whisper
openai
Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multitasking model that can perform multilingual speech recognition, speech translation, and language identification.
- Context window
- — tokens
- Input cost
- $0.00 / 1M
- Output cost
- $0.00 / 1M
- Latency (p50)
- —
