Whisper Large v3 is OpenAI’s open-source model for automatic speech recognition (ASR) and speech translation. Trained on over 5 million hours of labeled data, it demonstrates strong generalization across datasets and domains, excelling in zero-shot transcription and translation tasks. It supports 99+ languages and accepts common audio formats including mp3, mp4, wav, webm, flac, and ogg. With 1,550M parameters, it achieves a 10.3% word error rate and suits multilingual transcription in noisy, demanding conditions. It supports timestamp granularities at word and segment levels.
Retired on Nov 6, 2026: requests to this model ID now return an error. These models are live and work with the same API key.
Whisper Large v3 is OpenAI’s open-source model for automatic speech recognition (ASR) and speech translation. Trained on over 5 million hours of labeled data, it demonstrates strong generalization across datasets and domains, excelling in zero-shot transcription and translation tasks.
No. Whisper Large v3 (Free) was retired on NagaAI on Nov 6, 2026, and requests to it now return an error. Live models you can use instead with the same API key: GPT Transcribe, GPT-4o Mini Transcribe and Whisper 1.
It takes audio as input and returns text.
