OpenAI

OpenAI’s flagship image model with strong prompt fidelity, crisp text rendering, and instruction-based editing across up to 16 reference images.

Whisper-1 speech-to-text transcription trained on multilingual supervised audio, with a 25 MB upload limit per file.

Controlled self-hosted Whisper Large v3 Turbo transcription with multilingual ASR, translation, VAD, timestamps, subtitles, hotwords, and decoder controls exposed.