POST /v1/audio/transcriptions

Speech-to-text endpoint.

Inference APIs

Transcribe audio via multipart form upload and return the upstream JSON body unchanged.

POST/v1/audio/transcriptions

Request

  • Auth: tenant auth when enabled; otherwise dev mode is open
  • Content-Type: multipart/form-data
  • Max body size: 64 MiB

Request fields

FieldTypeRequiredNotes
modelform fieldyesGateway requires it to resolve the route
fileform fieldyes for upstream transcription APIsForwarded unchanged
languageform fieldnoForwarded unchanged
promptform fieldnoForwarded unchanged
response_formatform fieldnoForwarded unchanged
temperatureform fieldnoForwarded unchanged
other upstream fieldsform fieldnoForwarded unchanged

Response schema

FieldTypeRequiredNotes
textstringyesUpstream transcription text

Errors

HTTPCodeWhen
400invalid_request_errorInvalid content type, missing boundary, malformed multipart body, or missing model
400provider_not_configuredProvider missing from config or unavailable
400invalid_request_errorProvider does not support audio transcriptions
502upstream_errorUpstream request failed or response could not be read

Notes

  • The gateway forwards the multipart body as-is, including the boundary.
  • Response content is raw upstream JSON.
  • The response example is copyable, but the production payload is just upstream JSON text.