AllModels

Generate speech audio from text using the OpenAI SDK-compatible endpoint. Supports all AllModels TTS providers. Returns binary audio in the requested format (mp3, opus, aac, flac, wav, pcm).

post/allmodels/oai/audio/speech

Request

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

modelstring required

Model ID, e.g. 'elevenlabs/eleven_turbo_v2_5', 'deepgram/aura-2', 'cartesia/sonic'

inputstring required

The text to generate audio for

voicestring required

Voice ID, e.g. 'alloy', 'AM:@narrator', or a provider voice ID

response_formatstring

Audio format: mp3, opus, aac, flac, wav, pcm. Default: mp3

speednumber

Speed multiplier (0.25 to 4.0). Not all providers support speed control.

Successful response

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