AssemblyAI
AssemblyAI API

The AssemblyAI API provides speech-to-text transcription, speaker diarization, sentiment analysis, chapter detection, PII redaction, and other audio intelligence capabilities via REST and WebSocket interfaces.
Documentation GitHub OpenAPI
OpenAPI Specification

openapi: 3.1.0

info:
  title: AssemblyAI API
  description: AssemblyAI API
  version: 1.1.2
  contact:
    name: API Support
    email: [email protected]
    url: https://www.assemblyai.com/docs/

servers:
  - url: https://api.assemblyai.com
    description: AssemblyAI API

tags:
  - name: LeMUR
    description: LeMUR related operations
    externalDocs:
      url: https://www.assemblyai.com/docs/guides/processing-audio-with-llms-using-lemur
  - name: Streaming
    description: Streaming Speech-to-Text
    externalDocs:
      url: https://www.assemblyai.com/docs/speech-to-text/streaming

  - name: Transcript
    description: Transcript related operations
    externalDocs:
      url: https://www.assemblyai.com/docs/guides/transcribing-an-audio-file
security:
  - ApiKey: []

paths:
  /v2/upload:
    post:
      tags:
        - Transcript
      summary: AssemblyAI Upload a media file
      description: Upload a media file to AssemblyAI's servers.
      operationId: uploadFile
      x-fern-sdk-group-name: files
      x-fern-sdk-method-name: upload
      requestBody:
        content:
          application/octet-stream: {}
      responses:
        "200":
          x-label: Media file uploaded
          description: Media file uploaded successfully
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/UploadedFile"
        "400":
          $ref: "#/components/responses/BadRequest"
        "401":
          $ref: "#/components/responses/Unauthorized"
        "404":
          $ref: "#/components/responses/NotFound"
        "429":
          $ref: "#/components/responses/TooManyRequests"
        "500":
          $ref: "#/components/responses/InternalServerError"
        "503":
          $ref: "#/components/responses/ServiceUnavailable"
        "504":
          $ref: "#/components/responses/GatewayTimeout"

  /v2/transcript:
    post:
      tags:
        - Transcript
      summary: AssemblyAI Transcribe audio
      description: Create a transcript from a media file that is accessible via a URL.
      operationId: createTranscript
      x-fern-sdk-group-name: transcripts
      x-fern-sdk-method-name: submit
      x-fern-request-name: TranscriptParams
      requestBody:
        description: Params to create a transcript
        required: true
        content:
          application/json:
            schema:
              $ref: "#/components/schemas/TranscriptParams"
      responses:
        "200":
          x-label: Transcript created
          description: Transcript created and queued for processing
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/Transcript"
          links:
            GetTranscriptById:
              $ref: "#/components/links/GetTranscriptById"
            GetTranscriptSentencesById:
              $ref: "#/components/links/GetTranscriptSentencesById"
            GetTranscriptParagraphsById:
              $ref: "#/components/links/GetTranscriptParagraphsById"
            GetTranscriptSubtitlesById:
              $ref: "#/components/links/GetTranscriptSubtitlesById"
            GetTranscriptRedactedAudioById:
              $ref: "#/components/links/GetTranscriptRedactedAudioById"
            WordSearchByTranscriptId:
              $ref: "#/components/links/WordSearchByTranscriptId"
            DeleteTranscriptById:
              $ref: "#/components/links/DeleteTranscriptById"
        "400":
          $ref: "#/components/responses/BadRequest"
        "401":
          $ref: "#/components/responses/Unauthorized"
        "404":
          $ref: "#/components/responses/NotFound"
        "429":
          $ref: "#/components/responses/TooManyRequests"
        "500":
          $ref: "#/components/responses/InternalServerError"
        "503":
          $ref: "#/components/responses/ServiceUnavailable"
        "504":
          $ref: "#/components/responses/GatewayTimeout"
      callbacks:
        transcriptWebhook:
          "{$request.body#/webhook_url}":
            post:
              requestBody:
                required: true
                content:
                  application/json:
                    schema:
                      $ref: "#/components/schemas/TranscriptReadyNotification"

