Whisper 3 Large · deepinfra

Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification.

Modelo baseTodos os modelos desta baseTodos os modelos do provedorao provedor

Todos os modelos OpenAI em todos os provedores

Preço, $ $0.00045 / minuto

Contexto —

Aceita —

Última verificação 04.11.2026 12:00:14 UTC

Fonte —