AllModels

Transcribe audio files using the OpenAI SDK-compatible endpoint. Supports all AllModels STT providers. Accepts WAV, MP3, FLAC, MP4/M4A, OGG, and WebM.

post/allmodels/oai/audio/transcriptions

Request

Base URL
https://api.orthogonal.com/mpp
Auth
none declared
TypeScript
https://skmtc.dev/orthogonal/apis/orthogonal-api-marketplace/docs/allmodels/oai/audio/transcriptions/post.ts
A function with typed inputs. Its response is checked against the schema.

filestring required

Audio file to transcribe (binary upload)

modelstring required

Model ID, e.g. 'deepgram/nova-3', 'assemblyai/universal-3'

languagestring

Language code, e.g. 'en'

response_formatstring

Response format: json, text, srt, verbose_json, vtt

timestamp_granularities[]string[]

Timestamp granularity: word, segment

Successful response

Nov 8, 2026857e915717f4 Revision changes
- breaking
  added required request body
Sep 22, 2026f80c0aab1f7c Revision changes
- info
  endpoint added