whisper-tiny

Whisper Tiny is a lightweight automatic speech recognition model from OpenAI designed for fast and efficient speech-to-text transcription. With just 39M parameters, it is the smallest model in the Whisper family and is well suited for high-volume, latency-sensitive, and cost-sensitive audio workloads.

The multilingual version supports speech recognition across many languages and can also perform speech translation into English. It is ideal for applications such as voice agents, meeting transcription, subtitles, podcasts, audio indexing, and other workloads where speed and efficiency are prioritized over the accuracy of larger speech recognition models.