Vince Picone

Today we're releasing our first open source TTS model, TADA! TADA (Text Audio Dual Alignment) is a speech-language model that generates text and audio in one synchronized stream to reduce token-level hallucinations and improve latency. This means: → Zero content hallucinations across 1,000+ test samples → 5x faster than similar-grade LLM-based TTS → Fits much longer audio: 2,048 tokens cover ~700 seconds with TADA vs. ~70 seconds in conventional systems → Free transcript alongside audio with no added latency

Today, we're announcing significant new traction in our voice AI research and development partnerships. Over the past few months, we’ve quietly been expanding our focus on providing frontier voice AI training data to research labs looking to imbue emotion understanding and cutting edge expressivity into their foundation models. We believe some of the most exciting possibilities for deeper speech and emotion understanding will come to fruition this year. By training today’s frontier models to understand the nuances voice interaction—rife with subtle tones of frustration or satisfaction, “aha” moments, chuckles, sighs, backchannels, and interruptions—we believe that labs will unlock new possibilities for voice AI to become a primary interface within many applications. In our experience working with leading research labs and AI-first enterprises, a consistent pattern we’ve seen is a greater need for high-quality datasets and evaluation pipelines than for new algorithms or architectures. Researchers spend up to 80% of their time curating the data they need to diagnose model issues, fix failure modes, and improve model behavior. That’s why Hume is now focused on building the data and evaluation infrastructure needed to train next-generation voice models across industry.  With the right training, we hope that deeper voice understanding and empathy can be translated not just into more efficient interfaces but into better alignment of AI with human well-being. Read more below hume.ai/blog/data-blog-jan

Today we honor Dr. Paul Ekman, whose pioneering work on how we express and perceive emotion laid much of the groundwork our field stands on today. His ideas still shape how we try to understand human feeling with nuance and respect. May he rest in peace. paulekman.com/blog/the-passi…

One performance, infinite voices. Voice Conversion is now live on Hume’s creator studio and API! Generate the same pacing, pronunciation, and intonation with one recording across any voice you choose. Hear it for yourself ⬇️

Why are phone numbers so hard for voice AI?📞🤖 Did you know that reading out something as simple as 555-010-2314 is a weirdly difficult task for TTS? In a recent eval we ran on all the major TTS models, Hume’s Octave 2 comes out at the top with the lowest error rates for phone numbers (without sacrificing its <100ms model latency, high expressivity, and multilingual capabilities). Why is a seemingly simple string of numbers so difficult to nail consistently?