OpenAI's general-purpose speech recognition model trained on diverse multilingual audio data.
OpenAI's Whisper Large V3 for multilingual automatic speech recognition and audio transcription.
Official Python library for the OpenAI API with async support, streaming, and function calling.
Official Python client library for the OpenAI API, supporting GPT, DALL-E, Whisper, and embeddings.
CLIP vision-language model connecting images and text for zero-shot image classification and retrieval.
Official Node.js/TypeScript library for the OpenAI API with full type safety and streaming support.
Fast BPE tokeniser for OpenAI models implemented in Rust with Python bindings for high throughput.