Whisper

Whisper is a family of open-source speech recognition models released by OpenAI. It transcribes spoken audio into text and the multilingual large-v3 models can translate speech from many languages directly into English. The weights are published under the permissive MIT license, so you can download them and run them on your own hardware.

The current open release is large-v3-turbo, an optimized version of large-v3 released in September 2024. It keeps almost all of the accuracy of the full large-v3 model while running about 8x faster, which makes it far more practical for batch jobs and near-real-time use. The full large-v3 checkpoint is still available when you want the highest possible quality. Turbo itself is not trained for translation tasks; use the other multilingual large-v3 checkpoints for speech-to-English translation.

Alongside the open models, OpenAI offers hosted transcription through its API. The original endpoint, whisper-1, along with gpt-4o-transcribe, gpt-4o-mini-transcribe, and gpt-4o-transcribe-diarize, were deprecated in August 2026 and are scheduled for removal from the API on February 26, 2027. OpenAI now recommends gpt-transcribe for file-based transcription and gpt-live-transcribe for live streaming audio. gpt-realtime-whisper and gpt-realtime-translate are also listed on OpenAI's pricing page.

Pricing splits into two tracks. The open-source models are free to use — you only pay for your own compute. The hosted API is billed per minute of audio: gpt-transcribe costs $0.0045/min, gpt-live-transcribe and gpt-realtime-whisper cost $0.017/min, and gpt-realtime-translate costs $0.034/min. The deprecated whisper-1, gpt-4o-transcribe, gpt-4o-mini-transcribe, and gpt-4o-transcribe-diarize models remain billable at their existing per-minute rates until they are removed on February 26, 2027.

Accuracy varies a lot by language. Whisper was trained on around 99 languages, but quality is strongest for high-resource languages like English and drops noticeably for less common ones. Running the larger models locally also needs a capable GPU, and the model can occasionally hallucinate text during long silences.

Whisper is a good fit if you want a free, self-hostable transcription engine, need broad multilingual coverage, or want a managed API without building your own pipeline. Choose the hosted gpt-transcribe or gpt-live-transcribe models if you need file-based or live transcription through OpenAI's API, and plan to migrate away from any integration still using the deprecated endpoints.