Skip to content
Albastar Corp.

Transcription models

Access: Keys with the media:generate scope, on an account with media access granted by Albastar Corp.

Speech-to-text models for POST /v1/audio/transcriptions, with the capabilities and languages of each.

A transcription model returns the text of the speech in an audio file, through POST /v1/audio/transcriptions or a transcription media job. The label Speech to text marks a transcription model. Each model page transcribes the reference clip, Narrator A (a synthetic voice), and shows the response the model returned.

  • Parakeetparakeet25 languagesSpeech to textTranscribes speech in 25 European languages, with punctuation and optional word timestamps.