GPT Transcribe improves on its predecessor but can't catch ElevenLabs, Google, or Mistral on error rates
OpenAI has released GPT Transcribe and GPT Live Transcribe, two new speech recognition models accessible via its API. Benchmarks indicate that while these models improve on OpenAI's previous offerings, they still have higher error rates compared to those from ElevenLabs, Google, and Mistral.
Why it matters: OpenAI's new models increase competition in speech recognition, but the field remains led by other providers in terms of accuracy.
Full story at: The Decoder ↗