Skip to main content
Seta implements OpenAI’s transcription endpoint, so migrating off whisper-1 is a base URL change.
This page is the transcription shim (audio.transcriptions). For the synthesis shim that replaces OpenAI’s TTS — audio.speech, on a different host — see text-to-speech → OpenAI compatibility.

the whole migration

For Kazakh that swap is worth 8.71% WER instead of 44.95% — see accuracy.

parameter compatibility

why language is ignored

Not laziness — it is the point. Kazakh and Russian share one output vocabulary, so the model is never told which language to expect and a speaker can switch mid-sentence. Forcing one language per utterance is exactly the Whisper limitation this model exists to remove, so honouring language would make the model worse. It stays accepted so existing clients don’t break.

srt and vtt

Both are supported and return real subtitles:
verbose_json likewise returns populated segments and words. See word-level timestamps for how the alignment is produced and what the fields mean.

response shapes

Prefer the native /v1/transcribe endpoint for new code — same auth and price, but it also returns audio_seconds, credits_charged, and real-time factor, which the OpenAI shape has no room for.