              responses:
                "200":
                  description: Successfully received the notification

    get:
      tags:
        - Transcript
      summary: AssemblyAI List transcripts
      x-fern-sdk-group-name: transcripts
      x-fern-sdk-method-name: list
      x-fern-request-name: ListTranscriptParams
      operationId: listTranscripts
      description: |
        Retrieve a list of transcripts you created.
        Transcripts are sorted from newest to oldest. The previous URL always points to a page with older transcripts.
      parameters:
        - name: limit
          x-label: Limit
          in: query
          description: Maximum amount of transcripts to retrieve
          schema:
            $ref: "#/components/schemas/ListTranscriptParams/properties/limit"
        - name: status
          x-label: Status
          in: query
          description: Filter by transcript status
          schema:
            # Use TranscriptStatus instead of
            # ListTranscriptParams/properties/limit for better SDK generation
            $ref: "#/components/schemas/TranscriptStatus"

        - name: created_on
          x-label: Created on
          in: query
          description: Only get transcripts created on this date
          schema:
            $ref: "#/components/schemas/ListTranscriptParams/properties/created_on"

        - name: before_id
          x-label: Before ID
          in: query
          description: Get transcripts that were created before this transcript ID
          schema:
            $ref: "#/components/schemas/ListTranscriptParams/properties/before_id"

        - name: after_id
          x-label: After ID
          in: query
          description: Get transcripts that were created after this transcript ID
          schema:
            $ref: "#/components/schemas/ListTranscriptParams/properties/after_id"

        - name: throttled_only
          x-label: Throttled only
          in: query
          description: Only get throttled transcripts, overrides the status filter
          schema:
            $ref: "#/components/schemas/ListTranscriptParams/properties/throttled_only"
      responses:
        "200":
          description: |
            A list of transcripts. Transcripts are sorted from newest to oldest. The previous URL always points to a page with older transcripts.
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/TranscriptList"
        "400":
          $ref: "#/components/responses/BadRequest"
        "401":
          $ref: "#/components/responses/Unauthorized"
        "404":
          $ref: "#/components/responses/NotFound"
        "429":
          $ref: "#/components/responses/TooManyRequests"
        "500":
          $ref: "#/components/responses/InternalServerError"
        "503":
          $ref: "#/components/responses/ServiceUnavailable"
        "504":
          $ref: "#/components/responses/GatewayTimeout"

  /v2/transcript/{transcript_id}:
    get:
      tags:
        - Transcript
      summary: AssemblyAI Get transcript
      operationId: getTranscript
      x-fern-sdk-group-name: transcripts
      x-fern-sdk-method-name: get
      x-fern-request-name: GetTranscriptParams
      description: Get the transcript resource. The transcript is ready when the "status" is "completed".
      parameters:
        - name: transcript_id
          x-label: Transcript ID
          in: path
          description: ID of the transcript
          required: true
          schema:
            type: string
      responses:
        "200":
          description: The transcript resource
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/Transcript"
          links:
            GetTranscriptById:
              $ref: "#/components/links/GetTranscriptById"
            GetTranscriptSentencesById:
              $ref: "#/components/links/GetTranscriptSentencesById"
            GetTranscriptParagraphsById:
              $ref: "#/components/links/GetTranscriptParagraphsById"
            GetTranscriptSubtitlesById:
              $ref: "#/components/links/GetTranscriptSubtitlesById"
            GetTranscriptRedactedAudioById:
              $ref: "#/components/links/GetTranscriptRedactedAudioById"
            WordSearchByTranscriptId:
              $ref: "#/components/links/WordSearchByTranscriptId"
            DeleteTranscriptById:
              $ref: "#/components/links/DeleteTranscriptById"
        "400":
          $ref: "#/components/responses/BadRequest"
        "401":
          $ref: "#/components/responses/Unauthorized"
        "404":
          $ref: "#/components/responses/NotFound"
        "429":
          $ref: "#/components/responses/TooManyRequests"
        "500":
          $ref: "#/components/responses/InternalServerError"
        "503":
          $ref: "#/components/responses/ServiceUnavailable"
        "504":
          $ref: "#/components/responses/GatewayTimeout"

