Models/AssemblyAI/Universal-3 Pro

Universal-3 Pro

AssemblyAI 📝 Transcription

AssemblyAI's most advanced speech model — prompt-based architecture for domain-specific customization, speaker diarization, entity detection, sentiment analysis, summarization, and more. No retraining needed.

Specifications

Speed●●●●● Average
ModalitiesInput: audio  ·  Output: text
FeaturesTools: No Streaming: No

Pricing

Included with plan

Use Universal-3 Pro on Zubnet →

More from AssemblyAI

U
Universal-2
AssemblyAI's high-accuracy general-purpose STT — 99 languages, speaker diarization, streaming support. Strong out-of-the-box accuracy at lower cost.
📝 Transcription
U
Universal Streaming
AssemblyAI's ultra-fast streaming STT — designed for voice agents and real-time applications with minimal latency.
📝 Transcription