Praecise Platform
Menu

Rivier/ Reference/ models

Models transcription create

post/models/v1/audio/transcriptions

The words of a recording (base64 sound, or a sound file of the project's drive) in segments with a start and end in seconds, with the language found; names and terms in the word list are spelled as given. Runs on a route whose models take sound, under the project's limits.

Before you call

Credential
Authorization: Bearer $KEY
Scope
models:write
Graphql
Mutation.modelsTranscriptionCreate
Sdk
models.transcription.create
Cli
models transcription create

Request bodyapplication/json, required

  • modelstringrequired
    A route whose models take sound Pattern: ^[a-z][a-z0-9._-]{0,39}$.
  • audioobject
    • datastringrequired
      base64 At most 22000000 characters.
    • formatstringrequired
      wav, mp3, aac, ogg, flac, webm, m4a At most 12 characters.
  • assetstring (uuid)
    A sound file of the project's drive, in place of audio
  • languagestring
    The language spoken, when known Pattern: ^[a-z]{2,3}(-[A-Za-z0-9]{2,8})?$.
  • wordslist of string
    Names and terms to spell as given
  • purposestring or null

Responses

  • 200application/json
    Success
    • objecttranscriptionrequired
    • languagestring or nullrequired
    • textstringrequired
    • segmentslist of objectrequired
      • startnumberrequired
      • endnumberrequired
      • textstringrequired
    • costobject
      • usdnumberrequired
  • 400application/json
    The request was malformed
    • errorstringrequired
    • messagestring
  • 401application/json
    No valid credential
    • errorstringrequired
    • messagestring
  • 403application/json
    The credential lacks the scope, origin or address
    • errorstringrequired
    • messagestring
  • 429application/json
    Over the key's rate limit; see Retry-After
    • errorstringrequired
    • messagestring

This page as Markdown