Today, we released our 🎙 audio transcription🎙 alpha. Built on OpenAI Whisper models, this Speech-to-Text API transcribes 1h of audio as fast as 10s, with a word error rate as low as 1% -- and we want as many people as possible to try this remarkable tool.
To test it, request an API key on gladia.io.
In this video tutorial, AI Engineer at Gladia, Mariano Rodriguez, explains how to transcribe your audio in just a few clicks using our platform.
Ещё видео!