AssemblyAI Universal-3.5 Pro

Universal-3.5 Pro is AssemblyAI’s advanced speech-to-text model for complex, real-world audio, now available through Speechall. It supports code-switching across 18 languages, improved speaker labeling during interruptions and overlapping speech, and contextual prompting for domain-specific terms, names, and background information. Provide relevant context in plain language, and the model adjusts its transcription to better reflect what was said, which language was spoken, and who said it.