    delete:
      tags:
        - Transcript
      summary: AssemblyAI Delete transcript
      description: |
        Delete the transcript.
        Deleting does not delete the resource itself, but removes the data from the resource and marks it as deleted.
      operationId: deleteTranscript
      x-fern-sdk-group-name: transcripts
      x-fern-sdk-method-name: delete
      parameters:
        - name: transcript_id
          x-label: Transcript ID
          in: path
          description: ID of the transcript
          required: true
          schema:
            type: string
      responses:
        "200":
          description: The deleted transcript response
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/Transcript"
        "400":
          $ref: "#/components/responses/BadRequest"
        "401":
          $ref: "#/components/responses/Unauthorized"
        "404":
          $ref: "#/components/responses/NotFound"
        "429":
          $ref: "#/components/responses/TooManyRequests"
        "500":
          $ref: "#/components/responses/InternalServerError"
        "503":
          $ref: "#/components/responses/ServiceUnavailable"
        "504":
          $ref: "#/components/responses/GatewayTimeout"

  /v2/transcript/{transcript_id}/{subtitle_format}:
    get:
      tags:
        - Transcript
      summary: AssemblyAI Get subtitles for transcript
      description: Export your transcript in SRT or VTT format to use with a video player for subtitles and closed captions.
      operationId: getSubtitles
      x-fern-sdk-group-name: transcripts
      x-fern-sdk-method-name: getSubtitles
      x-fern-request-name: GetSubtitlesParams
      parameters:
        - name: transcript_id
          x-label: Transcript ID
          in: path
          description: ID of the transcript
          required: true
          schema:
            type: string
        - name: subtitle_format
          x-label: Subtitle format
          in: path
          description: The format of the captions
          required: true
          schema:
            $ref: "#/components/schemas/SubtitleFormat"
        - name: chars_per_caption
          x-label: Number of characters per caption
          in: query
          description: The maximum number of characters per caption
          schema:
            type: integer

      responses:
        "200":
          description: The exported captions as text
          content:
            text/plain:
              schema:
                type: string
                example: |
                  WEBVTT
                  00:12.340 --> 00:16.220
                  Last year I showed these two slides said that demonstrate
                  00:16.200 --> 00:20.040
                  that the Arctic ice cap which for most of the last 3,000,000 years has been the
                  00:20.020 --> 00:25.040
                  size of the lower 48 States has shrunk by 40% but this understates
        "400":
          $ref: "#/components/responses/BadRequest"
        "401":
          $ref: "#/components/responses/Unauthorized"
        "404":
          $ref: "#/components/responses/NotFound"
        "429":
          $ref: "#/components/responses/TooManyRequests"
        "500":
          $ref: "#/components/responses/InternalServerError"
        "503":
          $ref: "#/components/responses/ServiceUnavailable"
        "504":
          $ref: "#/components/responses/GatewayTimeout"

  /v2/transcript/{transcript_id}/sentences:
    get:
      tags:
        - Transcript
      summary: AssemblyAI Get sentences in transcript
      operationId: getTranscriptSentences
      x-fern-sdk-group-name: transcripts
      x-fern-sdk-method-name: getSentences
      x-fern-request-name: GetSentencesParams
      description: Get the transcript split by sentences. The API will attempt to semantically segment the transcript into sentences to create more reader-friendly transcripts.
      parameters:
        - name: transcript_id
          x-label: Transcript ID
          in: path
          description: ID of the transcript
          required: true
          schema:
            type: string
      responses:
        "200":
          description: Exported sentences
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/SentencesResponse"
        "400":
          $ref: "#/components/responses/BadRequest"
        "401":
          $ref: "#/components/responses/Unauthorized"
        "404":
          $ref: "#/components/responses/NotFound"
        "429":
          $ref: "#/components/responses/TooManyRequests"
        "500":
          $ref: "#/components/responses/InternalServerError"
        "503":
          $ref: "#/components/responses/ServiceUnavailable"
        "504":
          $ref: "#/components/responses/GatewayTimeout"

