API DocsTranscription

Transcription

Transcribe audio files, check job status and export documents.

Endpoint

Convert audio and video files to text — with optional speaker detection.

POST/api/transcribe

Supported formats

MP3, MP4, WAV, M4A, WEBM, OGG — up to 100 MB per file.

MP3WAVM4AOGGWEBM

Parameters

Upload via multipart/form-data with optional configuration parameters.

Parameter	Type	Default	Description
`file`required	`File`	-	The audio or video file to transcribe.
`language`	`string`	-	Language of the recording for better recognition.
`speaker_detection`	`boolean`	`false`	Enable speaker detection (true/false).
`anonymize`	`boolean`	`false`	Automatically anonymize the transcript after processing

Response

The initial response contains the job ID and status 'processing'.

200Initial response after upload

{
  "job_id": "job_abc123def456",
  "status": "processing",
  "created_at": "2025-01-15T10: 30: 00Z"
}

Completed transcription

Query the status endpoint to get the finished transcription.

200Response with status 'completed'

{
  "job_id": "job_abc123def456",
  "status": "completed",
  "result": {
    "text": "Good morning, welcome to the meeting. Let us begin with the quarterly review...",
    "duration_seconds": 342,
    "language": "en",
    "segments": [
      {
        "speaker": "Speaker 1",
        "start": 0,
        "end": 3.2,
        "text": "Good morning, welcome to the meeting."
      },
      {
        "speaker": "Speaker 2",
        "start": 3.5,
        "end": 7.1,
        "text": "Let us begin with the quarterly review."
      }
    ]
  }
}

Speaker detection

With speaker detection enabled, sections are labeled with speaker identifiers.

Anonymize Transcript

With the anonymize parameter, the transcript is automatically processed through the anonymization pipeline after transcription. Personal names, locations, and other sensitive data are detected and replaced with placeholders.

1curl -X POST https://app.anymize.ai/api/transcribe \
2  -H #86efac">"Authorization: Bearer YOUR_API_KEY" \
3  -F #86efac">"file=@meeting.mp3" \
4  -F #86efac">"language=de" \
5  -F #86efac">"speaker_detection=true" \
6  -F #86efac">"anonymize=true"

Anonymization + Transcription

The anonymized transcript is available via the status endpoint. Hash pairs for de-anonymization are available at /api/status/{jobId}/strings.

Example request

1curl -X POST https://app.anymize.ai/api/transcribe \
2  -H #86efac">"Authorization: Bearer YOUR_API_KEY" \
3  -F #86efac">"file=@meeting-recording.mp3" \
4  -F #86efac">"language=en" \
5  -F #86efac">"speaker_detection=true"

Job Status

Endpoint

Check the current status of an asynchronous job.

GET/api/status/{jobId}

Parameters

Parameter	Type	Default	Description
`jobId`required	`string`	-	The job ID you received when creating the job.

Status values

A job goes through the following states:

processingThe job is currently being processed.

completedThe job is complete — result is available.

failedThe job failed — error message is available.

Status: Processing

200Response during processing

{
  "job_id": "job_abc123def456",
  "status": "processing",
  "progress": 45,
  "created_at": "2025-01-15T10: 30: 00Z"
}

Status: Completed

When the job is complete, the response contains the result.

200Response for a completed job

{
  "job_id": "job_abc123def456",
  "status": "completed",
  "result": {
    "text": "The anonymized document content...",
    "entities_found": 12,
    "processing_time_ms": 2340
  },
  "created_at": "2025-01-15T10: 30: 00Z",
  "completed_at": "2025-01-15T10: 30: 04Z"
}

Status: Failed

200Response for a failed job

{
  "job_id": "job_abc123def456",
  "status": "failed",
  "error": {
    "message": "Unsupported file format",
    "code": "invalid_format"
  },
  "created_at": "2025-01-15T10: 30: 00Z"
}

Polling strategy

Query the status at regular intervals until the job is finished.

Tip

Start with a 2-second interval and increase exponentially up to 30 seconds.

1# Poll every 3 seconds until completed
2while true; do
3  RESULT=$(curl -s https://app.anymize.ai/api/status/job_abc123def456 \
4    -H #86efac">"Authorization: Bearer YOUR_API_KEY")
5  STATUS=$(echo $RESULT | jq -r #86efac">'.status')
6  echo #86efac">"Status: $STATUS"
7  if [ #86efac">"$STATUS" = "completed" ] || [ "$STATUS" = "failed" ]; then
8    echo $RESULT | jq .
9    break
10  fi
11  sleep 3
12done

Document Export

Endpoint

Export completed transcriptions in various formats.

GET/api/v1/jobs/{jobId}/export

Parameters

Specify job ID, format, and optionally a variant.

Parameter	Type	Default	Description
`jobId`required	`string`	-	The job ID of the completed transcription.
`format`	`string`	`pdf`	Output format: pdf, docx, or txt.
`textType`	`string`	`anonymized`	Export variant (e.g. anonymized or original).

Available formats

pdfPDF — Formatted document with layout and metadata.application/pdf

docxDOCX — Editable Word document.application/vnd.openxmlformats-officedocument.wordprocessingml.document

txtTXT — Plain text without formatting.text/plain

Response headers

The download includes appropriate Content-Type and Content-Disposition headers.

200Example response headers

Content-Type: application/pdf
Content-Disposition: attachment; filename="document_anonymized.pdf"
Content-Length: 245832

Export variants

Choose between the original and anonymized version.

Tip

Use the anonymized variant when sharing with third parties.

Example requests

Export as PDF

1curl -OJ https://app.anymize.ai/api/v1/jobs/job_abc123def456/export?format=pdf \
2  -H #86efac">"Authorization: Bearer YOUR_API_KEY"

Export as DOCX

1curl -OJ #86efac">"https://app.anymize.ai/api/v1/jobs/job_abc123def456/export?format=docx&textType=original" \
2  -H #86efac">"Authorization: Bearer YOUR_API_KEY"

Error cases

Common export errors and their causes.

404Not Found

{
  "error": {
    "message": "Job not found or not yet completed",
    "type": "not_found",
    "code": "job_not_found"
  }
}