Vulavula Logo
Vulavula API

​transcribe

Convert spoken words from audio to text.

​Speedy transcription of shorter audios in WAV format

POST
/api/v2alpha/transcribe/fast

TRANSCRIBE FAST

Transcribes WAV formatted audio as quickly as possible.

This endpoint has the following limitations

  • Accepts WAV files only
  • Quality profile must be mono-channel, 16khz sample rate, 16-bit sample width
  • Maximum audio length of 6 minutes or file size of 11MB

Args

  • upload: file content in bytes as part of form data.
  • language_code: (optional) the expected language if known - [zul, sot, afr, eng, fra]

​Speedy transcription of shorter audios in WAV format › query Parameters

  • lang_code

​Speedy transcription of shorter audios in WAV format › Request Body

  • uploadstring · binary · required

​Speedy transcription of shorter audios in WAV format › Responses

    No response specified

​Transcribe an audio file (received as base64) in one request

POST
/api/v2alpha/transcribe/sync

TRANSCRIBE SYNC

Accepts an audio file in one of the supported formats and returns the recognised speech within the same HTTP request/response cycle.

Supported formats: wav, mp3, flac, aac, ogg, mp4, aiff, opus

Note: processing may take up to 2min30s or fail altogether on long, low-quality or complex audio.

Args

  • file_name: name of the audio file
  • audio_blob: file byte contents as a base64-encoded string
  • language_code: (optional) the expected language if known - [zul, sot, afr, eng, fra]

​Transcribe an audio file (received as base64) in one request › Request Body

  • file_namestring · required
  • audio_blobrequired
  • file_sizeinteger · required
  • language_code
  • channels
  • sample_rate
  • frame_rate

​Transcribe an audio file (received as base64) in one request › Responses

    No response specified

​Transcribe an audio file (received as a file) in one request

POST
/api/v2alpha/transcribe/sync/file

TRANSCRIBE SYNC FILE

Accepts an audio file in one of the supported formats and returns the recognised speech within the same HTTP request/response cycle.

Supported formats: wav, mp3, flac, aac, ogg, mp4, aiff, opus

Note: processing may take up to 2min30s or fail altogether on long, low-quality or complex audio.

Args

  • file: file content in bytes as part of form data.
  • lang_code: (optional) the expected language if known - [zul, sot, afr, eng, fra]
  • diarise: (optional) enable diarisation
  • detect_music: (optional) enable music detection

Returns

  • TranscriptionDto: a data transfer object containing the transcribed text and other details

Raises

  • HTTPException 415: if the file type is not supported
  • HTTPException 413: if the file size exceeds the maximum allowed limit (100MB)
  • HTTPException 503: if downstream services are not yet available to serve requests.

​Transcribe an audio file (received as a file) in one request › query Parameters

  • lang_code
  • diariseboolean

    Enable diarisation

  • detect_musicboolean

    Enable music detection

​Transcribe an audio file (received as a file) in one request › Request Body

  • filestring · binary · required

​Transcribe an audio file (received as a file) in one request › Responses

    • id
    • upload_file_size
    • audio_length_seconds
    • sample_rate
    • channels
    • frame_rate
    • mime_type
    • language_code
    • diarisation_result
    • transcription_text
    • transcription_status
    • error_message
    • status_datetime
    • upload_datetime
    • warnings

​List all the batches that have been created

GET
/api/v2alpha/transcribe/batch

​List all the batches that have been created › Responses

    object[]
    • statusstring · enum · required
      Enum values:
      REQUESTED
      UPLOADED
      PROCESSING
      COMPLETE
      FAILED
      RETRYING
    • id
    • customer_id

      Services customer id.

    • project_id

      Services project id.

    • keychain_id

      Keychain ID.

    • language_code
    • created_at
    • updated_at

​Request a container to upload files for bulk processing

POST
/api/v2alpha/transcribe/batch

​Request a container to upload files for bulk processing › Responses

    • batch_idstring · required
    • blob_endpointstring · required
    • sas_tokenstring · required

​Kick off the transcription process for a batch of files

POST
/api/v2alpha/transcribe/batch/{id}/process

​Kick off the transcription process for a batch of files › path Parameters

  • idstring · required

​Kick off the transcription process for a batch of files › query Parameters

  • lang_code

    Language of audio if known. Choose: zul, sot, eng, afr, fra

  • diariseboolean

    Enable diarisation

​Kick off the transcription process for a batch of files › Responses

    No response specified

​Get more details of a specific batch

GET
/api/v2alpha/transcribe/batch/{id}

​Get more details of a specific batch › path Parameters

  • idstring · required

​Get more details of a specific batch › Responses

    • statusstring · enum · required
      Enum values:
      REQUESTED
      UPLOADED
      PROCESSING
      COMPLETE
      FAILED
      RETRYING
    • id
    • customer_id

      Services customer id.

    • project_id

      Services project id.

    • keychain_id

      Keychain ID.

    • language_code
    • created_at
    • updated_at

​List all the transcripts in a batch

GET
/api/v2alpha/transcribe/batch/{id}/transcriptions

​List all the transcripts in a batch › path Parameters

  • idstring · required

​List all the transcripts in a batch › Responses

    object[]
    • id
    • upload_file_size
    • audio_length_seconds
    • sample_rate
    • channels
    • frame_rate
    • mime_type
    • language_code
    • diarisation_result
    • transcription_text
    • transcription_status
    • error_message
    • status_datetime
    • upload_datetime
    • warnings

​Get usage statistics for the customer

GET
/api/v2alpha/transcribe/usage

GET TRANSCRIBE USAGE

Accepts a start date, end date, and interval and returns usage statistics for the customer.

Args

  • start_date_time: start date and time in ISO format (YYYY-MM-DDTHH:MM:SSZ)
  • end_date_time: end date and time in ISO format (YYYY-MM-DDTHH:MM:SSZ)
  • interval: interval for aggregating data (e.g., 'minute', 'hour', 'day')

Returns

  • TranscribeUsageReport: a report containing usage statistics for the customer

Raises

  • HTTPException 400: if the date format is invalid | if the interval is invalid | if the start date is after the end date

​Get usage statistics for the customer › query Parameters

  • start_date_timestring · required

    Start date and time in ISO format (YYYY-MM-DDTHH:MM:SSZ)

  • end_date_timestring · required

    End date and time in ISO format (YYYY-MM-DDTHH:MM:SSZ)

  • intervalstring · required

    Interval for aggregating data (e.g., 'minute', 'hour', 'day')

​Get usage statistics for the customer › Responses

    • total_invocationsinteger · required
    • total_successful_invocationsinteger · required
    • total_failed_invocationsinteger · required
    • total_pending_invocationsinteger · required
    • total_seconds_transcribednumber · required
    • total_tokensinteger · required
    • start_date_timestring · required
    • end_date_timestring · required
    • intervalstring · required
    • usageobject[]