  /v2/transcript/{transcript_id}/paragraphs:
    get:
      tags:
        - Transcript
      summary: AssemblyAI Get paragraphs in transcript
      operationId: getTranscriptParagraphs
      x-fern-sdk-group-name: transcripts
      x-fern-sdk-method-name: getParagraphs
      x-fern-request-name: GetParagraphsParams
      description: Get the transcript split by paragraphs. The API will attempt to semantically segment your transcript into paragraphs to create more reader-friendly transcripts.
      parameters:
        - name: transcript_id
          x-label: Transcript ID
          in: path
          description: ID of the transcript
          required: true
          schema:
            type: string
      responses:
        "200":
          description: Exported paragraphs
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/ParagraphsResponse"
        "400":
          $ref: "#/components/responses/BadRequest"
        "401":
          $ref: "#/components/responses/Unauthorized"
        "404":
          $ref: "#/components/responses/NotFound"
        "429":
          $ref: "#/components/responses/TooManyRequests"
        "500":
          $ref: "#/components/responses/InternalServerError"
        "503":
          $ref: "#/components/responses/ServiceUnavailable"
        "504":
          $ref: "#/components/responses/GatewayTimeout"

  /v2/transcript/{transcript_id}/word-search:
    get:
      tags:
        - Transcript
      summary: AssemblyAI Search words in transcript
      description: Search through the transcript for keywords. You can search for individual words, numbers, or phrases containing up to five words or numbers.
      operationId: wordSearch
      x-fern-sdk-group-name: transcripts
      x-fern-sdk-method-name: wordSearch
      x-fern-request-name: WordSearchParams
      parameters:
        - name: transcript_id
          x-label: Transcript ID
          in: path
          description: ID of the transcript
          required: true
          schema:
            type: string
        - name: words
          x-label: Words
          in: query
          description: Keywords to search for
          required: true
          style: form
          explode: false
          schema:
            type: array
            items:
              x-label: Word
              type: string

      responses:
        "200":
          description: Word search response
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/WordSearchResponse"
        "400":
          $ref: "#/components/responses/BadRequest"
        "401":
          $ref: "#/components/responses/Unauthorized"
        "404":
          $ref: "#/components/responses/NotFound"
        "429":
          $ref: "#/components/responses/TooManyRequests"
        "500":
          $ref: "#/components/responses/InternalServerError"
        "503":
          $ref: "#/components/responses/ServiceUnavailable"
        "504":
          $ref: "#/components/responses/GatewayTimeout"

  /v2/transcript/{transcript_id}/redacted-audio:
    get:
      tags:
        - Transcript
      summary: AssemblyAI Get redacted audio
      description: Retrieve the redacted audio object containing the status and URL to the redacted audio.
      operationId: getRedactedAudio
      x-fern-sdk-group-name: transcripts
      x-fern-sdk-method-name: getRedactedAudio
      x-fern-request-name: GetRedactedAudioParams
      parameters:
        - name: transcript_id
          x-label: Transcript ID
          in: path
          description: ID of the transcript
          required: true
          schema:
            type: string

      responses:
        "200":
          description: The redacted audio object containing the status and URL to the redacted audio
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/RedactedAudioResponse"
        "400":
          $ref: "#/components/responses/BadRequest"
        "401":
          $ref: "#/components/responses/Unauthorized"
        "404":
          $ref: "#/components/responses/NotFound"
        "429":
          $ref: "#/components/responses/TooManyRequests"
        "500":
          $ref: "#/components/responses/InternalServerError"
        "503":
          $ref: "#/components/responses/ServiceUnavailable"
        "504":
          $ref: "#/components/responses/GatewayTimeout"

