Uploaded September 2026 | Updated November 2026, 1 day ago
Universal-3.6 Pro Realtime is live. It leads two independent streaming speech benchmarks: it sits on the Pareto frontier in Daily's Pipecat STT benchmark, and it has the lowest word error rate of any streaming model on Coval's voice-agent leaderboard.
Built for the moments voice agents get wrong:
→ Short answers like "No" and "Nah," heard right 98.5% of the time, even in loud rooms and on phone lines
→ Background voices from the TV or the next desk stay out of the transcript
→ 32 languages from one endpoint, with automatic detection and mid-sentence switching
→ Entity-aware endpointing that waits while callers read out a phone number
Try it: assemblyai.com/blog/universal-3-6-pro-realtime-research
▬▬▬▬▬▬▬▬▬▬▬▬ CONNECT ▬▬▬▬▬▬▬▬▬▬▬▬
🖥️ Website: assemblyai.com
🐦 Twitter: twitter.com/AssemblyAI
🦾 Discord: discord.gg/Cd8MyVJAXd
▶️ Subscribe: youtube.com/c/AssemblyAI?sub_confirmation=1
🔥 We're hiring! Check our open roles: assemblyai.com/careers
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
#MachineLearning #DeepLearning
Universal-3.6 Pro Realtime is live. It leads two independent streaming speech benchmarks: it sits on the Pareto frontier in Daily's Pipecat STT benchmark, and it has the lowest word error rate of any streaming model on Coval's voice-agent leaderboard.
Built for the moments voice agents get wrong:
→ Short answers like "No" and "Nah," heard right 98.5% of the time, even in loud rooms and on phone lines
→ Background voices from the TV or the next desk stay out of the transcript
→ 32 languages from one endpoint, with automatic detection and mid-sentence switching
→ Entity-aware endpointing that waits while callers read out a phone number
Try it: assemblyai.com/blog/universal-3-6-pro-realtime-research
▬▬▬▬▬▬▬▬▬▬▬▬ CONNECT ▬▬▬▬▬▬▬▬▬▬▬▬
🖥️ Website: assemblyai.com
🐦 Twitter: twitter.com/AssemblyAI
🦾 Discord: discord.gg/Cd8MyVJAXd
▶️ Subscribe: youtube.com/c/AssemblyAI?sub_confirmation=1
🔥 We're hiring! Check our open roles: assemblyai.com/careers
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
#MachineLearning #DeepLearning










