Nvidia Releases New Open Transcription Model

Source à consulter

Nvidia has recently released a free speech-to-text model that can transcribe up to 40 languages. This model, which is available for all, can be used to transcribe audio recordings, but it does not work in real-time.

This innovation is a significant step forward for meeting and medical transcription tools, but it leaves real-time use to rivals like ElevenLabs.

This new offering provides creative possibilities for developers and designers looking to integrate voice recognition into their applications and products.

Titre et date issus du flux; image déclarée par la page source, réponse image vérifiée. Synthèse à relire.