  /v2/realtime/token:
    post:
      tags:
        - Streaming
      summary: AssemblyAI Create temporary authentication token for Streaming STT
      description: Create a temporary authentication token for Streaming Speech-to-Text
      operationId: createTemporaryToken
      x-fern-sdk-group-name: realtime
      x-fern-sdk-method-name: createTemporaryToken
      x-fern-request-name: CreateRealtimeTemporaryTokenParams
      requestBody:
        description: Params to create a temporary authentication token
        required: true
        content:
          application/json:
            schema:
              $ref: "#/components/schemas/CreateRealtimeTemporaryTokenParams"
      responses:
        "200":
          description: Temporary authentication token generated
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/RealtimeTemporaryTokenResponse"
        "400":
          $ref: "#/components/responses/BadRequest"
        "401":
          $ref: "#/components/responses/Unauthorized"
        "404":
          $ref: "#/components/responses/NotFound"
        "429":
          $ref: "#/components/responses/TooManyRequests"
        "500":
          $ref: "#/components/responses/InternalServerError"
        "503":
          $ref: "#/components/responses/ServiceUnavailable"
        "504":
          $ref: "#/components/responses/GatewayTimeout"

  /lemur/v3/generate/task:
    post:
      tags:
        - LeMUR
      summary: AssemblyAI Run a task using LeMUR
      description: Use the LeMUR task endpoint to input your own LLM prompt.
      operationId: lemurTask
      x-fern-sdk-group-name: lemur
      x-fern-sdk-method-name: task
      x-fern-request-name: LemurTaskParams
      requestBody:
        description: Params to run the task
        required: true
        content:
          application/json:
            schema:
              $ref: "#/components/schemas/LemurTaskParams"
      responses:
        "200":
          description: LeMUR task response
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/LemurTaskResponse"
          links:
            PurgeLemurRequestDataById:
              $ref: "#/components/links/PurgeLemurRequestDataById"
        "400":
          $ref: "#/components/responses/BadRequest"
        "401":
          $ref: "#/components/responses/Unauthorized"
        "404":
          $ref: "#/components/responses/NotFound"
        "429":
          $ref: "#/components/responses/TooManyRequests"
        "500":
          $ref: "#/components/responses/InternalServerError"
        "503":
          $ref: "#/components/responses/ServiceUnavailable"
        "504":
          $ref: "#/components/responses/GatewayTimeout"

  /lemur/v3/generate/summary:
    post:
      tags:
        - LeMUR
      summary: AssemblyAI Summarize a transcript using LeMUR
      description: |
        Custom Summary allows you to distill a piece of audio into a few impactful sentences.
        You can give the model context to obtain more targeted results while outputting the results in a variety of formats described in human language.
      operationId: lemurSummary
      x-fern-sdk-group-name: lemur
      x-fern-sdk-method-name: summary
      x-fern-request-name: LemurSummaryParams
      requestBody:
        description: Params to generate the summary
        required: true
        content:
          application/json:
            schema:
              $ref: "#/components/schemas/LemurSummaryParams"
      responses:
        "200":
          description: LeMUR summary response
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/LemurSummaryResponse"
          links:
            PurgeLemurRequestDataById:
              $ref: "#/components/links/PurgeLemurRequestDataById"
        "400":
          $ref: "#/components/responses/BadRequest"
        "401":
          $ref: "#/components/responses/Unauthorized"
        "404":
          $ref: "#/components/responses/NotFound"
        "429":
          $ref: "#/components/responses/TooManyRequests"
        "500":
          $ref: "#/components/responses/InternalServerError"
        "503":
          $ref: "#/components/responses/ServiceUnavailable"
        "504":
          $ref: "#/components/responses/GatewayTimeout"

