about a transcript
      tags:
      - subpackage_speechToText
      parameters:
      - name: uuid
        in: path
        required: true
        schema:
          type: string
          format: uuid
      - name: page
        in: query
        required: true
        schema:
          type: integer
          default: 1
      - name: per_page
        in: query
        required: false
        schema:
          type: integer
          default: 25
      - name: Authorization
        in: header
        description: API token from https://app.resemble.ai/account/api
        required: true
        schema:
          type: string
      responses:
        '200':
          description: List of questions
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Speech-to-Text_listTranscriptQuestions_Response_200'
  /speech-to-text/{uuid}/questions/{question_uuid}:
    get:
      operationId: get-transcript-question
      summary: Get intelligence question status
      description: Check the status of a specific question
      tags:
      - subpackage_speechToText
      parameters:
      - name: uuid
        in: path
        required: true
        schema:
          type: string
          format: uuid
      - name: question_uuid
        in: path
        required: true
        schema:
          type: string
          format: uuid
      - name: Authorization
        in: header
        description: API token from https://app.resemble.ai/account/api
        required: true
        schema:
          type: string
      responses:
        '200':
          description: Question details
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Speech-to-Text_getTranscriptQuestion_Response_200'
components:
  schemas:
    SpeechToTextUuidQuestionsGetResponsesContentApplicationJsonSchemaMeta:
      type: object
      properties: {}
      title: SpeechToTextUuidQuestionsGetResponsesContentApplicationJsonSchemaMeta
    SpeechToTextUuidGetResponsesContentApplicationJsonSchemaItemStatus:
      type: string
      enum:
      - pending
      - processing
      - completed
      - failed
      title: SpeechToTextUuidGetResponsesContentApplicationJsonSchemaItemStatus
    Speech-to-Text_askTranscriptQuestion_Response_200:
      type: object
      properties:
        success:
          type: boolean
        item:
          $ref: '#/components/schemas/SpeechToTextUuidAskPostResponsesContentApplicationJsonSchemaItem'
      title: Speech-to-Text_askTranscriptQuestion_Response_200
    SpeechToTextPostResponsesContentApplicationJsonSchemaItem:
      type: object
      properties:
        uuid:
          type: string
          format: uuid
        status:
          $ref: '#/components/schemas/SpeechToTextPostResponsesContentApplicationJsonSchemaItemStatus'
        created_at:
          type: string
          format: date-time
        updated_at:
          type: string
          format: date-time
      title: SpeechToTextPostResponsesContentApplicationJsonSchemaItem
    SpeechToTextGetResponsesContentApplicationJsonSchemaItemsItems:
      type: object
      properties:
        uuid:
          type: string
          format: uuid
        status:
          type: string
        duration_seconds:
          type: number
          format: double
        created_at:
          type: string
          format: date-time
        updated_at:
          type: string
          format: date-time
      title: SpeechToTextGetResponsesContentApplicationJsonSchemaItemsItems
    SpeechToTextUuidGetResponsesContentApplicationJsonSchemaItemWordsItems:
      type: object
      properties:
        text:
          type: string
        start_time:
          type: number
          format: double
        end_time:
          type: number
          format: double
        speaker_id:
          type: string
      title: SpeechToTextUuidGetResponsesContentApplicationJsonSchemaItemWordsItems
    SpeechToTextGetResponsesContentApplicationJsonSchemaMeta:
      type: object
      properties:
        page:
          type: integer
        per_page:
          type: integer
        total_pages:
          type: integer
        total_items:
          type: integer
      title: SpeechToTextGetResponsesContentApplicationJsonSchemaMeta
    Speech-to-Text_getTranscript_Response_200:
      type: object
      properties:
        success:
          type: boolean
        item:
          $ref: '#/components/schemas/SpeechToTextUuidGetResponsesContentApplicationJsonSchemaItem'
      title: Speech-to-Text_getTranscript_Response_200
    Error:
      type: object
      properties:
        success:
          type: boolean
        error:
