OpenAI Whisper Large V3 Turbo

A faster, slimmed-down Whisper Large V3 that keeps most of its accuracy and returns timed segments for subtitles.

Whisper Large V3 Turbo is a cloud speech-to-text model from OpenAI. It transcribes spoken audio into written text. It handles multiple spoken languages and can return timestamped segments along with the transcript. It also supports an optional text prompt that guides the spelling of names and terms. It runs through OpenRouter using your own API key, from about $0.0002 per minute of audio. It also runs on your own hardware through Hugging Face, with no API key and no per-use fees.