  /lemur/v3/generate/question-answer:
    post:
      tags:
        - LeMUR
      summary: AssemblyAI Ask questions using LeMUR
      description: |
        Question & Answer allows you to ask free-form questions about a single transcript or a group of transcripts.
        The questions can be any whose answers you find useful, such as judging whether a caller is likely to become a customer or whether all items on a meeting's agenda were covered.
      operationId: lemurQuestionAnswer
      x-fern-sdk-group-name: lemur
      x-fern-sdk-method-name: questionAnswer
      x-fern-request-name: LemurQuestionAnswerParams
      requestBody:
        description: Params to ask questions about the transcripts
        required: true
        content:
          application/json:
            schema:
              $ref: "#/components/schemas/LemurQuestionAnswerParams"
      responses:
        "200":
          description: LeMUR question & answer response
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/LemurQuestionAnswerResponse"
          links:
            PurgeLemurRequestDataById:
              $ref: "#/components/links/PurgeLemurRequestDataById"
        "400":
          $ref: "#/components/responses/BadRequest"
        "401":
          $ref: "#/components/responses/Unauthorized"
        "404":
          $ref: "#/components/responses/NotFound"
        "429":
          $ref: "#/components/responses/TooManyRequests"
        "500":
          $ref: "#/components/responses/InternalServerError"
        "503":
          $ref: "#/components/responses/ServiceUnavailable"
        "504":
          $ref: "#/components/responses/GatewayTimeout"

  /lemur/v3/generate/action-items:
    post:
      tags:
        - LeMUR
      summary: AssemblyAI Extract action items
      operationId: lemurActionItems
      x-label: Extract action items using LeMUR
      x-fern-sdk-group-name: lemur
      x-fern-sdk-method-name: actionItems
      x-fern-request-name: LemurActionItemsParams
      description: Use LeMUR to generate a list of action items from a transcript
      requestBody:
        description: Params to generate action items from transcripts
        required: true
        content:
          application/json:
            schema:
              $ref: "#/components/schemas/LemurActionItemsParams"
      responses:
        "200":
          description: LeMUR action items response
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/LemurActionItemsResponse"
          links:
            PurgeLemurRequestDataById:
              $ref: "#/components/links/PurgeLemurRequestDataById"
        "400":
          $ref: "#/components/responses/BadRequest"
        "401":
          $ref: "#/components/responses/Unauthorized"
        "404":
          $ref: "#/components/responses/NotFound"
        "429":
          $ref: "#/components/responses/TooManyRequests"
        "500":
          $ref: "#/components/responses/InternalServerError"
        "503":
          $ref: "#/components/responses/ServiceUnavailable"
        "504":
          $ref: "#/components/responses/GatewayTimeout"

  /lemur/v3/{request_id}:
    delete:
      tags:
        - LeMUR
      summary: AssemblyAI Purge LeMUR request data
      description: |
        Delete the data for a previously submitted LeMUR request.
        The LLM response data, as well as any context provided in the original request will be removed.
      operationId: purgeLemurRequestData
      x-fern-sdk-group-name: lemur
      x-fern-sdk-method-name: purgeRequestData
      x-fern-request-name: PurgeLemurRequestDataParams
      parameters:
        - name: request_id
          x-label: LeMUR request ID
          in: path
          description: The ID of the LeMUR request whose data you want to delete. This would be found in the response of the original request.
          required: true
          schema:
            type: string
      responses:
        "200":
          description: LeMUR request data deleted
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/PurgeLemurRequestDataResponse"
        "400":
          $ref: "#/components/responses/BadRequest"
        "401":
          $ref: "#/components/responses/Unauthorized"
        "404":
          $ref: "#/components/responses/NotFound"
        "429":
          $ref: "#/components/responses/TooManyRequests"
        "500":
          $ref: "#/components/responses/InternalServerError"
        "503":
          $ref: "#/components/responses/ServiceUnavailable"
        "504":
          $ref: "#/components/responses/GatewayTimeout"
AssemblyAI API

Documentation

Specifications

Other Resources

OpenAPI Specification