          type: string
        errors:
          type: object
          additionalProperties:
            type: array
            items:
              type: string
        message:
          type: string
      title: Error
    Speech-to-Text_listTranscripts_Response_200:
      type: object
      properties:
        success:
          type: boolean
        items:
          type: array
          items:
            $ref: '#/components/schemas/SpeechToTextGetResponsesContentApplicationJsonSchemaItemsItems'
        meta:
          $ref: '#/components/schemas/SpeechToTextGetResponsesContentApplicationJsonSchemaMeta'
      title: Speech-to-Text_listTranscripts_Response_200
    Speech-to-Text_getTranscriptQuestion_Response_200:
      type: object
      properties:
        success:
          type: boolean
        item:
          $ref: '#/components/schemas/SpeechToTextUuidQuestionsQuestionUuidGetResponsesContentApplicationJsonSchemaItem'
      title: Speech-to-Text_getTranscriptQuestion_Response_200
    SpeechToTextUuidGetResponsesContentApplicationJsonSchemaItem:
      type: object
      properties:
        uuid:
          type: string
          format: uuid
        status:
          $ref: '#/components/schemas/SpeechToTextUuidGetResponsesContentApplicationJsonSchemaItemStatus'
        text:
          type: string
        words:
          type: array
          items:
            $ref: '#/components/schemas/SpeechToTextUuidGetResponsesContentApplicationJsonSchemaItemWordsItems'
        duration_seconds:
          type: number
          format: double
        file_url:
          type: string
          format: uri
        query:
          type: string
        answer:
          type: string
        created_at:
          type: string
          format: date-time
        updated_at:
          type: string
          format: date-time
      title: SpeechToTextUuidGetResponsesContentApplicationJsonSchemaItem
    SpeechToTextPostResponsesContentApplicationJsonSchemaItemStatus:
      type: string
      enum:
      - pending
      - processing
      - completed
      - failed
      title: SpeechToTextPostResponsesContentApplicationJsonSchemaItemStatus
    SpeechToTextUuidQuestionsGetResponsesContentApplicationJsonSchemaItemsItems:
      type: object
      properties:
        uuid:
          type: string
          format: uuid
        query:
          type: string
        answer:
          type: string
        status:
          type: string
        created_at:
          type: string
          format: date-time
      title: SpeechToTextUuidQuestionsGetResponsesContentApplicationJsonSchemaItemsItems
    Speech-to-Text_listTranscriptQuestions_Response_200:
      type: object
      properties:
        success:
          type: boolean
        items:
          type: array
          items:
            $ref: '#/components/schemas/SpeechToTextUuidQuestionsGetResponsesContentApplicationJsonSchemaItemsItems'
        meta:
          $ref: '#/components/schemas/SpeechToTextUuidQuestionsGetResponsesContentApplicationJsonSchemaMeta'
      title: Speech-to-Text_listTranscriptQuestions_Response_200
    SpeechToTextUuidAskPostResponsesContentApplicationJsonSchemaItem:
      type: object
      properties:
        uuid:
          type: string
          format: uuid
        transcript_uuid:
          type: string
          format: uuid
        query:
          type: string
        status:
          type: string
        created_at:
          type: string
          format: date-time
      title: SpeechToTextUuidAskPostResponsesContentApplicationJsonSchemaItem
    Speech-to-Text_createTranscript_Response_200:
      type: object
      properties:
        success:
          type: boolean
        item:
          $ref: '#/components/schemas/SpeechToTextPostResponsesContentApplicationJsonSchemaItem'
      title: Speech-to-Text_createTranscript_Response_200
    SpeechToTextUuidQuestionsQuestionUuidGetResponsesContentApplicationJsonSchemaItem:
      type: object
      properties:
        uuid:
          type: string
          format: uuid
        transcript_uuid:
          type: string
          format: uuid
        query:
          type: string
        answer:
          type: string
        status:
          type: string
        created_at:
          type: string
          format: date-time
        updated_at:
          type: string
          format: date-time
      title: SpeechToTextUuidQuestionsQuestionUuidGetResponsesContentApplicationJsonSchemaItem
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      description: API token from https://app.resemble.ai/account/api