Whisper is OpenAI's open-source automatic speech recognition model, available via API as whisper-1. It supports transcription and translation across 50+ languages from audio files up to 25 MB. Accepts formats including mp3, mp4, wav, and webm. Priced per minute of audio duration, billed to the nearest second.
Recent activity on Whisper 1
Total usage per day on OpenRouter
Audio Inputs
15
Audio inputs count all speech or sound files processed by the model. Some requests may process multiple inputs.