inference

OpenAI-compatible audio transcription backed by SIE native extract. The multipart upload is bounded at 24 MiB. json, text, srt, verbose_json, and vtt responses are supported; stream=true and diarized_json are rejected explicitly.

post/v1/audio/transcriptions

Request

  • The document declares no server URL.
  • Auth
    • HTTP bearer
    • or API key in header x-api-key

Headers

X-SIE-MACHINE-PROFILEstring nullable

Preferred GPU or machine profile

X-SIE-Poolstring nullable

Explicit pool routing override

X-SIE-SDK-Versionstring nullable

Client SDK version for skew warnings

X-SIE-Remote'forbid'

Require local serving through a current worker execution fence. A selected remote profile returns 400; no verified local worker returns retryable 503. Duplicate or other values return 400.

Request body multipart/form-data

filestring binary required
languagestring nullable
modelstring required
promptstring nullable
response_format'json' | 'text' | 'srt' | 'verbose_json' | 'vtt'
streamboolean nullable
temperaturenumber double nullable
timestamp_granularities[]OpenAITranscriptionTimestampGranularity[] nullable

Response

OpenAI-compatible transcription response

durationnumber double nullable
languagestring nullable
taskstring nullable
textstring required

Changes

    • info

      added the optional property / to the response with the status

    • info

      added the optional property / to the response with the status

    • info

      added the optional property / to the response with the status

    • info

      added the optional property / to the response with the status

    • info

      added the optional property / to the response with the status

    • info

      added the optional property / to the response with the status

    • info

      added the optional property ///// to the response with the status

    • info

      added the new optional header request parameter X-SIE-Remote