ainewsblitz.com

Breaking

OpenAI Adds Two New Speech-to-Text Models, GPT-Live-Transcribe and GPT-Transcribe, to Its API

OpenAI Adds Two New Speech-to-Text Models, GPT-Live-Transcribe and GPT-Transcribe, to Its API
  • Foundation Models
  • Media Generation

OpenAI has introduced two new audio transcription models to its API, splitting real-time and file-based speech-to-text into dedicated systems and claiming sharply lower error rates than its earlier Whisper-1 model. The company announced GPT-Live-Transcribe, aimed at low-latency live transcription, and GPT-Transcribe, built for asynchronous transcription of completed audio files and batch workloads, with both available for developers immediately.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,934 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year