OpenAI: whisper-1:free
whisper-1:free
Audio (entrée)
Publié Feb 28, 2023Mis à jour Feb 28, 2023
OpenAI's general-purpose speech recognition model. Trained on a large dataset of diverse audio, it is a multitasking model that can perform multilingual speech recognition, speech translation to English, and language identification. The API version is optimized for high accuracy and robust performance across various accents and noisy environments.
Mode audio_transcription
Tarification
Prix en entrée
$0.00/ 1 M jetons
Prix en sortie
$0.00/ 1 M jetons
Points d'accès compatibles openaiÉditeur OpenAI
Performance
Chargement des performances...
Utilisation et classement
Chargement de l'utilisation...